{"id":"W2950041219","doi":"10.4000/cognitextes.1584","title":"Conversational corpora : when “big is beautiful”","year":2019,"lang":"fr","type":"article","venue":"Cognitextes","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Introspection; Relevance (law); Linguistics; Relevance theory; Corpus linguistics; Computer science; Orientation (vector space); Natural language processing; Artificial intelligence; Psychology; Cognitive psychology; Philosophy; Mathematics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002686371,0.0003238409,0.0003310994,0.0001379272,0.0004300253,0.0007150513,0.0005237621,0.0001560871,0.1022518],"category_scores_gemma":[0.0000525581,0.0003242366,0.0001819396,0.00007163666,0.001029737,0.0005905124,0.0001953485,0.0003508644,0.0183876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006345806,"about_ca_system_score_gemma":0.0002790102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008845034,"about_ca_topic_score_gemma":0.0003021202,"domain_scores_codex":[0.9982099,0.0001608194,0.0004286813,0.0003887074,0.0003959873,0.0004159249],"domain_scores_gemma":[0.9978341,0.0005094195,0.0002906374,0.0007408545,0.0005008307,0.0001241258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003455006,0.000246456,0.003310557,0.0002165608,0.0002595269,0.000008868881,0.05458989,0.000004659651,0.00007907247,0.8263595,0.08911498,0.02577541],"study_design_scores_gemma":[0.0008354886,0.0001052553,0.001698259,0.0002705023,0.0001493883,0.00001031,0.03146611,0.0002533448,0.0002308415,0.06216586,0.902325,0.0004896139],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1447753,0.04929864,0.00006878923,0.0224617,0.004596379,0.0007225657,0.001523888,0.0001644531,0.7763882],"genre_scores_gemma":[0.662079,0.000421762,0.0001927484,0.002488676,0.0008953259,0.00002284877,0.0003491019,0.000042996,0.3335075],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8132101,"threshold_uncertainty_score":0.999921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04400968261029808,"score_gpt":0.2639706144185442,"score_spread":0.2199609318082462,"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."}}