{"id":"W4385570310","doi":"10.18653/v1/2023.acl-short.152","title":"A Simple and Effective Framework for Strict Zero-Shot Hierarchical Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Benchmark (surveying); Computer science; Task (project management); Contradiction; Zero (linguistics); Process (computing); Artificial intelligence; Machine learning; Shot (pellet); Simple (philosophy); Programming language; Geography; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004548736,0.002160523,0.002069195,0.002910708,0.002029338,0.002755798,0.005298891,0.002909608,0.007032503],"category_scores_gemma":[0.01418544,0.001000021,0.001889113,0.002255352,0.001527505,0.005998396,0.004779827,0.005975462,0.006483866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00170317,"about_ca_system_score_gemma":0.003565317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007756465,"about_ca_topic_score_gemma":0.01653941,"domain_scores_codex":[0.9962094,0.001187657,0.0002629156,0.001307222,0.0007354001,0.0002974931],"domain_scores_gemma":[0.9952427,0.001894602,0.0003138907,0.001404395,0.0008300695,0.0003143256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005425844,0.00066802,0.003822604,0.0004894254,0.0002719996,0.0002984176,0.000617652,0.05575407,0.0168694,0.05655576,0.04190176,0.8222083],"study_design_scores_gemma":[0.00004500394,0.00009715826,0.0005303025,0.00004945092,0.00004413861,0.000143496,0.0001022492,0.9118033,0.004274291,0.07648399,0.006374394,0.00005217532],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006252017,0.000607261,0.9836559,0.0004459349,0.0001487426,0.0002051124,0.0005279188,0.006818934,0.001338061],"genre_scores_gemma":[0.2471038,0.0004720486,0.7356779,0.00110475,0.0005640226,0.0007063382,0.006194144,0.001130208,0.00704679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007756465,"threshold_uncertainty_score":0.02405632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05952995306102866,"score_gpt":0.3286750313388974,"score_spread":0.2691450782778687,"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."}}