{"id":"W3202143479","doi":"10.1016/j.procs.2021.08.123","title":"Inferring the Number and Order of Embedded Topics Across Documents","year":2021,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Order (exchange); Information retrieval; Data science; Theoretical computer science","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":[0.0005544286,0.0001204784,0.0001395829,0.000036524,0.0002871121,0.0005793641,0.001530675,0.00003882864,0.000003854278],"category_scores_gemma":[0.0001842965,0.00008455055,0.00002410046,0.001410396,0.0003748182,0.001131478,0.002138983,0.0001625639,0.000003734096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002513809,"about_ca_system_score_gemma":0.000279998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000110255,"about_ca_topic_score_gemma":0.000004046281,"domain_scores_codex":[0.9984565,0.00002598599,0.0002084442,0.0004854053,0.000481991,0.0003416711],"domain_scores_gemma":[0.9986261,0.00006946101,0.0001065394,0.0005508731,0.0005699664,0.00007709562],"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":[0.000004710227,0.0001283694,0.02277077,0.0002394805,0.00002278702,0.00006522665,0.02127753,0.00005099583,0.01443271,0.1566647,0.000448864,0.7838939],"study_design_scores_gemma":[0.0008357999,0.0001129223,0.01572086,0.0003702019,0.00001527002,0.0009523877,0.0001964158,0.2459617,0.592217,0.1398174,0.002798866,0.001001155],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1121082,0.0006053365,0.8850704,0.001190244,0.0004301129,0.0001175899,7.442048e-7,0.0001936604,0.0002837057],"genre_scores_gemma":[0.4481487,0.00001403749,0.5512245,0.0004855492,0.00005958435,0.000005925089,2.114154e-7,0.00000338964,0.00005808207],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7828928,"threshold_uncertainty_score":0.5586821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01020790319764575,"score_gpt":0.3080445696120024,"score_spread":0.2978366664143566,"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."}}