{"id":"W6966576373","doi":"10.48448/qs8n-4z25","title":"Grounding the Lexical Substitution Task in Entailment","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Substitution (logic); Textual entailment; Logical consequence; Task (project management); Sentence; Relation (database); Context (archaeology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00537871,0.001575289,0.001912873,0.003557994,0.002332869,0.003441097,0.003003308,0.002198949,0.009578913],"category_scores_gemma":[0.02705225,0.0009498536,0.001757322,0.003825054,0.002170084,0.01206002,0.007930874,0.002324221,0.005453197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001456179,"about_ca_system_score_gemma":0.002513555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003490118,"about_ca_topic_score_gemma":0.008287588,"domain_scores_codex":[0.9890751,0.004999467,0.001259455,0.002248846,0.002061609,0.0003554915],"domain_scores_gemma":[0.9883651,0.005456885,0.0006526002,0.003909475,0.001456333,0.0001596792],"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":[0.001572876,0.0005599085,0.009536776,0.003383737,0.0004300507,0.001352347,0.003186621,0.01760162,0.03454752,0.1936858,0.07178313,0.6623596],"study_design_scores_gemma":[0.0002747168,0.0004332562,0.005767942,0.0007224784,0.0004152599,0.002049461,0.002671525,0.3060693,0.09366938,0.404066,0.1836147,0.0002460401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1160772,0.003316369,0.8287225,0.002526925,0.0006270359,0.0007314659,0.009207206,0.01265833,0.02613287],"genre_scores_gemma":[0.3854288,0.0007030578,0.5839045,0.0007063563,0.0002046067,0.0005198636,0.02224311,0.001496886,0.004792796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009578913,"threshold_uncertainty_score":0.03204465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02902236310784589,"score_gpt":0.309155269678936,"score_spread":0.2801329065710901,"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."}}