{"id":"W4416035278","doi":"10.18653/v1/2025.emnlp-main.1667","title":"From Chat Logs to Collective Insights: Aggregative Question Answering","year":2025,"lang":"","type":"article","venue":"","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Question answering; Questions and answers; The Internet; Conversation analysis","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000360384,0.0004468396,0.0005913845,0.0006193838,0.0006400663,0.0007835522,0.001039146,0.0002823925,0.00006068952],"category_scores_gemma":[0.000264057,0.0004145429,0.0001411899,0.002329051,0.00009787038,0.0007170835,0.0006822405,0.0003178975,0.0003751289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000948793,"about_ca_system_score_gemma":0.000638992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006139824,"about_ca_topic_score_gemma":0.0005203216,"domain_scores_codex":[0.9965437,0.0004494386,0.0006400161,0.001363341,0.0004385849,0.0005649133],"domain_scores_gemma":[0.9978238,0.0004504138,0.0001925168,0.0008901174,0.0003811593,0.0002619583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002807292,0.0006993445,0.00195531,0.0001492341,0.000972736,0.0001506997,0.4618565,0.001499187,0.0246857,0.3023686,0.05202028,0.1533617],"study_design_scores_gemma":[0.003727521,0.001961262,0.007771558,0.01240147,0.0001302144,0.0000178566,0.01511178,0.4770713,0.3258654,0.07026372,0.08248297,0.003195027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06946992,0.002442286,0.8603742,0.00422815,0.007201339,0.0009395322,0.00001142388,0.0003190041,0.05501414],"genre_scores_gemma":[0.9444534,0.00007157357,0.01038926,0.00148254,0.0004459097,0.0001048012,0.000004107278,0.00001766405,0.04303071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8749835,"threshold_uncertainty_score":0.9998307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396950052420981,"score_gpt":0.2798178028179277,"score_spread":0.2658483022937179,"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."}}