{ "title": "128-Episode 20-Task Radar", "status": "pass", "generated_at_utc": "2026-06-22T13:13:58+00:00", "description": "Selected 128-episode metadata/raw baselines plus verified Qwen3-Omni v6, Cosmos3-Super, and Cosmos3-Nano diagnostics. Every method has 20 records; numeric scores appear only where the public artifact produced that task target.", "task_count": 20, "method_count": 7, "method_task_record_count": 140, "scored_method_task_count": 140, "normalization_policy": { "higher_is_better": "bounded metrics are plotted directly on 0-1 axes after clipping to [0, 1]", "lower_is_better": "lower-error metrics are converted to best_observed_value / raw_value within the same task", "raw_values": "raw metric values, metric keys, and sources are retained in this JSON; the SVG is an overview, not a replacement for the metric table", "radar_visual_radius": "SVG radar panels use sqrt(normalized_score) for radius so polygon area remains closer to the score and low-valued but real differences stay visible; the JSON and matrix retain exact linear normalized_score values", "result_record_policy": "every method has 20 task records; the current public release has 180/180 scored rows with proxy flags and reasons retained where compact substitute targets are used", "foundation_model_overlay": "Qwen3-Omni and Cosmos3 are grouped in the foundation-model radar panel. All current public model rows have 20 scored task records, with source paths retained for every metric.", "metadata_128_overlay": "128-episode aligned baselines are grouped in the metadata/text radar panel. Numeric scores come from JSONL metadata/text tasks plus staged sensor-block targets when the processed target exists.", "raw_128_overlay": "128-episode raw-feature baselines are grouped in the raw-feature radar panel. Eighteen axes use direct task targets; interaction text and camera-view sync are completed with documented compact proxies because raw interaction strings and paired video-view embeddings are absent from the 128 export." }, "chart_design": { "mode": "grouped_small_multiples", "method_count": 7, "reason": "This split view has 7 methods and 140 method-task records; grouped radar panels keep related methods readable while retaining the unified source matrix.", "groups": [ { "id": "metadata_128", "title": "128-episode metadata/text", "series_ids": [ "metadata128_simple", "metadata128_neural_mlp" ] }, { "id": "raw_128", "title": "128-episode raw features", "series_ids": [ "raw128_simple", "raw128_neural_mlp" ] }, { "id": "foundation_models", "title": "Foundation-model probes", "series_ids": [ "qwen3_omni_v6_lora", "cosmos3_super_reasoner", "cosmos3_nano_future_window" ] } ], "visual_radius_transform": "sqrt(normalized_score)", "exact_value_source": "docs/data/task_method_20_result_matrix.json" }, "source_unified_radar": "docs/data/unified_task_model_radar.json", "source_result_matrix": "docs/data/task_method_20_result_matrix.json", "series": [ { "id": "metadata128_simple", "label": "128ep Aligned Simple", "short_label": "128-S", "color": "#ffd166", "kind": "partial_128_episode_aligned_baseline", "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available", "stroke_dasharray": "9 6", "method_detail": "128-episode aligned simple baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.", "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges", "result_record_count": 20, "scored_task_count": 20, "covered_task_count": 20, "proxy_scored_task_count": 1, "scoreless_task_count": 0, "unsupported_task_count": 0, "not_evaluated_task_count": 0, "status_counts": { "proxy_scored": 1, "scored": 19 }, "coverage_fraction": 1.0, "result_record_fraction": 1.0 }, { "id": "metadata128_neural_mlp", "label": "128ep Aligned NN", "short_label": "128-NN", "color": "#f472b6", "kind": "partial_128_episode_aligned_baseline", "scope": "128 selected episodes, JSONL metadata/text plus staged sensor-block targets where available", "stroke_dasharray": "3 6", "method_detail": "128-episode aligned MLP baselines: JSONL metadata/text tasks plus staged sensor-block tasks where the processed target exists.", "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges", "result_record_count": 20, "scored_task_count": 20, "covered_task_count": 20, "proxy_scored_task_count": 1, "scoreless_task_count": 0, "unsupported_task_count": 0, "not_evaluated_task_count": 0, "status_counts": { "proxy_scored": 1, "scored": 19 }, "coverage_fraction": 1.0, "result_record_fraction": 1.0 }, { "id": "raw128_simple", "label": "128ep Raw Simple", "short_label": "128-RS", "color": "#f59e0b", "kind": "complete_128_episode_raw_feature_baseline", "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes", "stroke_dasharray": "8 4", "method_detail": "128-episode 4430-dim sensor NPZ simple heads; tasks 15/19 use compact proxies.", "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges", "result_record_count": 20, "scored_task_count": 20, "covered_task_count": 20, "proxy_scored_task_count": 2, "scoreless_task_count": 0, "unsupported_task_count": 0, "not_evaluated_task_count": 0, "status_counts": { "proxy_scored": 2, "scored": 18 }, "coverage_fraction": 1.0, "result_record_fraction": 1.0 }, { "id": "raw128_neural_mlp", "label": "128ep Raw NN", "short_label": "128-RN", "color": "#22d3ee", "kind": "complete_128_episode_raw_feature_baseline", "scope": "128 selected episodes, staged 4430-dim sensor NPZ features; 2 compact proxy axes", "stroke_dasharray": "2 5", "method_detail": "128-episode 4430-dim sensor NPZ MLP heads; tasks 15/19 use compact proxies.", "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges", "result_record_count": 20, "scored_task_count": 20, "covered_task_count": 20, "proxy_scored_task_count": 2, "scoreless_task_count": 0, "unsupported_task_count": 0, "not_evaluated_task_count": 0, "status_counts": { "proxy_scored": 2, "scored": 18 }, "coverage_fraction": 1.0, "result_record_fraction": 1.0 }, { "id": "qwen3_omni_v6_lora", "label": "Qwen3-Omni v6 LoRA", "short_label": "Qwen3", "color": "#9bb8ff", "kind": "partial_128_episode_foundation_model_overlay", "scope": "128 selected episodes, held-out test", "stroke_dasharray": "7 7", "method_detail": "Verified held-out Qwen3-Omni v6 LoRA metrics, plus task 16 and any completed private-GPU future/retrieval/sensor-target probes scored from task-specific JSON.", "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges", "result_record_count": 20, "scored_task_count": 20, "covered_task_count": 20, "proxy_scored_task_count": 0, "scoreless_task_count": 0, "unsupported_task_count": 0, "not_evaluated_task_count": 0, "status_counts": { "scored": 20 }, "coverage_fraction": 1.0, "result_record_fraction": 1.0 }, { "id": "cosmos3_super_reasoner", "label": "Cosmos3-Super Reasoner", "short_label": "C3-S", "color": "#ff9c7a", "kind": "partial_128_episode_foundation_model_overlay", "scope": "128 selected episodes, held-out test", "stroke_dasharray": "4 7", "method_detail": "Verified Cosmos3-Super base-weight Reasoner JSON-task evaluation, plus task 5/8/9/10/11/12/13/14/16/17/18/19/20 probes where public metrics exist.", "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges", "result_record_count": 20, "scored_task_count": 20, "covered_task_count": 20, "proxy_scored_task_count": 0, "scoreless_task_count": 0, "unsupported_task_count": 0, "not_evaluated_task_count": 0, "status_counts": { "scored": 20 }, "coverage_fraction": 1.0, "result_record_fraction": 1.0 }, { "id": "cosmos3_nano_future_window", "label": "Cosmos3-Nano Future Window", "short_label": "C3-N", "color": "#d9c7ff", "kind": "partial_128_episode_world_model_overlay", "scope": "128 selected episodes, held-out test", "stroke_dasharray": "2 7", "method_detail": "Verified Cosmos3-Nano future-window compatibility metrics, plus model-output probes for tasks 2/5/7/8/10/11/12/13/14/15/16/17/18/19 and a derived task-20 boundary timing probe scored from held-out future-window artifacts.", "plotted_as": "grouped small-multiple radar panel with direct legend and coverage badges", "result_record_count": 20, "scored_task_count": 20, "covered_task_count": 20, "proxy_scored_task_count": 0, "scoreless_task_count": 0, "unsupported_task_count": 0, "not_evaluated_task_count": 0, "status_counts": { "scored": 20 }, "coverage_fraction": 1.0, "result_record_fraction": 1.0 } ], "tasks": [ { "task_number": 1, "task_id": "timeline_action", "label": "Action Recognition", "axis_label": "01 Action Recognition", "short_label": "Action", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.008252821966746326, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/timeline_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.008252821966746326, "raw_text": "0.0083", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.004175793689174209, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/timeline_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.004175793689174209, "raw_text": "0.0042", "status_label": "scored" }, "raw128_simple": { "raw": 0.002915061325704321, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/timeline_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.002915061325704321, "raw_text": "0.0029", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.0014955083181204041, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/timeline_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0014955083181204041, "raw_text": "0.0015", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.0028830723979596335, "metric_key": "action_macro_f1", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0028830723979596335, "raw_text": "0.0029", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.0008284021201089245, "metric_key": "action_macro_f1", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0008284021201089245, "raw_text": "0.0008", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.007936507936507936, "metric_key": "action_accuracy_from_retrieved_future", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.007936507936507936, "raw_text": "0.0079", "status_label": "scored" } } }, { "task_number": 2, "task_id": "timeline_subtask", "label": "Procedure Step Recognition", "axis_label": "02 Procedure Step Recognition", "short_label": "Step", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.00019512195121951218, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/timeline_subtask/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.00019512195121951218, "raw_text": "0.0002", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 7.207207207207208e-05, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/timeline_subtask/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 7.207207207207208e-05, "raw_text": "0.0001", "status_label": "scored" }, "raw128_simple": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/timeline_subtask/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 7.35632183908046e-05, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/timeline_subtask/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 7.35632183908046e-05, "raw_text": "0.0001", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.0037313432835820895, "metric_key": "subtask_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0037313432835820895, "raw_text": "0.0037", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.0, "metric_key": "subtask_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.0, "metric_key": "timeline_subtask_macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_current_subtask_object_relevance_patched_textonly_20260621/timeline_subtask/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" } } }, { "task_number": 3, "task_id": "transition_detection", "label": "Action Boundary Detection", "axis_label": "03 Action Boundary Detection", "short_label": "Boundary", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.29652162550029315, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/transition_detection/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.29652162550029315, "raw_text": "0.2965", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.4841733292368365, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/transition_detection/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.4841733292368365, "raw_text": "0.4842", "status_label": "scored" }, "raw128_simple": { "raw": 0.4203613574238283, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/transition_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.4203613574238283, "raw_text": "0.4204", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.4902206914147213, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/transition_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.4902206914147213, "raw_text": "0.4902", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.9898313492063492, "metric_key": "transition_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.9898313492063492, "raw_text": "0.9898", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.36830357142857145, "metric_key": "transition_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.36830357142857145, "raw_text": "0.3683", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.9682539682539683, "metric_key": "transition_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.9682539682539683, "raw_text": "0.9683", "status_label": "scored" } } }, { "task_number": 4, "task_id": "next_action", "label": "Next-Action Prediction", "axis_label": "04 Next-Action Prediction", "short_label": "Next act", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.006514774539765508, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.006514774539765508, "raw_text": "0.0065", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.004910507980164745, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.004910507980164745, "raw_text": "0.0049", "status_label": "scored" }, "raw128_simple": { "raw": 0.003285273363482094, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.003285273363482094, "raw_text": "0.0033", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.0018477984371755407, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0018477984371755407, "raw_text": "0.0018", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.04305335446381405, "metric_key": "next_action_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.04305335446381405, "raw_text": "0.0431", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.013392857142857142, "metric_key": "next_action_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.013392857142857142, "raw_text": "0.0134", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.007936507936507936, "metric_key": "action_accuracy_from_retrieved_future", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.007936507936507936, "raw_text": "0.0079", "status_label": "scored" } } }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "label": "Hand Trajectory Forecasting", "axis_label": "05 Hand Trajectory Forecasting", "short_label": "Hand traj", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "mpjpe", "metric_name": "MPJPE", "metric_direction": "lower", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 8.817333221435547, "metric_key": "mpjpe", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.012231610603598841, "raw_text": "8.817", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.429434210062027, "metric_key": "mpjpe", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.25114484128127007, "raw_text": "0.4294", "status_label": "scored" }, "raw128_simple": { "raw": 0.2729249894618988, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.39516420515180267, "raw_text": "0.2729", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.18475216627120972, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.5837560051580399, "raw_text": "0.1848", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.7216105627267382, "metric_key": "hand_trajectory_forecast_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_sensor_target_probes_a100_20260619T000000Z/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.149457605109387, "raw_text": "0.7216", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.8915253522315043, "metric_key": "hand_trajectory_forecast_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.12097265238372007, "raw_text": "0.8915", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.6912806884333101, "metric_key": "hand_trajectory_forecast_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.15601504328321764, "raw_text": "0.6913", "status_label": "scored" } } }, { "task_number": 6, "task_id": "contact_prediction", "label": "Contact State Prediction", "axis_label": "06 Contact State Prediction", "short_label": "Contact", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.4381481308057444, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/contact_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.4381481308057444, "raw_text": "0.4381", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.5682695682695682, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/contact_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.5682695682695682, "raw_text": "0.5683", "status_label": "scored" }, "raw128_simple": { "raw": 0.886990707397193, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/contact_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.886990707397193, "raw_text": "0.8870", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 1.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/contact_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 1.0, "raw_text": "1.000", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.8177083333333334, "metric_key": "contact_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.8177083333333334, "raw_text": "0.8177", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.32142857142857145, "metric_key": "contact_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.32142857142857145, "raw_text": "0.3214", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.7433862433862434, "metric_key": "contact_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.7433862433862434, "raw_text": "0.7434", "status_label": "scored" } } }, { "task_number": 7, "task_id": "object_relevance", "label": "Object Relevance Prediction", "axis_label": "07 Object Relevance Prediction", "short_label": "Objects", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "micro_f1", "metric_name": "micro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.17764578833693304, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_relevance/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.17764578833693304, "raw_text": "0.1776", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.18662723837686876, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_relevance/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.18662723837686876, "raw_text": "0.1866", "status_label": "scored" }, "raw128_simple": { "raw": 0.0655376369662084, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/object_relevance/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0655376369662084, "raw_text": "0.0655", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.1765890386972509, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/object_relevance/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.1765890386972509, "raw_text": "0.1766", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.3064982378331287, "metric_key": "object_micro_f1", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.3064982378331287, "raw_text": "0.3065", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.13704276146316333, "metric_key": "object_micro_f1", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.13704276146316333, "raw_text": "0.1370", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.00047209895194032665, "metric_key": "object_relevance_micro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_current_subtask_object_relevance_patched_textonly_20260621/object_relevance/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.00047209895194032665, "raw_text": "0.0005", "status_label": "scored" } } }, { "task_number": 8, "task_id": "caption_grounding", "label": "Language Grounding", "axis_label": "08 Language Grounding", "short_label": "Language", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "mrr", "metric_name": "MRR", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.002332374220713973, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/caption_grounding/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.002332374220713973, "raw_text": "0.0023", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.008236799389123917, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/caption_grounding/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.008236799389123917, "raw_text": "0.0082", "status_label": "scored" }, "raw128_simple": { "raw": 0.011138836853206158, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/caption_grounding/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.011138836853206158, "raw_text": "0.0111", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.0063402121886610985, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/caption_grounding/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0063402121886610985, "raw_text": "0.0063", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.8764467592592605, "metric_key": "caption_grounding_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.8764467592592605, "raw_text": "0.8764", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.30639899644580487, "metric_key": "caption_grounding_iou", "source": "results/omni_finetune/model_output_task_probes_20260616/caption_grounding/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.30639899644580487, "raw_text": "0.3064", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.5221041086644663, "metric_key": "caption_grounding_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/caption_grounding/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.5221041086644663, "raw_text": "0.5221", "status_label": "scored" } } }, { "task_number": 9, "task_id": "cross_modal_retrieval", "label": "Cross-Modal Retrieval", "axis_label": "09 Cross-Modal Retrieval", "short_label": "X-modal", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "mrr", "metric_name": "MRR", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.002587692579254508, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.002587692579254508, "raw_text": "0.0026", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.0026067993603646755, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.0026067993603646755, "raw_text": "0.0026", "status_label": "scored" }, "raw128_simple": { "raw": 0.003459817497059703, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.003459817497059703, "raw_text": "0.0035", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.002535284962505102, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.002535284962505102, "raw_text": "0.0025", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.5080191798941732, "metric_key": "cross_modal_retrieval_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.5080191798941732, "raw_text": "0.5080", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.6628490677465636, "metric_key": "cross_modal_retrieval_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.6628490677465636, "raw_text": "0.6628", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.022138720585222767, "metric_key": "future_retrieval_mrr", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.022138720585222767, "raw_text": "0.0221", "status_label": "scored" } } }, { "task_number": 10, "task_id": "modality_reconstruction", "label": "Cross-Modal Reconstruction", "axis_label": "10 Cross-Modal Reconstruction", "short_label": "Recon", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "r2", "metric_name": "R2", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": -190.66106203944798, "metric_key": "r2", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/modality_reconstruction/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "-190.66", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": -0.43481132003942147, "metric_key": "r2", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/modality_reconstruction/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "-0.4348", "status_label": "scored" }, "raw128_simple": { "raw": -1.3450960391924882, "metric_key": "r2", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/modality_reconstruction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "-1.345", "status_label": "scored" }, "raw128_neural_mlp": { "raw": -1.3974418160502369, "metric_key": "r2", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/modality_reconstruction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "-1.397", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.9670547540707002, "metric_key": "modality_reconstruction_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_sensor_target_probes_a100_20260619T000000Z/modality_reconstruction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.9670547540707002, "raw_text": "0.9671", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.9939466801653591, "metric_key": "modality_reconstruction_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/modality_reconstruction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.9939466801653591, "raw_text": "0.9939", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.0002873382957286892, "metric_key": "feature_reconstruction_quality", "source": "results/omni_finetune/model_output_task_probes_20260616/modality_reconstruction/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0002873382957286892, "raw_text": "0.0003", "status_label": "scored" } } }, { "task_number": 11, "task_id": "temporal_order", "label": "Temporal Order Verification", "axis_label": "11 Temporal Order Verification", "short_label": "Order", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "f1", "metric_name": "F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.4198864140782312, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/temporal_order/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.4198864140782312, "raw_text": "0.4199", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.8252408266656923, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/temporal_order/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.8252408266656923, "raw_text": "0.8252", "status_label": "scored" }, "raw128_simple": { "raw": 0.49824413370686593, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/temporal_order/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.49824413370686593, "raw_text": "0.4982", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.8030047098504103, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/temporal_order/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.8030047098504103, "raw_text": "0.8030", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.40984631701404173, "metric_key": "temporal_order_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_order_sync_time_probes_a100_20260617T132500Z/temporal_order/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.40984631701404173, "raw_text": "0.4098", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.6286317274823326, "metric_key": "temporal_order_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/temporal_order/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.6286317274823326, "raw_text": "0.6286", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.5954109425716205, "metric_key": "temporal_order_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_future_order_misalignment_patched_textonly_20260621/temporal_order/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.5954109425716205, "raw_text": "0.5954", "status_label": "scored" } } }, { "task_number": 12, "task_id": "misalignment_detection", "label": "Multimodal Synchronization Detection", "axis_label": "12 Multimodal Synchronization Detection", "short_label": "Sync", "provenance_source": "walkthrough_backed_task_contract", "metric_key": "f1", "metric_name": "F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.49980060227663614, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/misalignment_detection/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.49980060227663614, "raw_text": "0.4998", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.7773773780941162, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/misalignment_detection/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.7773773780941162, "raw_text": "0.7774", "status_label": "scored" }, "raw128_simple": { "raw": 0.4958867673901769, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/misalignment_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.4958867673901769, "raw_text": "0.4959", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.8272709077974252, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/misalignment_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.8272709077974252, "raw_text": "0.8273", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.3344936184319576, "metric_key": "misalignment_detection_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_order_sync_time_probes_a100_20260617T132500Z/misalignment_detection/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.3344936184319576, "raw_text": "0.3345", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.37271645981034185, "metric_key": "misalignment_detection_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/misalignment_detection/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.37271645981034185, "raw_text": "0.3727", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.477201691802725, "metric_key": "misalignment_detection_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_future_order_misalignment_patched_textonly_20260621/misalignment_detection/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.477201691802725, "raw_text": "0.4772", "status_label": "scored" } } }, { "task_number": 13, "task_id": "long_horizon_next_action", "label": "Long-Horizon Next-Action Forecasting", "axis_label": "13 Long-Horizon Next-Action Forecasting", "short_label": "Long act", "provenance_source": "historical_result_bundle", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.004579592783699693, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.004579592783699693, "raw_text": "0.0046", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.0029821307969142615, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.0029821307969142615, "raw_text": "0.0030", "status_label": "scored" }, "raw128_simple": { "raw": 0.0024280172369056294, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0024280172369056294, "raw_text": "0.0024", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.001063859887389299, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.001063859887389299, "raw_text": "0.0011", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.0023356666867101906, "metric_key": "long_horizon_next_action_macro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_future_task_probes_a100_20260616T143608Z/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0023356666867101906, "raw_text": "0.0023", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.008807588075880758, "metric_key": "long_horizon_next_action_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/long_horizon_next_action/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.008807588075880758, "raw_text": "0.0088", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.0024906600249066007, "metric_key": "long_horizon_next_action_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/long_horizon_next_action/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0024906600249066007, "raw_text": "0.0025", "status_label": "scored" } } }, { "task_number": 14, "task_id": "next_subtask_forecast", "label": "Long-Horizon Next-Subtask Forecasting", "axis_label": "14 Long-Horizon Next-Subtask Forecasting", "short_label": "Long step", "provenance_source": "historical_result_bundle", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.0001206030150753769, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.0001206030150753769, "raw_text": "0.0001", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 2.086049543676662e-05, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 2.086049543676662e-05, "raw_text": "0.0000", "status_label": "scored" }, "raw128_simple": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.004206715978529301, "metric_key": "next_subtask_forecast_macro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_future_task_probes_a100_20260616T143608Z/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.004206715978529301, "raw_text": "0.0042", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.0, "metric_key": "next_subtask_forecast_macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.006614876224708678, "metric_key": "next_subtask_forecast_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/next_subtask_forecast/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.006614876224708678, "raw_text": "0.0066", "status_label": "scored" } } }, { "task_number": 15, "task_id": "interaction_text_prediction", "label": "Interaction Text Prediction", "axis_label": "15 Interaction Text Prediction", "short_label": "Interact txt", "provenance_source": "historical_result_bundle", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": true, "values": { "metadata128_simple": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "raw128_simple": { "raw": 0.012611998261547169, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "proxy_scored", "reason": "documented compact proxy completion for this raw128 task axis", "normalized_score": 0.012611998261547169, "raw_text": "0.0126", "status_label": "proxy scored" }, "raw128_neural_mlp": { "raw": 0.009791421280985521, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "proxy_scored", "reason": "documented compact proxy completion for this raw128 task axis", "normalized_score": 0.009791421280985521, "raw_text": "0.0098", "status_label": "proxy scored" }, "qwen3_omni_v6_lora": { "raw": 0.4318674027510605, "metric_key": "macro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_interaction_text_task15_a100_20260620T010305Z/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.4318674027510605, "raw_text": "0.4319", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.17949512355264183, "metric_key": "macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_interaction_text_task15_textonly_v1_20260620T1558Z/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.17949512355264183, "raw_text": "0.1795", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.1788367958939587, "metric_key": "macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_interaction_text_task15_patched_textonly_20260621/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.1788367958939587, "raw_text": "0.1788", "status_label": "scored" } } }, { "task_number": 16, "task_id": "action_object_relation", "label": "Action-Object Relation Prediction", "axis_label": "16 Action-Object Relation Prediction", "short_label": "Act+obj", "provenance_source": "historical_result_bundle", "metric_key": "macro_f1", "metric_name": "macro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "raw128_simple": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/action_object_relation/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/action_object_relation/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.0002220083079671497, "metric_key": "action_object_relation_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0002220083079671497, "raw_text": "0.0002", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.0, "metric_key": "action_object_relation_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0, "raw_text": "0.0000", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.002794157670325683, "metric_key": "action_object_relation_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.002794157670325683, "raw_text": "0.0028", "status_label": "scored" } } }, { "task_number": 17, "task_id": "object_set_forecast", "label": "Future Object-Set Forecasting", "axis_label": "17 Future Object-Set Forecasting", "short_label": "Future obj", "provenance_source": "historical_result_bundle", "metric_key": "micro_f1", "metric_name": "micro-F1", "metric_direction": "higher", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.17656983343047333, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.17656983343047333, "raw_text": "0.1766", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.17418550827844048, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.17418550827844048, "raw_text": "0.1742", "status_label": "scored" }, "raw128_simple": { "raw": 0.06469493412657774, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/object_set_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.06469493412657774, "raw_text": "0.0647", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.17523098630012288, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/object_set_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.17523098630012288, "raw_text": "0.1752", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.1659483964851402, "metric_key": "object_set_forecast_micro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_future_task_probes_a100_20260616T143608Z/object_set_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.1659483964851402, "raw_text": "0.1659", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.0009279881217520415, "metric_key": "object_set_forecast_micro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/object_set_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.0009279881217520415, "raw_text": "0.0009", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.01781970649895178, "metric_key": "object_set_forecast_micro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/object_set_forecast/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.01781970649895178, "raw_text": "0.0178", "status_label": "scored" } } }, { "task_number": 18, "task_id": "imu_to_hand_pose", "label": "IMU-to-Hand Pose Reconstruction", "axis_label": "18 IMU-to-Hand Pose Reconstruction", "short_label": "IMU->hand", "provenance_source": "historical_result_bundle", "metric_key": "mae", "metric_name": "MAE", "metric_direction": "lower", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 0.2294670194387436, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.18324815505876868, "raw_text": "0.2295", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 0.2555866539478302, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "status": "scored", "reason": null, "normalized_score": 0.16452114110609004, "raw_text": "0.2556", "status_label": "scored" }, "raw128_simple": { "raw": 0.22941437363624573, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.1832902066792771, "raw_text": "0.2294", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 0.252998411655426, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.1662042369509182, "raw_text": "0.2530", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 0.9641651902471952, "metric_key": "imu_to_hand_pose_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_sensor_target_probes_a100_20260619T000000Z/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.043612244441436056, "raw_text": "0.9642", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.9896650636969544, "metric_key": "imu_to_hand_pose_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.04248852414968175, "raw_text": "0.9897", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.9920062431451954, "metric_key": "imu_to_hand_pose_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.04238824931752955, "raw_text": "0.9920", "status_label": "scored" } } }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "label": "Camera-View Synchronization Retrieval", "axis_label": "19 Camera-View Synchronization Retrieval", "short_label": "Cam sync", "provenance_source": "historical_result_bundle", "metric_key": "mrr", "metric_name": "MRR", "metric_direction": "higher", "raw128_proxy_axis": true, "values": { "metadata128_simple": { "raw": 0.0021294241305440664, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_aligned_metadata_baseline", "status": "proxy_scored", "reason": "paired camera-view embeddings are absent from the 128 JSONL/feature export; metadata features retrieve the synchronized same-window depth/audio block as a documented compact synchronization proxy", "normalized_score": 0.0021294241305440664, "raw_text": "0.0021", "status_label": "proxy scored" }, "metadata128_neural_mlp": { "raw": 0.0027218370232731104, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_aligned_metadata_baseline", "status": "proxy_scored", "reason": "paired camera-view embeddings are absent from the 128 JSONL/feature export; metadata features retrieve the synchronized same-window depth/audio block as a documented compact synchronization proxy", "normalized_score": 0.0027218370232731104, "raw_text": "0.0027", "status_label": "proxy scored" }, "raw128_simple": { "raw": 0.0026625150348991156, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "proxy_scored", "reason": "documented compact proxy completion for this raw128 task axis", "normalized_score": 0.0026625150348991156, "raw_text": "0.0027", "status_label": "proxy scored" }, "raw128_neural_mlp": { "raw": 0.0025448438245803118, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "proxy_scored", "reason": "documented compact proxy completion for this raw128 task axis", "normalized_score": 0.0025448438245803118, "raw_text": "0.0025", "status_label": "proxy scored" }, "qwen3_omni_v6_lora": { "raw": 0.6587714947089998, "metric_key": "camera_view_sync_retrieval_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_camera_view_sync_mosaic_tile_a100_20260619T0305Z/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.6587714947089998, "raw_text": "0.6588", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 0.9979751961528727, "metric_key": "camera_view_sync_retrieval_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.9979751961528727, "raw_text": "0.9980", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 0.9989875980764363, "metric_key": "camera_view_sync_retrieval_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.9989875980764363, "raw_text": "0.9990", "status_label": "scored" } } }, { "task_number": 20, "task_id": "time_to_transition", "label": "Time-to-Next-Transition Regression", "axis_label": "20 Time-to-Next-Transition Regression", "short_label": "Time2bdry", "provenance_source": "historical_result_bundle", "metric_key": "mae", "metric_name": "MAE frames", "metric_direction": "lower", "raw128_proxy_axis": false, "values": { "metadata128_simple": { "raw": 624.8108520507812, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.016864874132806403, "raw_text": "624.81", "status_label": "scored" }, "metadata128_neural_mlp": { "raw": 41.4664421081543, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json", "scope": "multi_episode_128_aligned_baseline", "status": "scored", "reason": null, "normalized_score": 0.25411768748242325, "raw_text": "41.47", "status_label": "scored" }, "raw128_simple": { "raw": 52.32759475708008, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/time_to_transition/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.20137284019197565, "raw_text": "52.33", "status_label": "scored" }, "raw128_neural_mlp": { "raw": 42.374061584472656, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/time_to_transition/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "status": "scored", "reason": null, "normalized_score": 0.24867468405504953, "raw_text": "42.37", "status_label": "scored" }, "qwen3_omni_v6_lora": { "raw": 134.0687422166874, "metric_key": "time_to_transition_mae", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_order_sync_time_probes_a100_20260617T132500Z/time_to_transition/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.07859666766782253, "raw_text": "134.07", "status_label": "scored" }, "cosmos3_super_reasoner": { "raw": 52.94642857142857, "metric_key": "time_to_transition_mae", "source": "results/omni_finetune/model_output_task_probes_20260616/time_to_transition/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.19901920981190058, "raw_text": "52.95", "status_label": "scored" }, "cosmos3_nano_future_window": { "raw": 33.80952380952381, "metric_key": "time_to_transition_mae", "source": "results/omni_finetune/model_output_task_probes_20260616/time_to_transition/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "status": "scored", "reason": null, "normalized_score": 0.3116682871966295, "raw_text": "33.81", "status_label": "scored" } } } ], "task_method_result_matrix": [ { "task_number": 1, "task_id": "timeline_action", "task_label": "Action Recognition", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.008252821966746326, "raw_text": "0.0083", "normalized_score": 0.008252821966746326, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/timeline_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 1, "task_id": "timeline_action", "task_label": "Action Recognition", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.004175793689174209, "raw_text": "0.0042", "normalized_score": 0.004175793689174209, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/timeline_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 1, "task_id": "timeline_action", "task_label": "Action Recognition", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.002915061325704321, "raw_text": "0.0029", "normalized_score": 0.002915061325704321, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/timeline_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 1, "task_id": "timeline_action", "task_label": "Action Recognition", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0014955083181204041, "raw_text": "0.0015", "normalized_score": 0.0014955083181204041, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/timeline_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 1, "task_id": "timeline_action", "task_label": "Action Recognition", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0028830723979596335, "raw_text": "0.0029", "normalized_score": 0.0028830723979596335, "metric_key": "action_macro_f1", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 1, "task_id": "timeline_action", "task_label": "Action Recognition", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0008284021201089245, "raw_text": "0.0008", "normalized_score": 0.0008284021201089245, "metric_key": "action_macro_f1", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 1, "task_id": "timeline_action", "task_label": "Action Recognition", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.007936507936507936, "raw_text": "0.0079", "normalized_score": 0.007936507936507936, "metric_key": "action_accuracy_from_retrieved_future", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 2, "task_id": "timeline_subtask", "task_label": "Procedure Step Recognition", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.00019512195121951218, "raw_text": "0.0002", "normalized_score": 0.00019512195121951218, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/timeline_subtask/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 2, "task_id": "timeline_subtask", "task_label": "Procedure Step Recognition", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 7.207207207207208e-05, "raw_text": "0.0001", "normalized_score": 7.207207207207208e-05, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/timeline_subtask/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 2, "task_id": "timeline_subtask", "task_label": "Procedure Step Recognition", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/timeline_subtask/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 2, "task_id": "timeline_subtask", "task_label": "Procedure Step Recognition", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 7.35632183908046e-05, "raw_text": "0.0001", "normalized_score": 7.35632183908046e-05, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/timeline_subtask/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 2, "task_id": "timeline_subtask", "task_label": "Procedure Step Recognition", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0037313432835820895, "raw_text": "0.0037", "normalized_score": 0.0037313432835820895, "metric_key": "subtask_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 2, "task_id": "timeline_subtask", "task_label": "Procedure Step Recognition", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "subtask_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 2, "task_id": "timeline_subtask", "task_label": "Procedure Step Recognition", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "timeline_subtask_macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_current_subtask_object_relevance_patched_textonly_20260621/timeline_subtask/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 3, "task_id": "transition_detection", "task_label": "Action Boundary Detection", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.29652162550029315, "raw_text": "0.2965", "normalized_score": 0.29652162550029315, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/transition_detection/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 3, "task_id": "transition_detection", "task_label": "Action Boundary Detection", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.4841733292368365, "raw_text": "0.4842", "normalized_score": 0.4841733292368365, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/transition_detection/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 3, "task_id": "transition_detection", "task_label": "Action Boundary Detection", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.4203613574238283, "raw_text": "0.4204", "normalized_score": 0.4203613574238283, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/transition_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 3, "task_id": "transition_detection", "task_label": "Action Boundary Detection", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.4902206914147213, "raw_text": "0.4902", "normalized_score": 0.4902206914147213, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/transition_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 3, "task_id": "transition_detection", "task_label": "Action Boundary Detection", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9898313492063492, "raw_text": "0.9898", "normalized_score": 0.9898313492063492, "metric_key": "transition_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 3, "task_id": "transition_detection", "task_label": "Action Boundary Detection", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.36830357142857145, "raw_text": "0.3683", "normalized_score": 0.36830357142857145, "metric_key": "transition_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 3, "task_id": "transition_detection", "task_label": "Action Boundary Detection", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9682539682539683, "raw_text": "0.9683", "normalized_score": 0.9682539682539683, "metric_key": "transition_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 4, "task_id": "next_action", "task_label": "Next-Action Prediction", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.006514774539765508, "raw_text": "0.0065", "normalized_score": 0.006514774539765508, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 4, "task_id": "next_action", "task_label": "Next-Action Prediction", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.004910507980164745, "raw_text": "0.0049", "normalized_score": 0.004910507980164745, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 4, "task_id": "next_action", "task_label": "Next-Action Prediction", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.003285273363482094, "raw_text": "0.0033", "normalized_score": 0.003285273363482094, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 4, "task_id": "next_action", "task_label": "Next-Action Prediction", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0018477984371755407, "raw_text": "0.0018", "normalized_score": 0.0018477984371755407, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 4, "task_id": "next_action", "task_label": "Next-Action Prediction", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.04305335446381405, "raw_text": "0.0431", "normalized_score": 0.04305335446381405, "metric_key": "next_action_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 4, "task_id": "next_action", "task_label": "Next-Action Prediction", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.013392857142857142, "raw_text": "0.0134", "normalized_score": 0.013392857142857142, "metric_key": "next_action_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 4, "task_id": "next_action", "task_label": "Next-Action Prediction", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.007936507936507936, "raw_text": "0.0079", "normalized_score": 0.007936507936507936, "metric_key": "action_accuracy_from_retrieved_future", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "task_label": "Hand Trajectory Forecasting", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 8.817333221435547, "raw_text": "8.817", "normalized_score": 0.012231610603598841, "metric_key": "mpjpe", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "task_label": "Hand Trajectory Forecasting", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.429434210062027, "raw_text": "0.4294", "normalized_score": 0.25114484128127007, "metric_key": "mpjpe", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "task_label": "Hand Trajectory Forecasting", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.2729249894618988, "raw_text": "0.2729", "normalized_score": 0.39516420515180267, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "task_label": "Hand Trajectory Forecasting", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.18475216627120972, "raw_text": "0.1848", "normalized_score": 0.5837560051580399, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "task_label": "Hand Trajectory Forecasting", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.7216105627267382, "raw_text": "0.7216", "normalized_score": 0.149457605109387, "metric_key": "hand_trajectory_forecast_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_sensor_target_probes_a100_20260619T000000Z/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "task_label": "Hand Trajectory Forecasting", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.8915253522315043, "raw_text": "0.8915", "normalized_score": 0.12097265238372007, "metric_key": "hand_trajectory_forecast_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 5, "task_id": "hand_trajectory_forecast", "task_label": "Hand Trajectory Forecasting", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.6912806884333101, "raw_text": "0.6913", "normalized_score": 0.15601504328321764, "metric_key": "hand_trajectory_forecast_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/hand_trajectory_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 6, "task_id": "contact_prediction", "task_label": "Contact State Prediction", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.4381481308057444, "raw_text": "0.4381", "normalized_score": 0.4381481308057444, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/contact_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 6, "task_id": "contact_prediction", "task_label": "Contact State Prediction", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.5682695682695682, "raw_text": "0.5683", "normalized_score": 0.5682695682695682, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/contact_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 6, "task_id": "contact_prediction", "task_label": "Contact State Prediction", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.886990707397193, "raw_text": "0.8870", "normalized_score": 0.886990707397193, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/contact_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 6, "task_id": "contact_prediction", "task_label": "Contact State Prediction", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 1.0, "raw_text": "1.000", "normalized_score": 1.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/contact_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 6, "task_id": "contact_prediction", "task_label": "Contact State Prediction", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.8177083333333334, "raw_text": "0.8177", "normalized_score": 0.8177083333333334, "metric_key": "contact_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 6, "task_id": "contact_prediction", "task_label": "Contact State Prediction", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.32142857142857145, "raw_text": "0.3214", "normalized_score": 0.32142857142857145, "metric_key": "contact_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 6, "task_id": "contact_prediction", "task_label": "Contact State Prediction", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.7433862433862434, "raw_text": "0.7434", "normalized_score": 0.7433862433862434, "metric_key": "contact_accuracy", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 7, "task_id": "object_relevance", "task_label": "Object Relevance Prediction", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.17764578833693304, "raw_text": "0.1776", "normalized_score": 0.17764578833693304, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_relevance/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 7, "task_id": "object_relevance", "task_label": "Object Relevance Prediction", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.18662723837686876, "raw_text": "0.1866", "normalized_score": 0.18662723837686876, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_relevance/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 7, "task_id": "object_relevance", "task_label": "Object Relevance Prediction", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0655376369662084, "raw_text": "0.0655", "normalized_score": 0.0655376369662084, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/object_relevance/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 7, "task_id": "object_relevance", "task_label": "Object Relevance Prediction", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.1765890386972509, "raw_text": "0.1766", "normalized_score": 0.1765890386972509, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/object_relevance/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 7, "task_id": "object_relevance", "task_label": "Object Relevance Prediction", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.3064982378331287, "raw_text": "0.3065", "normalized_score": 0.3064982378331287, "metric_key": "object_micro_f1", "source": "results/omni_finetune/verified_public/xperience10m_qwen3_omni_128ep_multiscale_cap96_v6_rank64_lr5e5_full8gpu_lora_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 7, "task_id": "object_relevance", "task_label": "Object Relevance Prediction", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.13704276146316333, "raw_text": "0.1370", "normalized_score": 0.13704276146316333, "metric_key": "object_micro_f1", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_super_reasoner_128ep_test_full_20260607/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 7, "task_id": "object_relevance", "task_label": "Object Relevance Prediction", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.00047209895194032665, "raw_text": "0.0005", "normalized_score": 0.00047209895194032665, "metric_key": "object_relevance_micro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_current_subtask_object_relevance_patched_textonly_20260621/object_relevance/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 8, "task_id": "caption_grounding", "task_label": "Language Grounding", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.002332374220713973, "raw_text": "0.0023", "normalized_score": 0.002332374220713973, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/caption_grounding/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 8, "task_id": "caption_grounding", "task_label": "Language Grounding", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.008236799389123917, "raw_text": "0.0082", "normalized_score": 0.008236799389123917, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/caption_grounding/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 8, "task_id": "caption_grounding", "task_label": "Language Grounding", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.011138836853206158, "raw_text": "0.0111", "normalized_score": 0.011138836853206158, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/caption_grounding/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 8, "task_id": "caption_grounding", "task_label": "Language Grounding", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0063402121886610985, "raw_text": "0.0063", "normalized_score": 0.0063402121886610985, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/caption_grounding/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 8, "task_id": "caption_grounding", "task_label": "Language Grounding", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.8764467592592605, "raw_text": "0.8764", "normalized_score": 0.8764467592592605, "metric_key": "caption_grounding_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_retrieval_task_probes_a100_20260617T175919Z/caption_grounding/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 8, "task_id": "caption_grounding", "task_label": "Language Grounding", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.30639899644580487, "raw_text": "0.3064", "normalized_score": 0.30639899644580487, "metric_key": "caption_grounding_iou", "source": "results/omni_finetune/model_output_task_probes_20260616/caption_grounding/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 8, "task_id": "caption_grounding", "task_label": "Language Grounding", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.5221041086644663, "raw_text": "0.5221", "normalized_score": 0.5221041086644663, "metric_key": "caption_grounding_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/caption_grounding/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 9, "task_id": "cross_modal_retrieval", "task_label": "Cross-Modal Retrieval", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.002587692579254508, "raw_text": "0.0026", "normalized_score": 0.002587692579254508, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 9, "task_id": "cross_modal_retrieval", "task_label": "Cross-Modal Retrieval", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0026067993603646755, "raw_text": "0.0026", "normalized_score": 0.0026067993603646755, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 9, "task_id": "cross_modal_retrieval", "task_label": "Cross-Modal Retrieval", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.003459817497059703, "raw_text": "0.0035", "normalized_score": 0.003459817497059703, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 9, "task_id": "cross_modal_retrieval", "task_label": "Cross-Modal Retrieval", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.002535284962505102, "raw_text": "0.0025", "normalized_score": 0.002535284962505102, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 9, "task_id": "cross_modal_retrieval", "task_label": "Cross-Modal Retrieval", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.5080191798941732, "raw_text": "0.5080", "normalized_score": 0.5080191798941732, "metric_key": "cross_modal_retrieval_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_cross_modal_retrieval_probe_a100_20260618T000000Z/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 9, "task_id": "cross_modal_retrieval", "task_label": "Cross-Modal Retrieval", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.6628490677465636, "raw_text": "0.6628", "normalized_score": 0.6628490677465636, "metric_key": "cross_modal_retrieval_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/cross_modal_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 9, "task_id": "cross_modal_retrieval", "task_label": "Cross-Modal Retrieval", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.022138720585222767, "raw_text": "0.0221", "normalized_score": 0.022138720585222767, "metric_key": "future_retrieval_mrr", "source": "results/omni_finetune/verified_public/xperience10m_cosmos3_nano_128ep_future_window_h5_compat_adapter_eval_test_full/eval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 10, "task_id": "modality_reconstruction", "task_label": "Cross-Modal Reconstruction", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": -190.66106203944798, "raw_text": "-190.66", "normalized_score": 0.0, "metric_key": "r2", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/modality_reconstruction/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 10, "task_id": "modality_reconstruction", "task_label": "Cross-Modal Reconstruction", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": -0.43481132003942147, "raw_text": "-0.4348", "normalized_score": 0.0, "metric_key": "r2", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/modality_reconstruction/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 10, "task_id": "modality_reconstruction", "task_label": "Cross-Modal Reconstruction", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": -1.3450960391924882, "raw_text": "-1.345", "normalized_score": 0.0, "metric_key": "r2", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/modality_reconstruction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 10, "task_id": "modality_reconstruction", "task_label": "Cross-Modal Reconstruction", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": -1.3974418160502369, "raw_text": "-1.397", "normalized_score": 0.0, "metric_key": "r2", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/modality_reconstruction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 10, "task_id": "modality_reconstruction", "task_label": "Cross-Modal Reconstruction", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9670547540707002, "raw_text": "0.9671", "normalized_score": 0.9670547540707002, "metric_key": "modality_reconstruction_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_sensor_target_probes_a100_20260619T000000Z/modality_reconstruction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 10, "task_id": "modality_reconstruction", "task_label": "Cross-Modal Reconstruction", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9939466801653591, "raw_text": "0.9939", "normalized_score": 0.9939466801653591, "metric_key": "modality_reconstruction_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/modality_reconstruction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 10, "task_id": "modality_reconstruction", "task_label": "Cross-Modal Reconstruction", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0002873382957286892, "raw_text": "0.0003", "normalized_score": 0.0002873382957286892, "metric_key": "feature_reconstruction_quality", "source": "results/omni_finetune/model_output_task_probes_20260616/modality_reconstruction/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 11, "task_id": "temporal_order", "task_label": "Temporal Order Verification", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.4198864140782312, "raw_text": "0.4199", "normalized_score": 0.4198864140782312, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/temporal_order/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 11, "task_id": "temporal_order", "task_label": "Temporal Order Verification", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.8252408266656923, "raw_text": "0.8252", "normalized_score": 0.8252408266656923, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/temporal_order/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 11, "task_id": "temporal_order", "task_label": "Temporal Order Verification", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.49824413370686593, "raw_text": "0.4982", "normalized_score": 0.49824413370686593, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/temporal_order/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 11, "task_id": "temporal_order", "task_label": "Temporal Order Verification", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.8030047098504103, "raw_text": "0.8030", "normalized_score": 0.8030047098504103, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/temporal_order/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 11, "task_id": "temporal_order", "task_label": "Temporal Order Verification", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.40984631701404173, "raw_text": "0.4098", "normalized_score": 0.40984631701404173, "metric_key": "temporal_order_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_order_sync_time_probes_a100_20260617T132500Z/temporal_order/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 11, "task_id": "temporal_order", "task_label": "Temporal Order Verification", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.6286317274823326, "raw_text": "0.6286", "normalized_score": 0.6286317274823326, "metric_key": "temporal_order_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/temporal_order/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 11, "task_id": "temporal_order", "task_label": "Temporal Order Verification", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.5954109425716205, "raw_text": "0.5954", "normalized_score": 0.5954109425716205, "metric_key": "temporal_order_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_future_order_misalignment_patched_textonly_20260621/temporal_order/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 12, "task_id": "misalignment_detection", "task_label": "Multimodal Synchronization Detection", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.49980060227663614, "raw_text": "0.4998", "normalized_score": 0.49980060227663614, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/misalignment_detection/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 12, "task_id": "misalignment_detection", "task_label": "Multimodal Synchronization Detection", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.7773773780941162, "raw_text": "0.7774", "normalized_score": 0.7773773780941162, "metric_key": "f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/misalignment_detection/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 12, "task_id": "misalignment_detection", "task_label": "Multimodal Synchronization Detection", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.4958867673901769, "raw_text": "0.4959", "normalized_score": 0.4958867673901769, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/misalignment_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 12, "task_id": "misalignment_detection", "task_label": "Multimodal Synchronization Detection", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.8272709077974252, "raw_text": "0.8273", "normalized_score": 0.8272709077974252, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/misalignment_detection/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 12, "task_id": "misalignment_detection", "task_label": "Multimodal Synchronization Detection", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.3344936184319576, "raw_text": "0.3345", "normalized_score": 0.3344936184319576, "metric_key": "misalignment_detection_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_order_sync_time_probes_a100_20260617T132500Z/misalignment_detection/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 12, "task_id": "misalignment_detection", "task_label": "Multimodal Synchronization Detection", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.37271645981034185, "raw_text": "0.3727", "normalized_score": 0.37271645981034185, "metric_key": "misalignment_detection_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/misalignment_detection/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 12, "task_id": "misalignment_detection", "task_label": "Multimodal Synchronization Detection", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.477201691802725, "raw_text": "0.4772", "normalized_score": 0.477201691802725, "metric_key": "misalignment_detection_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_future_order_misalignment_patched_textonly_20260621/misalignment_detection/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 13, "task_id": "long_horizon_next_action", "task_label": "Long-Horizon Next-Action Forecasting", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.004579592783699693, "raw_text": "0.0046", "normalized_score": 0.004579592783699693, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 13, "task_id": "long_horizon_next_action", "task_label": "Long-Horizon Next-Action Forecasting", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0029821307969142615, "raw_text": "0.0030", "normalized_score": 0.0029821307969142615, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 13, "task_id": "long_horizon_next_action", "task_label": "Long-Horizon Next-Action Forecasting", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0024280172369056294, "raw_text": "0.0024", "normalized_score": 0.0024280172369056294, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 13, "task_id": "long_horizon_next_action", "task_label": "Long-Horizon Next-Action Forecasting", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.001063859887389299, "raw_text": "0.0011", "normalized_score": 0.001063859887389299, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 13, "task_id": "long_horizon_next_action", "task_label": "Long-Horizon Next-Action Forecasting", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0023356666867101906, "raw_text": "0.0023", "normalized_score": 0.0023356666867101906, "metric_key": "long_horizon_next_action_macro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_future_task_probes_a100_20260616T143608Z/long_horizon_next_action/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 13, "task_id": "long_horizon_next_action", "task_label": "Long-Horizon Next-Action Forecasting", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.008807588075880758, "raw_text": "0.0088", "normalized_score": 0.008807588075880758, "metric_key": "long_horizon_next_action_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/long_horizon_next_action/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 13, "task_id": "long_horizon_next_action", "task_label": "Long-Horizon Next-Action Forecasting", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0024906600249066007, "raw_text": "0.0025", "normalized_score": 0.0024906600249066007, "metric_key": "long_horizon_next_action_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/long_horizon_next_action/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 14, "task_id": "next_subtask_forecast", "task_label": "Long-Horizon Next-Subtask Forecasting", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0001206030150753769, "raw_text": "0.0001", "normalized_score": 0.0001206030150753769, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 14, "task_id": "next_subtask_forecast", "task_label": "Long-Horizon Next-Subtask Forecasting", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 2.086049543676662e-05, "raw_text": "0.0000", "normalized_score": 2.086049543676662e-05, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 14, "task_id": "next_subtask_forecast", "task_label": "Long-Horizon Next-Subtask Forecasting", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 14, "task_id": "next_subtask_forecast", "task_label": "Long-Horizon Next-Subtask Forecasting", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 14, "task_id": "next_subtask_forecast", "task_label": "Long-Horizon Next-Subtask Forecasting", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.004206715978529301, "raw_text": "0.0042", "normalized_score": 0.004206715978529301, "metric_key": "next_subtask_forecast_macro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_future_task_probes_a100_20260616T143608Z/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 14, "task_id": "next_subtask_forecast", "task_label": "Long-Horizon Next-Subtask Forecasting", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "next_subtask_forecast_macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/next_subtask_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 14, "task_id": "next_subtask_forecast", "task_label": "Long-Horizon Next-Subtask Forecasting", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.006614876224708678, "raw_text": "0.0066", "normalized_score": 0.006614876224708678, "metric_key": "next_subtask_forecast_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/next_subtask_forecast/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 15, "task_id": "interaction_text_prediction", "task_label": "Interaction Text Prediction", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 15, "task_id": "interaction_text_prediction", "task_label": "Interaction Text Prediction", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 15, "task_id": "interaction_text_prediction", "task_label": "Interaction Text Prediction", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "proxy_scored", "status_label": "proxy scored", "scored": true, "proxy_scored": true, "raw": 0.012611998261547169, "raw_text": "0.0126", "normalized_score": 0.012611998261547169, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": "documented compact proxy completion for this raw128 task axis" }, { "task_number": 15, "task_id": "interaction_text_prediction", "task_label": "Interaction Text Prediction", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "proxy_scored", "status_label": "proxy scored", "scored": true, "proxy_scored": true, "raw": 0.009791421280985521, "raw_text": "0.0098", "normalized_score": 0.009791421280985521, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": "documented compact proxy completion for this raw128 task axis" }, { "task_number": 15, "task_id": "interaction_text_prediction", "task_label": "Interaction Text Prediction", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.4318674027510605, "raw_text": "0.4319", "normalized_score": 0.4318674027510605, "metric_key": "macro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_interaction_text_task15_a100_20260620T010305Z/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 15, "task_id": "interaction_text_prediction", "task_label": "Interaction Text Prediction", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.17949512355264183, "raw_text": "0.1795", "normalized_score": 0.17949512355264183, "metric_key": "macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_interaction_text_task15_textonly_v1_20260620T1558Z/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 15, "task_id": "interaction_text_prediction", "task_label": "Interaction Text Prediction", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.1788367958939587, "raw_text": "0.1788", "normalized_score": 0.1788367958939587, "metric_key": "macro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_nano_interaction_text_task15_patched_textonly_20260621/interaction_text_prediction/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 16, "task_id": "action_object_relation", "task_label": "Action-Object Relation Prediction", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/action_object_relation/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 16, "task_id": "action_object_relation", "task_label": "Action-Object Relation Prediction", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/action_object_relation/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 16, "task_id": "action_object_relation", "task_label": "Action-Object Relation Prediction", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/action_object_relation/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 16, "task_id": "action_object_relation", "task_label": "Action-Object Relation Prediction", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "macro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/action_object_relation/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 16, "task_id": "action_object_relation", "task_label": "Action-Object Relation Prediction", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0002220083079671497, "raw_text": "0.0002", "normalized_score": 0.0002220083079671497, "metric_key": "action_object_relation_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/qwen3_omni_v6_lora/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 16, "task_id": "action_object_relation", "task_label": "Action-Object Relation Prediction", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0, "raw_text": "0.0000", "normalized_score": 0.0, "metric_key": "action_object_relation_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 16, "task_id": "action_object_relation", "task_label": "Action-Object Relation Prediction", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.002794157670325683, "raw_text": "0.0028", "normalized_score": 0.002794157670325683, "metric_key": "action_object_relation_macro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/action_object_relation/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 17, "task_id": "object_set_forecast", "task_label": "Future Object-Set Forecasting", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.17656983343047333, "raw_text": "0.1766", "normalized_score": 0.17656983343047333, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/object_set_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 17, "task_id": "object_set_forecast", "task_label": "Future Object-Set Forecasting", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.17418550827844048, "raw_text": "0.1742", "normalized_score": 0.17418550827844048, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/object_set_forecast/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 17, "task_id": "object_set_forecast", "task_label": "Future Object-Set Forecasting", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.06469493412657774, "raw_text": "0.0647", "normalized_score": 0.06469493412657774, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/object_set_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 17, "task_id": "object_set_forecast", "task_label": "Future Object-Set Forecasting", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.17523098630012288, "raw_text": "0.1752", "normalized_score": 0.17523098630012288, "metric_key": "micro_f1", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/object_set_forecast/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 17, "task_id": "object_set_forecast", "task_label": "Future Object-Set Forecasting", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.1659483964851402, "raw_text": "0.1659", "normalized_score": 0.1659483964851402, "metric_key": "object_set_forecast_micro_f1", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_future_task_probes_a100_20260616T143608Z/object_set_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 17, "task_id": "object_set_forecast", "task_label": "Future Object-Set Forecasting", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.0009279881217520415, "raw_text": "0.0009", "normalized_score": 0.0009279881217520415, "metric_key": "object_set_forecast_micro_f1", "source": "results/omni_finetune/xperience10m_cosmos3_super_future_task_probes_a100_textonly_v1_20260620/object_set_forecast/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 17, "task_id": "object_set_forecast", "task_label": "Future Object-Set Forecasting", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.01781970649895178, "raw_text": "0.0178", "normalized_score": 0.01781970649895178, "metric_key": "object_set_forecast_micro_f1", "source": "results/omni_finetune/model_output_task_probes_20260616/object_set_forecast/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 18, "task_id": "imu_to_hand_pose", "task_label": "IMU-to-Hand Pose Reconstruction", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.2294670194387436, "raw_text": "0.2295", "normalized_score": 0.18324815505876868, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 18, "task_id": "imu_to_hand_pose", "task_label": "IMU-to-Hand Pose Reconstruction", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.2555866539478302, "raw_text": "0.2556", "normalized_score": 0.16452114110609004, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_aligned_sensor_block_baseline", "reason": null }, { "task_number": 18, "task_id": "imu_to_hand_pose", "task_label": "IMU-to-Hand Pose Reconstruction", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.22941437363624573, "raw_text": "0.2294", "normalized_score": 0.1832902066792771, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 18, "task_id": "imu_to_hand_pose", "task_label": "IMU-to-Hand Pose Reconstruction", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.252998411655426, "raw_text": "0.2530", "normalized_score": 0.1662042369509182, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 18, "task_id": "imu_to_hand_pose", "task_label": "IMU-to-Hand Pose Reconstruction", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9641651902471952, "raw_text": "0.9642", "normalized_score": 0.043612244441436056, "metric_key": "imu_to_hand_pose_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_sensor_target_probes_a100_20260619T000000Z/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 18, "task_id": "imu_to_hand_pose", "task_label": "IMU-to-Hand Pose Reconstruction", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9896650636969544, "raw_text": "0.9897", "normalized_score": 0.04248852414968175, "metric_key": "imu_to_hand_pose_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 18, "task_id": "imu_to_hand_pose", "task_label": "IMU-to-Hand Pose Reconstruction", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9920062431451954, "raw_text": "0.9920", "normalized_score": 0.04238824931752955, "metric_key": "imu_to_hand_pose_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/imu_to_hand_pose/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "task_label": "Camera-View Synchronization Retrieval", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "proxy_scored", "status_label": "proxy scored", "scored": true, "proxy_scored": true, "raw": 0.0021294241305440664, "raw_text": "0.0021", "normalized_score": 0.0021294241305440664, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_aligned_metadata_baseline", "reason": "paired camera-view embeddings are absent from the 128 JSONL/feature export; metadata features retrieve the synchronized same-window depth/audio block as a documented compact synchronization proxy" }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "task_label": "Camera-View Synchronization Retrieval", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "proxy_scored", "status_label": "proxy scored", "scored": true, "proxy_scored": true, "raw": 0.0027218370232731104, "raw_text": "0.0027", "normalized_score": 0.0027218370232731104, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_aligned_metadata_baseline", "reason": "paired camera-view embeddings are absent from the 128 JSONL/feature export; metadata features retrieve the synchronized same-window depth/audio block as a documented compact synchronization proxy" }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "task_label": "Camera-View Synchronization Retrieval", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "proxy_scored", "status_label": "proxy scored", "scored": true, "proxy_scored": true, "raw": 0.0026625150348991156, "raw_text": "0.0027", "normalized_score": 0.0026625150348991156, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": "documented compact proxy completion for this raw128 task axis" }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "task_label": "Camera-View Synchronization Retrieval", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "proxy_scored", "status_label": "proxy scored", "scored": true, "proxy_scored": true, "raw": 0.0025448438245803118, "raw_text": "0.0025", "normalized_score": 0.0025448438245803118, "metric_key": "mrr", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": "documented compact proxy completion for this raw128 task axis" }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "task_label": "Camera-View Synchronization Retrieval", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.6587714947089998, "raw_text": "0.6588", "normalized_score": 0.6587714947089998, "metric_key": "camera_view_sync_retrieval_mrr", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_camera_view_sync_mosaic_tile_a100_20260619T0305Z/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "task_label": "Camera-View Synchronization Retrieval", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9979751961528727, "raw_text": "0.9980", "normalized_score": 0.9979751961528727, "metric_key": "camera_view_sync_retrieval_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_super_retrieval_task_probes_a100_textonly_prompatch_v2_20260620/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 19, "task_id": "camera_view_sync_retrieval", "task_label": "Camera-View Synchronization Retrieval", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 0.9989875980764363, "raw_text": "0.9990", "normalized_score": 0.9989875980764363, "metric_key": "camera_view_sync_retrieval_mrr", "source": "results/omni_finetune/xperience10m_cosmos3_nano_retrieval_task_probes_a100_patched_textonly_20260621/camera_view_sync_retrieval/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 20, "task_id": "time_to_transition", "task_label": "Time-to-Next-Transition Regression", "series_id": "metadata128_simple", "method": "128ep Aligned Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 624.8108520507812, "raw_text": "624.81", "normalized_score": 0.016864874132806403, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/time_to_transition/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 20, "task_id": "time_to_transition", "task_label": "Time-to-Next-Transition Regression", "series_id": "metadata128_neural_mlp", "method": "128ep Aligned NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 41.4664421081543, "raw_text": "41.47", "normalized_score": 0.25411768748242325, "metric_key": "mae", "source": "results/omni_finetune/a100_128_metadata_task_baselines_20260616_v2/neural_mlp/time_to_transition/metrics.json", "scope": "multi_episode_128_aligned_baseline", "reason": null }, { "task_number": 20, "task_id": "time_to_transition", "task_label": "Time-to-Next-Transition Regression", "series_id": "raw128_simple", "method": "128ep Raw Simple", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 52.32759475708008, "raw_text": "52.33", "normalized_score": 0.20137284019197565, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/simple_raw128/time_to_transition/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 20, "task_id": "time_to_transition", "task_label": "Time-to-Next-Transition Regression", "series_id": "raw128_neural_mlp", "method": "128ep Raw NN", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 42.374061584472656, "raw_text": "42.37", "normalized_score": 0.24867468405504953, "metric_key": "mae", "source": "results/omni_finetune/a100_128_raw20_task_baselines_complete20_proxy_20260616T091500Z/neural_mlp_raw128/time_to_transition/metrics.json", "scope": "multi_episode_128_raw_sensor_feature_baseline", "reason": null }, { "task_number": 20, "task_id": "time_to_transition", "task_label": "Time-to-Next-Transition Regression", "series_id": "qwen3_omni_v6_lora", "method": "Qwen3-Omni v6 LoRA", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 134.0687422166874, "raw_text": "134.07", "normalized_score": 0.07859666766782253, "metric_key": "time_to_transition_mae", "source": "results/omni_finetune/xperience10m_qwen3_omni_v6_order_sync_time_probes_a100_20260617T132500Z/time_to_transition/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 20, "task_id": "time_to_transition", "task_label": "Time-to-Next-Transition Regression", "series_id": "cosmos3_super_reasoner", "method": "Cosmos3-Super Reasoner", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 52.94642857142857, "raw_text": "52.95", "normalized_score": 0.19901920981190058, "metric_key": "time_to_transition_mae", "source": "results/omni_finetune/model_output_task_probes_20260616/time_to_transition/cosmos3_super_reasoner/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null }, { "task_number": 20, "task_id": "time_to_transition", "task_label": "Time-to-Next-Transition Regression", "series_id": "cosmos3_nano_future_window", "method": "Cosmos3-Nano Future Window", "status": "scored", "status_label": "scored", "scored": true, "proxy_scored": false, "raw": 33.80952380952381, "raw_text": "33.81", "normalized_score": 0.3116682871966295, "metric_key": "time_to_transition_mae", "source": "results/omni_finetune/model_output_task_probes_20260616/time_to_transition/cosmos3_nano_future_window/metrics.json", "scope": "multi_episode_128_partial_model_overlay", "reason": null } ] }