{"id":"W3134614468","doi":"10.31234/osf.io/gvr6m","title":"Do We Need Neural Models to Explain Human Judgments of Acceptability?","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Social Science Fund of China; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Sentence; Computer science; Natural language processing; Language model; Word (group theory); Artificial intelligence; Simple (philosophy); Variance (accounting); Similarity (geometry); n-gram; Sentence processing; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001095098,0.00009605959,0.0001571525,0.00004513445,0.00004141825,0.00006232731,0.0009439913,0.00002970974,0.0001189414],"category_scores_gemma":[0.000013878,0.00008697265,0.0000539814,0.0002429606,0.00001106106,0.0004659207,0.0005705755,0.00007185357,0.00002009191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001759586,"about_ca_system_score_gemma":0.00001559096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006736543,"about_ca_topic_score_gemma":0.000006794499,"domain_scores_codex":[0.9988692,0.0000364566,0.000268569,0.0003788425,0.0002565113,0.0001903917],"domain_scores_gemma":[0.9992266,0.00002203559,0.00003871087,0.0005060949,0.00004088431,0.0001657258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002339131,0.0002086005,0.00266174,0.0001154922,0.00003556431,0.00001153233,0.03283168,0.1687489,0.02389737,0.456414,0.002781033,0.3122707],"study_design_scores_gemma":[0.000215953,0.0000829558,0.0002155807,0.000005360772,0.000001876691,4.027507e-7,0.000222435,0.9868174,0.004031813,0.008043784,0.0002377904,0.0001246415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2559695,0.00001884282,0.732932,0.007659798,0.00007858559,0.0001541075,7.641175e-7,0.0001104695,0.003075947],"genre_scores_gemma":[0.9332597,9.473843e-7,0.06528125,0.001324455,0.00003736127,0.000007246079,2.628054e-7,0.00000505962,0.00008370203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8180685,"threshold_uncertainty_score":0.3546642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1065612792918263,"score_gpt":0.2939703466880779,"score_spread":0.1874090673962516,"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."}}