{"id":"W4415622320","doi":"10.1145/3773904","title":"Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstration","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Human-Robot Interaction","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; University of British Columbia","funders":"","keywords":"Consistency (knowledge bases); Generalization; Task (project management); Robot; Quality (philosophy); Robotics; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02828062,0.001464934,0.001253859,0.002922502,0.0008451189,0.003040225,0.002309222,0.002528183,0.001356016],"category_scores_gemma":[0.2289839,0.0008838325,0.001073141,0.00172574,0.003202319,0.006406043,0.005410212,0.003175181,0.0004098442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001750706,"about_ca_system_score_gemma":0.002275971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003314407,"about_ca_topic_score_gemma":0.002710296,"domain_scores_codex":[0.9737102,0.01129098,0.003423874,0.003577464,0.007222944,0.0007745257],"domain_scores_gemma":[0.7750314,0.1583537,0.02396296,0.02035783,0.01919011,0.00310394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002152306,0.001167191,0.1741703,0.001997122,0.0006553879,0.0004237261,0.003028437,0.2631491,0.02807514,0.02244546,0.003999131,0.4987368],"study_design_scores_gemma":[0.0002573959,0.00338954,0.0834497,0.0007670353,0.0002630657,0.0009223082,0.0009456787,0.8125364,0.03596988,0.05513946,0.006001148,0.0003584601],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1569763,0.001779112,0.8348719,0.001001554,0.0001175788,0.0004975664,0.0005999221,0.001547842,0.002608337],"genre_scores_gemma":[0.8229182,0.0002870033,0.1743154,0.0002818001,0.00006940068,0.0004725897,0.0008288185,0.0003761384,0.0004507423],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02828062,"threshold_uncertainty_score":0.149564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1635242660823105,"score_gpt":0.3779144299640027,"score_spread":0.2143901638816922,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}