{"id":"W4306964455","doi":"10.31234/osf.io/qjnpv","title":"The Plausibility of Sampling as an Algorithmic Theory of Sentence Processing","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; McGill University","funders":"","keywords":"Computer science; Variance (accounting); Sampling (signal processing); Context (archaeology); Reading (process); Class (philosophy); Parsing; Sentence; Artificial intelligence; Natural language processing; Algorithm; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.002893062,0.0002386784,0.0003599127,0.0001153605,0.0002633361,0.0001819176,0.004123507,0.00014533,0.00003050879],"category_scores_gemma":[0.0003221431,0.0001615858,0.0001213747,0.0003572989,0.0002480994,0.0003370106,0.004588794,0.0008540659,4.326992e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009621575,"about_ca_system_score_gemma":0.0006146441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002575877,"about_ca_topic_score_gemma":0.00001306025,"domain_scores_codex":[0.9974052,0.0003348504,0.0006001939,0.0007340104,0.0006665444,0.0002591737],"domain_scores_gemma":[0.9967742,0.0003974092,0.0007165208,0.001684531,0.0003738353,0.00005349056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004691288,0.0001346482,0.0001070111,0.0005669473,0.0000298675,0.00000542656,0.003326619,0.0001491902,0.002039611,0.1526772,0.000009026027,0.8409076],"study_design_scores_gemma":[0.00006841867,0.0001316468,0.00010831,0.000278449,0.00001618552,0.00001924798,0.0006730368,0.04100651,0.026222,0.9311171,0.00006240293,0.0002966642],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0217808,0.004851225,0.9713303,0.0001785235,0.0002678901,0.0004444368,0.00001101755,0.0005141055,0.0006217325],"genre_scores_gemma":[0.4833159,0.0000267487,0.5164281,0.00005273197,0.00002374991,0.00003590859,0.000005107391,0.00001165375,0.0001000524],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8406109,"threshold_uncertainty_score":0.766257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03517788596247404,"score_gpt":0.337574704823559,"score_spread":0.3023968188610849,"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."}}