{"id":"W4284689311","doi":"10.1145/3477495.3531986","title":"H-ERNIE","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Relevance (law); Ambiguity; Focus (optics); Matching (statistics); Mores; Language model; Natural language; Information retrieval; Natural language processing; Artificial intelligence; Programming language","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":[0.001290699,0.0009575306,0.0008091152,0.001033167,0.001215057,0.001945522,0.000947763,0.001220695,0.1794634],"category_scores_gemma":[0.003034172,0.0003157968,0.0004543168,0.0008256669,0.0004878727,0.002443996,0.002222696,0.001668568,0.1180775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001088444,"about_ca_system_score_gemma":0.001985705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003148567,"about_ca_topic_score_gemma":0.00444122,"domain_scores_codex":[0.9992072,0.0001282073,0.00002849033,0.0002528914,0.0002550309,0.0001282714],"domain_scores_gemma":[0.9989492,0.0001663643,0.00004368357,0.0002532044,0.000412866,0.0001747038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005931939,0.0002015363,0.001872457,0.000360068,0.00005567274,0.0003317222,0.0001695624,0.002713128,0.008527428,0.03959766,0.3960782,0.5494995],"study_design_scores_gemma":[0.00009483234,0.0002056608,0.001483887,0.0001115518,0.00002954954,0.0004219281,0.0001223219,0.0169181,0.009201166,0.01669388,0.9546483,0.00006885948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02333816,0.006609685,0.133354,0.01390836,0.01116533,0.0006439419,0.01117371,0.02004192,0.7797649],"genre_scores_gemma":[0.1352332,0.002999102,0.06315598,0.004110343,0.001722596,0.0003341497,0.01787258,0.002268777,0.7723034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1794634,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0967995303531606,"score_gpt":0.3273152172855074,"score_spread":0.2305156869323468,"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."}}