{"id":"W3092429884","doi":"10.1609/aaai.v35i11.17161","title":"Interpretable Sequence Classification via Discrete Optimization","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Schwartz/Reisman Emergency Medicine Institute; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Vector Institute; Canadian Institute for Advanced Research; Agencia Nacional de Investigación y Desarrollo; Microsoft Research","keywords":"Computer science; Artificial intelligence; Sequence (biology); Automaton; Machine learning; TRACE (psycholinguistics); Class (philosophy); Task (project management); Pattern recognition (psychology); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006862648,0.0004285646,0.0004779885,0.0001815294,0.0002506119,0.001099461,0.003749128,0.0002877077,0.0001225485],"category_scores_gemma":[0.000558448,0.0003446894,0.0002513442,0.0006977504,0.0002600238,0.0005405046,0.002128172,0.001250215,0.00002742452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000117508,"about_ca_system_score_gemma":0.0003017091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001468418,"about_ca_topic_score_gemma":0.000006438032,"domain_scores_codex":[0.9968328,0.00006482463,0.0008418941,0.001118558,0.0007409112,0.0004009818],"domain_scores_gemma":[0.9967206,0.00008522956,0.001054789,0.0008068796,0.001217668,0.000114891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006307141,0.0003623914,0.0002816946,0.000468108,0.0001092179,0.000003185493,0.005477942,0.1169754,0.04486852,0.5688426,0.0001686677,0.2623792],"study_design_scores_gemma":[0.00001325999,0.0000687697,0.0000474958,0.0007937906,0.00002169303,0.000006208229,0.0002592224,0.8970646,0.06147345,0.03989432,0.00002285376,0.0003343757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00858897,0.00005065056,0.9754525,0.005088783,0.001476084,0.0005081023,0.00000928054,0.000212425,0.008613239],"genre_scores_gemma":[0.9445674,0.000109598,0.05450956,0.0001663464,0.0001248627,0.00006633877,0.00001108412,0.00002378067,0.0004209727],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9359785,"threshold_uncertainty_score":0.9999375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08354368913952419,"score_gpt":0.3199233827761914,"score_spread":0.2363796936366672,"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."}}