| { |
| "status": "pass", |
| "generated_at_utc": "2026-06-07T15:47:30+00:00", |
| "summary": { |
| "task_count": 12, |
| "expected_task_count": 12, |
| "task_family_counts": { |
| "diagnostic": 3, |
| "forecast": 2, |
| "retrieval": 2, |
| "supervised": 5 |
| }, |
| "modality_usage_counts": { |
| "depth": 10, |
| "inertial": 11, |
| "language": 4, |
| "motion_capture": 11, |
| "pose_slam": 11, |
| "video": 12 |
| }, |
| "interactive_surface": "task cards plus scrub/play/chapter walkthrough storyboard", |
| "failure_count": 0 |
| }, |
| "checks": [ |
| { |
| "name": "required_task_surface_inputs_present", |
| "status": "pass", |
| "inputs": { |
| "task_walkthroughs_json": true, |
| "website_index": true, |
| "walkthrough_markdown": true |
| } |
| }, |
| { |
| "name": "tasks_object_present", |
| "status": "pass" |
| }, |
| { |
| "name": "exactly_12_tasks", |
| "status": "pass", |
| "observed": 12, |
| "expected": 12 |
| }, |
| { |
| "name": "expected_task_ids_present", |
| "status": "pass", |
| "missing": [], |
| "extra": [] |
| }, |
| { |
| "name": "timeline_action: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "timeline_action: human_readable_display_name", |
| "status": "pass", |
| "expected": "Action Recognition", |
| "observed": "Action Recognition" |
| }, |
| { |
| "name": "timeline_action: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "timeline_action" |
| }, |
| { |
| "name": "timeline_action: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "20-frame multimodal window", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_action: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Egocentric Action Recognition", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_action: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Action Recognition", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_action: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Recognize the current manipulation action from synchronized visual, motion, inertial, pose, and annotation context.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_action: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "window features -> action label builder -> classifier", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_action: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "current action class", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_action: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Look at one short multimodal window and name what action is happening now.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_action: known_task_family", |
| "status": "pass", |
| "observed": "supervised", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "timeline_action: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial", |
| "language" |
| ] |
| }, |
| { |
| "name": "timeline_action: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "timeline_action: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "timeline_action: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "video", |
| "modalities": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial", |
| "language" |
| ] |
| }, |
| { |
| "name": "timeline_action: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "macro_f1", |
| "name": "macro-F1", |
| "direction": "higher", |
| "minimal": 0.05, |
| "neural_mlp": 0.014814814814814814 |
| } |
| }, |
| { |
| "name": "timeline_action: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "timeline_subtask: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "timeline_subtask: human_readable_display_name", |
| "status": "pass", |
| "expected": "Procedure Step Recognition", |
| "observed": "Procedure Step Recognition" |
| }, |
| { |
| "name": "timeline_subtask: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "timeline_subtask" |
| }, |
| { |
| "name": "timeline_subtask: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "20-frame multimodal window", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_subtask: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Temporal Subtask Recognition", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_subtask: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Procedure Step Recognition", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_subtask: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Recognize the broader activity stage so fine actions become a readable procedure timeline.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_subtask: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "window features -> subtask label builder -> classifier", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_subtask: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "current procedure step", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_subtask: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Predict the higher-level task stage for the current window.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "timeline_subtask: known_task_family", |
| "status": "pass", |
| "observed": "supervised", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "timeline_subtask: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial", |
| "language" |
| ] |
| }, |
| { |
| "name": "timeline_subtask: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "timeline_subtask: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "timeline_subtask: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "language", |
| "modalities": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial", |
| "language" |
| ] |
| }, |
| { |
| "name": "timeline_subtask: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "macro_f1", |
| "name": "macro-F1", |
| "direction": "higher", |
| "minimal": 0.05056355513846935, |
| "neural_mlp": 0.02810810810810811 |
| } |
| }, |
| { |
| "name": "timeline_subtask: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "transition_detection: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "transition_detection: human_readable_display_name", |
| "status": "pass", |
| "expected": "Action Boundary Detection", |
| "observed": "Action Boundary Detection" |
| }, |
| { |
| "name": "transition_detection: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "transition_detection" |
| }, |
| { |
| "name": "transition_detection: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "current window with boundary target", |
| "raw_hits": [] |
| }, |
| { |
| "name": "transition_detection: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Temporal Action Segmentation", |
| "raw_hits": [] |
| }, |
| { |
| "name": "transition_detection: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Action Boundary Detection", |
| "raw_hits": [] |
| }, |
| { |
| "name": "transition_detection: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Detect the local moment where the episode changes from one action segment to the next.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "transition_detection: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "action changes -> boundary labels -> binary classifier", |
| "raw_hits": [] |
| }, |
| { |
| "name": "transition_detection: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "boundary or steady", |
| "raw_hits": [] |
| }, |
| { |
| "name": "transition_detection: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Detect whether the current window is near a boundary between actions.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "transition_detection: known_task_family", |
| "status": "pass", |
| "observed": "diagnostic", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "transition_detection: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "video", |
| "pose_slam", |
| "motion_capture", |
| "inertial", |
| "language" |
| ] |
| }, |
| { |
| "name": "transition_detection: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "transition_detection: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "transition_detection: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "pose_slam", |
| "modalities": [ |
| "video", |
| "pose_slam", |
| "motion_capture", |
| "inertial", |
| "language" |
| ] |
| }, |
| { |
| "name": "transition_detection: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "macro_f1", |
| "name": "macro-F1", |
| "direction": "higher", |
| "minimal": 0.6118237590630229, |
| "neural_mlp": 0.5862068965517241 |
| } |
| }, |
| { |
| "name": "transition_detection: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "next_action: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "next_action: human_readable_display_name", |
| "status": "pass", |
| "expected": "Next-Action Prediction", |
| "observed": "Next-Action Prediction" |
| }, |
| { |
| "name": "next_action: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "next_action" |
| }, |
| { |
| "name": "next_action: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "current window at time t", |
| "raw_hits": [] |
| }, |
| { |
| "name": "next_action: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Short-Horizon Intention Prediction", |
| "raw_hits": [] |
| }, |
| { |
| "name": "next_action: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Next-Action Prediction", |
| "raw_hits": [] |
| }, |
| { |
| "name": "next_action: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Forecast the near-future action from the current observations only.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "next_action: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "current features -> future label shift -> classifier", |
| "raw_hits": [] |
| }, |
| { |
| "name": "next_action: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "action at t+20 frames", |
| "raw_hits": [] |
| }, |
| { |
| "name": "next_action: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Use the current window to guess the action that will happen shortly after it.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "next_action: known_task_family", |
| "status": "pass", |
| "observed": "supervised", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "next_action: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "next_action: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "next_action: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "next_action: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "video", |
| "modalities": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "next_action: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "macro_f1", |
| "name": "macro-F1", |
| "direction": "higher", |
| "minimal": 0.05925925925925927, |
| "neural_mlp": 0.04186046511627907 |
| } |
| }, |
| { |
| "name": "next_action: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "hand_trajectory_forecast: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: human_readable_display_name", |
| "status": "pass", |
| "expected": "Hand Trajectory Forecasting", |
| "observed": "Hand Trajectory Forecasting" |
| }, |
| { |
| "name": "hand_trajectory_forecast: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "hand_trajectory_forecast" |
| }, |
| { |
| "name": "hand_trajectory_forecast: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "current multimodal window", |
| "raw_hits": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "3D Hand Motion Forecasting", |
| "raw_hits": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Hand Trajectory Forecasting", |
| "raw_hits": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Predict the future 3D left/right hand path from the current multimodal state.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "current features -> future mocap target -> regression head", |
| "raw_hits": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "future hand-joint trajectory", |
| "raw_hits": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Predict where the hands will move over the next few frames.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: known_task_family", |
| "status": "pass", |
| "observed": "forecast", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "hand_trajectory_forecast: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "motion_capture", |
| "video", |
| "depth", |
| "pose_slam", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "hand_trajectory_forecast: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "hand_trajectory_forecast: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "motion_capture", |
| "modalities": [ |
| "motion_capture", |
| "video", |
| "depth", |
| "pose_slam", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "hand_trajectory_forecast: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "mpjpe", |
| "name": "MPJPE", |
| "direction": "lower", |
| "minimal": 0.8646570444107056, |
| "neural_mlp": 0.10785018652677536 |
| } |
| }, |
| { |
| "name": "hand_trajectory_forecast: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "contact_prediction: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "contact_prediction: human_readable_display_name", |
| "status": "pass", |
| "expected": "Contact State Prediction", |
| "observed": "Contact State Prediction" |
| }, |
| { |
| "name": "contact_prediction: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "contact_prediction" |
| }, |
| { |
| "name": "contact_prediction: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "non-contact, non-caption features", |
| "raw_hits": [] |
| }, |
| { |
| "name": "contact_prediction: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Human-Object Contact Prediction", |
| "raw_hits": [] |
| }, |
| { |
| "name": "contact_prediction: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Contact State Prediction", |
| "raw_hits": [] |
| }, |
| { |
| "name": "contact_prediction: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Predict whether body or hand contact with the scene is occurring without leaking contact labels.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "contact_prediction: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "feature filter -> contact target -> binary classifier", |
| "raw_hits": [] |
| }, |
| { |
| "name": "contact_prediction: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "contact or no contact", |
| "raw_hits": [] |
| }, |
| { |
| "name": "contact_prediction: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Predict whether the body or hand is in contact with something.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "contact_prediction: known_task_family", |
| "status": "pass", |
| "observed": "supervised", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "contact_prediction: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "motion_capture", |
| "video", |
| "depth", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "contact_prediction: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "contact_prediction: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "contact_prediction: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "motion_capture", |
| "modalities": [ |
| "motion_capture", |
| "video", |
| "depth", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "contact_prediction: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "macro_f1", |
| "name": "macro-F1", |
| "direction": "higher", |
| "minimal": 1.0, |
| "neural_mlp": 1.0 |
| } |
| }, |
| { |
| "name": "contact_prediction: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "object_relevance: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "object_relevance: human_readable_display_name", |
| "status": "pass", |
| "expected": "Object Relevance Prediction", |
| "observed": "Object Relevance Prediction" |
| }, |
| { |
| "name": "object_relevance: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "object_relevance" |
| }, |
| { |
| "name": "object_relevance: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "non-caption multimodal features", |
| "raw_hits": [] |
| }, |
| { |
| "name": "object_relevance: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Object-Centric Interaction Recognition", |
| "raw_hits": [] |
| }, |
| { |
| "name": "object_relevance: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Object Relevance Prediction", |
| "raw_hits": [] |
| }, |
| { |
| "name": "object_relevance: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Infer which objects are relevant to the current manipulation window from non-caption features.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "object_relevance: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "object vocabulary -> multi-hot labels -> sigmoid heads", |
| "raw_hits": [] |
| }, |
| { |
| "name": "object_relevance: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "relevant object set", |
| "raw_hits": [] |
| }, |
| { |
| "name": "object_relevance: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Predict which objects matter in the current window.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "object_relevance: known_task_family", |
| "status": "pass", |
| "observed": "supervised", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "object_relevance: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "object_relevance: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "object_relevance: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "object_relevance: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "video", |
| "modalities": [ |
| "video", |
| "depth", |
| "pose_slam", |
| "motion_capture", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "object_relevance: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "micro_f1", |
| "name": "micro-F1", |
| "direction": "higher", |
| "minimal": 0.18034382095361662, |
| "neural_mlp": 0.1679279279279279 |
| } |
| }, |
| { |
| "name": "object_relevance: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "caption_grounding: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "caption_grounding: human_readable_display_name", |
| "status": "pass", |
| "expected": "Language Grounding", |
| "observed": "Language Grounding" |
| }, |
| { |
| "name": "caption_grounding: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "caption_grounding" |
| }, |
| { |
| "name": "caption_grounding: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "text-like query and candidate windows", |
| "raw_hits": [] |
| }, |
| { |
| "name": "caption_grounding: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Language-to-Moment Grounding", |
| "raw_hits": [] |
| }, |
| { |
| "name": "caption_grounding: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Language Grounding", |
| "raw_hits": [] |
| }, |
| { |
| "name": "caption_grounding: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Retrieve the matching time window for an annotation-derived text query.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "caption_grounding: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "query features -> candidate index -> cosine ranker", |
| "raw_hits": [] |
| }, |
| { |
| "name": "caption_grounding: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "ranked matching moments", |
| "raw_hits": [] |
| }, |
| { |
| "name": "caption_grounding: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Given a text-like query from annotation, find the matching time window.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "caption_grounding: known_task_family", |
| "status": "pass", |
| "observed": "retrieval", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "caption_grounding: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "language", |
| "video", |
| "depth", |
| "pose_slam" |
| ] |
| }, |
| { |
| "name": "caption_grounding: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "caption_grounding: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "caption_grounding: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "language", |
| "modalities": [ |
| "language", |
| "video", |
| "depth", |
| "pose_slam" |
| ] |
| }, |
| { |
| "name": "caption_grounding: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "mrr", |
| "name": "MRR", |
| "direction": "higher", |
| "minimal": 0.016023479050338015, |
| "neural_mlp": 0.01684125567132316 |
| } |
| }, |
| { |
| "name": "caption_grounding: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "cross_modal_retrieval: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: human_readable_display_name", |
| "status": "pass", |
| "expected": "Cross-Modal Retrieval", |
| "observed": "Cross-Modal Retrieval" |
| }, |
| { |
| "name": "cross_modal_retrieval: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "cross_modal_retrieval" |
| }, |
| { |
| "name": "cross_modal_retrieval: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "motion/IMU/pose query; depth/video candidates", |
| "raw_hits": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Multimodal Representation Retrieval", |
| "raw_hits": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Cross-Modal Retrieval", |
| "raw_hits": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Use motion, IMU, and camera-pose signals to retrieve the matching depth/video window.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "modality split -> projection -> nearest-neighbor ranker", |
| "raw_hits": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "ranked visual windows", |
| "raw_hits": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Use one group of modalities to retrieve the matching window from another group.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: known_task_family", |
| "status": "pass", |
| "observed": "retrieval", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "cross_modal_retrieval: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "motion_capture", |
| "inertial", |
| "pose_slam", |
| "depth", |
| "video" |
| ] |
| }, |
| { |
| "name": "cross_modal_retrieval: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "cross_modal_retrieval: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "depth", |
| "modalities": [ |
| "motion_capture", |
| "inertial", |
| "pose_slam", |
| "depth", |
| "video" |
| ] |
| }, |
| { |
| "name": "cross_modal_retrieval: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "mrr", |
| "name": "MRR", |
| "direction": "higher", |
| "minimal": 0.26925966892956127, |
| "neural_mlp": 0.1299971898648288 |
| } |
| }, |
| { |
| "name": "cross_modal_retrieval: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "modality_reconstruction: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "modality_reconstruction: human_readable_display_name", |
| "status": "pass", |
| "expected": "Cross-Modal Reconstruction", |
| "observed": "Cross-Modal Reconstruction" |
| }, |
| { |
| "name": "modality_reconstruction: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "modality_reconstruction" |
| }, |
| { |
| "name": "modality_reconstruction: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "motion, IMU, and camera/pose features", |
| "raw_hits": [] |
| }, |
| { |
| "name": "modality_reconstruction: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Modality Feature Reconstruction", |
| "raw_hits": [] |
| }, |
| { |
| "name": "modality_reconstruction: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Cross-Modal Reconstruction", |
| "raw_hits": [] |
| }, |
| { |
| "name": "modality_reconstruction: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Predict compressed depth/video feature vectors from motion, IMU, and camera-pose features.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "modality_reconstruction: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "source-target split -> scaler -> regression head", |
| "raw_hits": [] |
| }, |
| { |
| "name": "modality_reconstruction: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "reconstructed depth/video vector", |
| "raw_hits": [] |
| }, |
| { |
| "name": "modality_reconstruction: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Predict one modality feature block from other modality blocks.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "modality_reconstruction: known_task_family", |
| "status": "pass", |
| "observed": "forecast", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "modality_reconstruction: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "motion_capture", |
| "inertial", |
| "pose_slam", |
| "depth", |
| "video" |
| ] |
| }, |
| { |
| "name": "modality_reconstruction: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "modality_reconstruction: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "modality_reconstruction: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "depth", |
| "modalities": [ |
| "motion_capture", |
| "inertial", |
| "pose_slam", |
| "depth", |
| "video" |
| ] |
| }, |
| { |
| "name": "modality_reconstruction: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "r2", |
| "name": "R2", |
| "direction": "higher", |
| "minimal": -0.015271898913936655, |
| "neural_mlp": -0.010171410134180991 |
| } |
| }, |
| { |
| "name": "modality_reconstruction: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "temporal_order: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "temporal_order: human_readable_display_name", |
| "status": "pass", |
| "expected": "Temporal Order Verification", |
| "observed": "Temporal Order Verification" |
| }, |
| { |
| "name": "temporal_order: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "temporal_order" |
| }, |
| { |
| "name": "temporal_order: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "two adjacent windows plus difference vector", |
| "raw_hits": [] |
| }, |
| { |
| "name": "temporal_order: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Temporal Order Verification", |
| "raw_hits": [] |
| }, |
| { |
| "name": "temporal_order: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Temporal Order Verification", |
| "raw_hits": [] |
| }, |
| { |
| "name": "temporal_order: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Tell whether two neighboring windows are in chronological order or reversed.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "temporal_order: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "pair builder -> feature combiner -> binary classifier", |
| "raw_hits": [] |
| }, |
| { |
| "name": "temporal_order: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "correct or reversed", |
| "raw_hits": [] |
| }, |
| { |
| "name": "temporal_order: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Tell whether two nearby windows are in the correct time order.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "temporal_order: known_task_family", |
| "status": "pass", |
| "observed": "diagnostic", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "temporal_order: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "video", |
| "pose_slam", |
| "motion_capture", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "temporal_order: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "temporal_order: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "temporal_order: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "video", |
| "modalities": [ |
| "video", |
| "pose_slam", |
| "motion_capture", |
| "inertial" |
| ] |
| }, |
| { |
| "name": "temporal_order: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "f1", |
| "name": "F1", |
| "direction": "higher", |
| "minimal": 0.5399515738498789, |
| "neural_mlp": 0.8520179372197308 |
| } |
| }, |
| { |
| "name": "temporal_order: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "misalignment_detection: required_fields", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "misalignment_detection: human_readable_display_name", |
| "status": "pass", |
| "expected": "Multimodal Synchronization Detection", |
| "observed": "Multimodal Synchronization Detection" |
| }, |
| { |
| "name": "misalignment_detection: artifact_id_matches_key", |
| "status": "pass", |
| "observed": "misalignment_detection" |
| }, |
| { |
| "name": "misalignment_detection: public_field_input_short_is_human_readable", |
| "status": "pass", |
| "value": "motion-side and visual/depth-side feature groups", |
| "raw_hits": [] |
| }, |
| { |
| "name": "misalignment_detection: public_field_research_name_is_human_readable", |
| "status": "pass", |
| "value": "Cross-Modal Misalignment Detection", |
| "raw_hits": [] |
| }, |
| { |
| "name": "misalignment_detection: public_field_display_name_is_human_readable", |
| "status": "pass", |
| "value": "Multimodal Synchronization Detection", |
| "raw_hits": [] |
| }, |
| { |
| "name": "misalignment_detection: public_field_card_blurb_is_human_readable", |
| "status": "pass", |
| "value": "Detect whether motion and visual/depth streams have been artificially shifted out of sync.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "misalignment_detection: public_field_process_short_is_human_readable", |
| "status": "pass", |
| "value": "aligned/shifted pairs -> feature combiner -> binary classifier", |
| "raw_hits": [] |
| }, |
| { |
| "name": "misalignment_detection: public_field_output_short_is_human_readable", |
| "status": "pass", |
| "value": "aligned or shifted", |
| "raw_hits": [] |
| }, |
| { |
| "name": "misalignment_detection: public_field_plain_goal_is_human_readable", |
| "status": "pass", |
| "value": "Detect when modalities that should match are shifted out of sync.", |
| "raw_hits": [] |
| }, |
| { |
| "name": "misalignment_detection: known_task_family", |
| "status": "pass", |
| "observed": "diagnostic", |
| "allowed": [ |
| "diagnostic", |
| "forecast", |
| "retrieval", |
| "supervised" |
| ] |
| }, |
| { |
| "name": "misalignment_detection: modality_list_present", |
| "status": "pass", |
| "observed": [ |
| "motion_capture", |
| "inertial", |
| "video", |
| "depth", |
| "pose_slam" |
| ] |
| }, |
| { |
| "name": "misalignment_detection: known_modalities", |
| "status": "pass", |
| "unknown": [] |
| }, |
| { |
| "name": "misalignment_detection: modality_assets_exist", |
| "status": "pass", |
| "missing": [] |
| }, |
| { |
| "name": "misalignment_detection: poster_modality_in_task_modalities", |
| "status": "pass", |
| "poster_modality": "pose_slam", |
| "modalities": [ |
| "motion_capture", |
| "inertial", |
| "video", |
| "depth", |
| "pose_slam" |
| ] |
| }, |
| { |
| "name": "misalignment_detection: numeric_minimal_and_neural_metrics", |
| "status": "pass", |
| "metric": { |
| "key": "f1", |
| "name": "F1", |
| "direction": "higher", |
| "minimal": 0.5051698670605613, |
| "neural_mlp": 0.7152682255845944 |
| } |
| }, |
| { |
| "name": "misalignment_detection: middle_modules_explain_process", |
| "status": "pass", |
| "observed_count": 5 |
| }, |
| { |
| "name": "markdown_heading_present:timeline_action", |
| "status": "pass", |
| "expected": "### Action Recognition (`timeline_action`)" |
| }, |
| { |
| "name": "markdown_heading_present:timeline_subtask", |
| "status": "pass", |
| "expected": "### Procedure Step Recognition (`timeline_subtask`)" |
| }, |
| { |
| "name": "markdown_heading_present:transition_detection", |
| "status": "pass", |
| "expected": "### Action Boundary Detection (`transition_detection`)" |
| }, |
| { |
| "name": "markdown_heading_present:next_action", |
| "status": "pass", |
| "expected": "### Next-Action Prediction (`next_action`)" |
| }, |
| { |
| "name": "markdown_heading_present:hand_trajectory_forecast", |
| "status": "pass", |
| "expected": "### Hand Trajectory Forecasting (`hand_trajectory_forecast`)" |
| }, |
| { |
| "name": "markdown_heading_present:contact_prediction", |
| "status": "pass", |
| "expected": "### Contact State Prediction (`contact_prediction`)" |
| }, |
| { |
| "name": "markdown_heading_present:object_relevance", |
| "status": "pass", |
| "expected": "### Object Relevance Prediction (`object_relevance`)" |
| }, |
| { |
| "name": "markdown_heading_present:caption_grounding", |
| "status": "pass", |
| "expected": "### Language Grounding (`caption_grounding`)" |
| }, |
| { |
| "name": "markdown_heading_present:cross_modal_retrieval", |
| "status": "pass", |
| "expected": "### Cross-Modal Retrieval (`cross_modal_retrieval`)" |
| }, |
| { |
| "name": "markdown_heading_present:modality_reconstruction", |
| "status": "pass", |
| "expected": "### Cross-Modal Reconstruction (`modality_reconstruction`)" |
| }, |
| { |
| "name": "markdown_heading_present:temporal_order", |
| "status": "pass", |
| "expected": "### Temporal Order Verification (`temporal_order`)" |
| }, |
| { |
| "name": "markdown_heading_present:misalignment_detection", |
| "status": "pass", |
| "expected": "### Multimodal Synchronization Detection (`misalignment_detection`)" |
| }, |
| { |
| "name": "markdown_has_12_task_sections", |
| "status": "pass", |
| "observed": 12 |
| }, |
| { |
| "name": "markdown_contains_case_studies", |
| "status": "pass" |
| }, |
| { |
| "name": "website_marker_present:id=\"taskPlayer\"", |
| "status": "pass", |
| "marker": "id=\"taskPlayer\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"taskGrid\"", |
| "status": "pass", |
| "marker": "id=\"taskGrid\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"walkthroughSelector\"", |
| "status": "pass", |
| "marker": "id=\"walkthroughSelector\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"playerStoryboard\"", |
| "status": "pass", |
| "marker": "id=\"playerStoryboard\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"playerFrameChip\"", |
| "status": "pass", |
| "marker": "id=\"playerFrameChip\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"playerFrameCaption\"", |
| "status": "pass", |
| "marker": "id=\"playerFrameCaption\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"playerScrub\"", |
| "status": "pass", |
| "marker": "id=\"playerScrub\"" |
| }, |
| { |
| "name": "website_marker_present:fetch(\"data/task_walkthroughs.json\"", |
| "status": "pass", |
| "marker": "fetch(\"data/task_walkthroughs.json\"" |
| }, |
| { |
| "name": "website_marker_present:class=\"task-card\"", |
| "status": "pass", |
| "marker": "class=\"task-card\"" |
| }, |
| { |
| "name": "website_marker_present:class=\"task-card-media\"", |
| "status": "pass", |
| "marker": "class=\"task-card-media\"" |
| }, |
| { |
| "name": "website_marker_present:class=\"story-button", |
| "status": "pass", |
| "marker": "class=\"story-button" |
| }, |
| { |
| "name": "website_marker_present:class=\"flow-step", |
| "status": "pass", |
| "marker": "class=\"flow-step" |
| }, |
| { |
| "name": "website_marker_present:id=\"playerPlay\"", |
| "status": "pass", |
| "marker": "id=\"playerPlay\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"playerPrev\"", |
| "status": "pass", |
| "marker": "id=\"playerPrev\"" |
| }, |
| { |
| "name": "website_marker_present:id=\"playerNext\"", |
| "status": "pass", |
| "marker": "id=\"playerNext\"" |
| }, |
| { |
| "name": "website_no_artifact_id_css_or_markup", |
| "status": "pass" |
| }, |
| { |
| "name": "task_cards_do_not_render_artifact_ids", |
| "status": "pass" |
| }, |
| { |
| "name": "task_cards_render_human_names", |
| "status": "pass" |
| }, |
| { |
| "name": "task_cards_render_input_process_output", |
| "status": "pass" |
| }, |
| { |
| "name": "task_cards_use_representative_modality_thumbnail", |
| "status": "pass" |
| }, |
| { |
| "name": "interactive_player_wired_to_task_metadata", |
| "status": "pass" |
| }, |
| { |
| "name": "interactive_video_storyboard_controls_present", |
| "status": "pass" |
| }, |
| { |
| "name": "selector_uses_human_names", |
| "status": "pass" |
| }, |
| { |
| "name": "extension_probe_uses_human_name:body_motion_intensity", |
| "status": "pass", |
| "expected": "Body and Hand Motion Intensity" |
| }, |
| { |
| "name": "extension_probe_uses_human_name:multi_view_consistency_retrieval", |
| "status": "pass", |
| "expected": "Multi-View Consistency Retrieval" |
| }, |
| { |
| "name": "extension_probe_uses_human_name:action_phase_progress", |
| "status": "pass", |
| "expected": "Action Phase Progress Estimation" |
| }, |
| { |
| "name": "extension_probe_uses_human_name:ego_motion_forecast", |
| "status": "pass", |
| "expected": "Short-Horizon Ego-Motion Forecasting" |
| } |
| ], |
| "failures": [] |
| } |
|
|
