{"id":"W4283822869","doi":"10.1609/aaai.v36i6.20563","title":"Active Sampling for Text Classification with Subinstance Level Queries","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction; University of Wisconsin-Madison","keywords":"Computer science; Sample (material); Labeled data; Artificial intelligence; Annotation; Machine learning; Salient; Class (philosophy); Domain (mathematical analysis); Selection (genetic algorithm); Task (project management); Data mining; Information retrieval","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004527393,0.0001736811,0.000192819,0.00009905285,0.0007008317,0.0001787881,0.001555411,0.00003213641,0.00003612587],"category_scores_gemma":[0.0002212119,0.0001298783,0.00007549553,0.0006068809,0.0001710651,0.0003203852,0.0002935707,0.0003608366,0.000006493775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007825723,"about_ca_system_score_gemma":0.0001412463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003804187,"about_ca_topic_score_gemma":0.00001036907,"domain_scores_codex":[0.9984345,0.00002117394,0.0003111486,0.0004822519,0.0004717848,0.0002791657],"domain_scores_gemma":[0.9986635,0.0001422182,0.0004203061,0.000247226,0.0004773269,0.000049408],"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":[0.0001599078,0.00009319669,0.000102836,0.00002343575,0.00001225415,1.098884e-7,0.00206056,0.000533761,0.01455376,0.8570056,0.00006105789,0.1253935],"study_design_scores_gemma":[0.0001262526,0.001307151,0.001830805,0.0001869612,0.00002432001,0.00001734489,0.007033959,0.4993164,0.270155,0.2158618,0.003513744,0.0006263017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1216079,0.00002302763,0.8586314,0.01095795,0.0005963718,0.001009706,0.00005137055,0.0001999822,0.006922287],"genre_scores_gemma":[0.9775177,0.000005532614,0.02158511,0.000156645,0.00004951979,0.0001871864,0.000001530919,0.00001311206,0.0004836799],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8559098,"threshold_uncertainty_score":0.5390302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1621162943112375,"score_gpt":0.3247130027261861,"score_spread":0.1625967084149486,"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."}}