{"id":"W2169142063","doi":"10.1613/jair.3940","title":"Topic Segmentation and Labeling in Asynchronous Conversations","year":2013,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Computer science; Asynchronous communication; Segmentation; Artificial intelligence; Conversation; Natural language processing; Exploit; Graph; Linguistics; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001483233,0.00005607758,0.0001292637,0.0006173765,0.00009331142,0.0002190246,0.0004075541,0.00003963238,0.00005487368],"category_scores_gemma":[0.0003308776,0.00004950662,0.00003205341,0.000753769,0.00009904255,0.001067455,0.0001150136,0.0003548369,0.00003760059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364216,"about_ca_system_score_gemma":0.0000981612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001492061,"about_ca_topic_score_gemma":0.00006485697,"domain_scores_codex":[0.9985737,0.0001609762,0.0004621408,0.0001356075,0.0004470028,0.0002206006],"domain_scores_gemma":[0.9986854,0.0003300168,0.0001209393,0.0001559603,0.0006273811,0.00008034636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005079478,0.00009118294,0.00166586,0.000009693793,0.00001290541,0.00002145948,0.002088136,0.0005984973,0.04945802,0.0401774,0.00006379978,0.905808],"study_design_scores_gemma":[0.00005879125,0.0004367064,0.001808388,0.0000965072,0.000004935979,0.00003980524,0.003578268,0.1695396,0.2807754,0.543384,0.0001115992,0.0001660705],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.214954,0.000177129,0.7828961,0.001651909,0.000049527,0.0001354386,8.147802e-8,0.00001141254,0.0001244048],"genre_scores_gemma":[0.8893526,0.0002283799,0.1103128,0.00002616236,0.00005024385,0.000007254876,1.301088e-7,0.000003137727,0.00001924419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9056419,"threshold_uncertainty_score":0.2112059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1082659095785678,"score_gpt":0.424850168063926,"score_spread":0.3165842584853582,"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."}}