{"id":"W7106841847","doi":"10.48448/z637-e867","title":"From Chat Logs to Collective Insights: Aggregative Question Answering","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Chatbot; Construct (python library); Conversation; Question answering; Task (project management); Conversation analysis; Through-the-lens metering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006333893,0.001412804,0.0009298088,0.003556366,0.001287245,0.003700565,0.001695822,0.00223724,0.002206612],"category_scores_gemma":[0.02653539,0.0005530097,0.001073834,0.002376707,0.001142603,0.006280699,0.004540615,0.002300672,0.00141723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009333271,"about_ca_system_score_gemma":0.001388796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007129191,"about_ca_topic_score_gemma":0.01241501,"domain_scores_codex":[0.99408,0.003804439,0.0002328571,0.001101155,0.0005526393,0.0002289402],"domain_scores_gemma":[0.9831881,0.01162327,0.0009989742,0.002538288,0.0009855588,0.0006658285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001378112,0.001695038,0.1002294,0.001687237,0.001130225,0.001637406,0.01874939,0.08751494,0.01735607,0.0455242,0.05896363,0.6641344],"study_design_scores_gemma":[0.00005547678,0.000139668,0.01295464,0.0001531988,0.0001260083,0.0002768369,0.004162872,0.8424614,0.004195452,0.1109129,0.02446965,0.00009194176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3223951,0.006221678,0.6229064,0.01128746,0.0005092784,0.0006108044,0.01115034,0.0126484,0.01227054],"genre_scores_gemma":[0.7797871,0.0005427469,0.2070885,0.0009459123,0.0003213459,0.0002602211,0.008613233,0.0002594948,0.00218145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007129191,"threshold_uncertainty_score":0.03349721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0314607735788219,"score_gpt":0.331171315706711,"score_spread":0.2997105421278892,"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."}}