{"id":"W2108703806","doi":"10.1145/2468356.2468803","title":"We need to talk","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; National Research Council Canada; Research and Productivity Council","funders":"","keywords":"Computer science; Usability; Leverage (statistics); Natural language; Human–computer interaction; Natural (archaeology); Domain (mathematical analysis); Spoken language; Perception; Speech community; Natural language understanding; Speech processing; Natural language processing; Artificial intelligence; Linguistics; Psychology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004773043,0.00004355648,0.00005387171,0.00004440936,0.00002190822,0.0001382144,0.000392503,0.00001849095,0.000205171],"category_scores_gemma":[0.00001431009,0.00003221904,0.00001964256,0.0001922693,0.000003709804,0.0002280344,0.0001063705,0.00001890851,0.009259935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008023341,"about_ca_system_score_gemma":0.00001321063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007149653,"about_ca_topic_score_gemma":0.00002318386,"domain_scores_codex":[0.9995358,0.00001053713,0.00007224795,0.0001319534,0.000100396,0.0001490926],"domain_scores_gemma":[0.9995188,0.00001775016,0.000009574285,0.0002966862,0.0000281622,0.0001291045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001388671,0.0000390432,0.0006300062,0.000007733105,0.000008391816,0.00001031494,0.001087333,0.00001596049,0.02040847,0.1428458,0.7214552,0.1134904],"study_design_scores_gemma":[0.001217616,0.0005598626,0.02117429,0.00005047825,0.000003247532,0.00009752924,0.0009297363,0.03044801,0.08430466,0.05656775,0.8034495,0.001197316],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03743712,0.00004715359,0.6965151,0.02137976,0.001144044,0.0003892323,3.095502e-7,0.0004502853,0.2426369],"genre_scores_gemma":[0.9414326,6.491142e-7,0.04508724,0.001812401,0.00009965737,0.00002658931,2.534449e-7,0.000002821351,0.0115378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9039955,"threshold_uncertainty_score":0.9915115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01390534073812762,"score_gpt":0.2172478889508535,"score_spread":0.2033425482127258,"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."}}