{"id":"W4287549823","doi":"10.48550/arxiv.2012.12477","title":"IIRC: Incremental Implicitly-Refined Classification","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Benchmark (surveying); Computer science; Task (project management); Class (philosophy); Granularity; Artificial intelligence; Machine learning; Programming language; Engineering; Systems engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000196284,0.0002671356,0.0002567022,0.0001989851,0.0001921814,0.0001959661,0.001592129,0.0002089411,0.00007482002],"category_scores_gemma":[0.00004664776,0.0003294171,0.0001727442,0.0006059613,0.00006729373,0.0003580513,0.00152991,0.0006105751,0.0004577476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002391522,"about_ca_system_score_gemma":0.000186414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007318724,"about_ca_topic_score_gemma":0.0000160468,"domain_scores_codex":[0.9981194,0.000159797,0.0002265065,0.001075445,0.0001329221,0.0002859912],"domain_scores_gemma":[0.9984595,0.00006732228,0.0003022534,0.0008419314,0.0001067884,0.0002222646],"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":[0.0000477577,0.0001019888,0.002179134,0.00006875004,0.0001163842,0.0001800152,0.0007329079,0.02685458,0.003123252,0.9592068,0.001834806,0.005553667],"study_design_scores_gemma":[0.0006519459,0.00005805368,0.01226021,0.00004097715,0.00004001399,0.000003905303,0.0002532486,0.9558707,0.0001869604,0.02256231,0.007546893,0.0005247119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06273356,0.00002284106,0.9196215,0.001102114,0.0004793909,0.0002701502,0.000009164672,0.0005376963,0.01522362],"genre_scores_gemma":[0.9937489,0.00004932391,0.0043558,0.0006115151,0.00008572868,0.000001422891,0.00005279546,0.00001827875,0.001076258],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9366444,"threshold_uncertainty_score":0.9999158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1617675545790387,"score_gpt":0.2103964934366655,"score_spread":0.04862893885762673,"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."}}