{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005014638,0.0003088684,0.0003430694,0.0009438703,0.0004504441,0.0002524084,0.0004163594,0.0002351452,0.0003786185],"category_scores_gemma":[0.0002498986,0.0003797781,0.0001026338,0.0008740576,0.00004431736,0.001345881,0.00001917406,0.001201898,0.000126512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003787784,"about_ca_system_score_gemma":0.00004452577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008639758,"about_ca_topic_score_gemma":0.002314411,"domain_scores_codex":[0.9976152,0.0003010336,0.0009374886,0.0005673955,0.0002781718,0.0003006778],"domain_scores_gemma":[0.998037,0.0008063834,0.0001710919,0.0008409312,0.00008077235,0.00006375757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003916211,0.0001047732,0.004187169,0.00004953179,0.0001024384,0.0000029447,0.0003255511,0.9426379,0.01012655,0.0004044807,0.000132194,0.04188735],"study_design_scores_gemma":[0.0017065,0.000108422,0.08937339,0.0007237872,0.0002194503,0.00001124772,0.003490615,0.8952364,0.005029467,0.001282068,0.001930858,0.0008877594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0512927,0.0001454681,0.9426279,0.0007359548,0.001208741,0.0003004036,0.000008775247,0.0005912802,0.003088756],"genre_scores_gemma":[0.9912437,0.00007579462,0.007440813,0.0002434547,0.00005008799,0.00004370559,0.0006462556,0.00004146322,0.0002147262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.939951,"threshold_uncertainty_score":0.9998654,"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."}}