{"id":"W38777760","doi":"10.1248/cpb.c24-00192","title":"Mots composés dans les modèles de langue pour la recherche d'information","year":2004,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Philosophy","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":[0.00044118,0.00005976688,0.00005386978,0.00004016318,0.00004404919,0.00008275725,0.0003782726,0.00008966702,0.000007656554],"category_scores_gemma":[0.00007458544,0.0000518052,0.00002453431,0.00008525208,0.000009765681,0.0004949787,0.00008440321,0.000136568,0.00006311719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001238771,"about_ca_system_score_gemma":0.00009140217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009267879,"about_ca_topic_score_gemma":0.00008927701,"domain_scores_codex":[0.9994788,0.00007607553,0.0001151112,0.00009194233,0.000105906,0.0001321596],"domain_scores_gemma":[0.9995551,0.0001114059,0.00002763937,0.0002298863,0.00003239656,0.0000436162],"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":[0.000001901301,0.00004273703,0.0006894448,0.00002093815,0.000009450329,0.000007457656,0.01290917,0.08190128,0.006757282,0.7502696,0.0003460072,0.1470448],"study_design_scores_gemma":[0.0004483802,0.00001414556,0.003277241,0.00002769364,0.000002641576,0.00005210004,0.0004888004,0.9247003,0.01408778,0.0545135,0.002214442,0.0001729718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04712568,0.00001016204,0.8907428,0.001887752,0.00003208835,0.00004322627,4.686888e-7,0.0001977403,0.0599601],"genre_scores_gemma":[0.4611358,0.000003369527,0.5384319,0.0002093017,0.00001581105,0.000002516776,9.75965e-7,0.000001807553,0.000198524],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.842799,"threshold_uncertainty_score":0.2112555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1890640294505659,"score_gpt":0.3222413363651943,"score_spread":0.1331773069146284,"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."}}