{"id":"W6966556966","doi":"10.48448/zvjr-kz09","title":"Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Alternation (linguistics); Word (group theory); Sentence; Verb; ENCODE","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"],"consensus_categories":[],"category_scores_codex":[0.00162987,0.0002777729,0.0003983518,0.001913601,0.0002397899,0.0001110873,0.0006737047,0.0001158884,0.0003704639],"category_scores_gemma":[0.0007463037,0.0002878267,0.00005281129,0.001377063,0.0005790212,0.0004708731,0.0003546709,0.0002773556,0.000002542808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009132064,"about_ca_system_score_gemma":0.0006063543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002836987,"about_ca_topic_score_gemma":0.004839448,"domain_scores_codex":[0.9974441,0.0000624899,0.0003986962,0.0007242616,0.00076605,0.000604404],"domain_scores_gemma":[0.9987418,0.0002031365,0.0004065202,0.0004051475,0.0001429249,0.0001004356],"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":[0.0001615667,0.001359602,0.001927241,0.001492098,0.0002215391,0.00003215519,0.0701721,0.01379321,0.01497318,0.8494663,0.04550819,0.0008927947],"study_design_scores_gemma":[0.008765575,0.00059243,0.0001166718,0.001400413,0.0002198445,0.00001160498,0.06991711,0.8310289,0.0006630033,0.04416167,0.04095261,0.002170133],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02029711,0.002487074,0.188948,0.0002433475,0.002427326,0.00993551,0.01048526,0.001767225,0.7634091],"genre_scores_gemma":[0.9645286,0.00003454936,0.01162194,0.00006059432,0.0003072177,0.0001996207,0.0003410354,0.0006093274,0.02229717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9442315,"threshold_uncertainty_score":0.9999574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04520536613552254,"score_gpt":0.3216495426044942,"score_spread":0.2764441764689716,"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."}}