{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001532381,0.00007928885,0.00008839745,0.0004695201,0.0002623696,0.0002444483,0.00218036,0.00002742707,0.00007512106],"category_scores_gemma":[0.0009043403,0.00006415933,0.00001704399,0.0004562202,0.00005943879,0.0009405005,0.002371485,0.0004273347,0.00001282743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002114184,"about_ca_system_score_gemma":0.0002849789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001054028,"about_ca_topic_score_gemma":6.191465e-7,"domain_scores_codex":[0.9976454,0.00001580664,0.0003909775,0.0001653193,0.001565124,0.0002174042],"domain_scores_gemma":[0.9988451,0.0001278616,0.0001563885,0.0001439484,0.0006741132,0.00005255908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002444186,0.0001230904,0.02493952,0.00006345688,0.0000253151,8.092688e-7,0.00645116,0.0001665666,0.0007183166,0.9359294,0.001478711,0.02985923],"study_design_scores_gemma":[0.005718892,0.00114502,0.1492919,0.0005740608,0.000003141578,0.00009831906,0.01008976,0.2684644,0.07385817,0.2786306,0.2108798,0.001246057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9535571,0.00001212867,0.002416804,0.01029981,0.0006344082,0.0004549253,0.000008529868,0.0000467677,0.03256949],"genre_scores_gemma":[0.9918726,0.00001593147,0.007557464,0.0001983173,0.00001368831,0.00003806433,0.000003527518,0.000002247848,0.0002981232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6572988,"threshold_uncertainty_score":0.4051687,"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."}}