{"id":"W3209896493","doi":"","title":"Partial order: Finding Consensus among Uncertain Feature Attributions","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Feature (linguistics); Computer science; Aggregate (composite); Order (exchange); Attribution; Rank (graph theory); Trustworthiness; Artificial intelligence; Machine learning; Post hoc; Psychology; Mathematics; Social psychology; Economics; Computer security","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":[0.0004012241,0.0004437663,0.0004676991,0.0002927845,0.000580921,0.0005028021,0.002046595,0.0005763152,0.00009978491],"category_scores_gemma":[0.0003187187,0.0005525416,0.0003070865,0.001827145,0.000307832,0.0004316547,0.002739191,0.001207329,0.0001379376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004930366,"about_ca_system_score_gemma":0.0007662332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009396966,"about_ca_topic_score_gemma":0.0007740156,"domain_scores_codex":[0.9967619,0.0003533846,0.000294146,0.001640992,0.0001780923,0.0007714548],"domain_scores_gemma":[0.9967206,0.0003003122,0.0003187151,0.001745786,0.0006081609,0.000306396],"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":[0.00002571697,0.0001954984,0.01021109,0.00008921597,0.0002102175,0.004635463,0.001070442,0.6185613,0.0002385284,0.3614079,0.002725761,0.0006288612],"study_design_scores_gemma":[0.0002987949,0.00006649342,0.001535219,0.0003014638,0.0001339498,0.00003044671,0.001561007,0.9653366,0.006693552,0.02030238,0.00251159,0.00122856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4296786,0.000119037,0.566142,0.000720241,0.001125335,0.0003306663,0.00002710713,0.0003624777,0.001494595],"genre_scores_gemma":[0.9924825,0.00009419047,0.004032441,0.0001171249,0.0001343,0.000003060989,0.0000637679,0.0000229914,0.003049619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5628039,"threshold_uncertainty_score":0.9996926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1165002914122213,"score_gpt":0.2276059895553315,"score_spread":0.1111056981431102,"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."}}