{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000294146,0.00006305194,0.00008173082,0.00007527183,0.00009238824,0.00008547725,0.0002212751,0.000063257,0.000003018498],"category_scores_gemma":[0.0002097628,0.00005407294,0.00002732761,0.0003024567,0.00001687864,0.0001265092,0.0001268188,0.00009488541,0.00001695737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000172078,"about_ca_system_score_gemma":0.00001860611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007790411,"about_ca_topic_score_gemma":0.000001339012,"domain_scores_codex":[0.9992642,0.0000415041,0.0001024331,0.0003055142,0.0001086476,0.0001777314],"domain_scores_gemma":[0.9985929,0.001021762,0.00002319046,0.0002735375,0.00002942036,0.00005923756],"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":[0.000005123177,0.000008697042,0.0008622169,0.00001174029,0.000005924655,7.883556e-7,0.0002723914,0.00008873683,0.0003491935,0.8823319,0.0005949929,0.1154683],"study_design_scores_gemma":[0.0001234617,0.00004667212,0.02040924,0.000005005931,0.000001829601,9.171855e-7,0.00001573309,0.6244922,0.0002326188,0.3537159,0.0008919769,0.00006443432],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05233097,0.000008294344,0.9450991,0.001490996,0.0001059925,0.0003299849,0.000001534249,0.0002672675,0.0003658616],"genre_scores_gemma":[0.8471074,0.000004438668,0.1524577,0.0001904925,0.00005163595,0.00009193902,0.000002862133,0.000004543043,0.00008893915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7947764,"threshold_uncertainty_score":0.220503,"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."}}