{"id":"W2995567445","doi":"10.1098/rstb.2018.0531","title":"Studying language in context using the temporal generalization method","year":2019,"lang":"en","type":"review","venue":"Philosophical Transactions of the Royal Society B Biological Sciences","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generalization; Context (archaeology); Computer science; Natural language processing; Artificial intelligence; Linguistics; Mathematics; Geography; Philosophy; Archaeology","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":[0.001835472,0.0002983626,0.0009344934,0.00005172944,0.0005048811,0.0001190889,0.00270141,0.0003736216,0.00001758022],"category_scores_gemma":[0.00008787616,0.0001267604,0.001133343,0.001610564,0.0006096585,0.0001265213,0.0001730683,0.0005628041,0.000005963579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110514,"about_ca_system_score_gemma":0.0002409151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005554316,"about_ca_topic_score_gemma":0.00001435314,"domain_scores_codex":[0.9966151,0.001210738,0.0006831456,0.0006286891,0.0004902266,0.0003720656],"domain_scores_gemma":[0.9981646,0.0007968008,0.0003974258,0.0005344131,0.00004397964,0.00006276453],"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":[0.00001039239,0.000578714,0.0004909466,0.002344664,0.0003551612,0.000004246683,0.0033245,0.01184339,0.00005567415,0.02642946,0.00005376588,0.9545091],"study_design_scores_gemma":[0.00274532,0.00211739,0.0004412101,0.0164349,0.001738719,0.0002236505,0.004424543,0.7308415,0.0002234184,0.06844534,0.1670997,0.005264356],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001713618,0.6803911,0.3165334,0.0009342913,0.0007487188,0.001012107,0.00002569997,0.0000506188,0.0001326911],"genre_scores_gemma":[0.2581294,0.6920013,0.04794737,0.0008344202,0.0007463286,0.0001812679,0.00001296862,0.00003491217,0.0001120029],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9492447,"threshold_uncertainty_score":0.5169138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2243793111162843,"score_gpt":0.3873992375860156,"score_spread":0.1630199264697313,"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."}}