{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002841959,0.0003176232,0.0002709733,0.001289229,0.0005811825,0.0002148182,0.001690143,0.0001147124,0.008159916],"category_scores_gemma":[0.0002123627,0.0002335564,0.00006280802,0.002904961,0.002175763,0.0002327727,0.0006542028,0.0007521925,0.002065058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002704093,"about_ca_system_score_gemma":0.0008647015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001227029,"about_ca_topic_score_gemma":0.00272491,"domain_scores_codex":[0.9959775,0.0001817845,0.0003587673,0.0008644923,0.001858829,0.0007586682],"domain_scores_gemma":[0.9987216,0.00008340029,0.0002703289,0.0007663537,0.00003069326,0.0001276532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006375157,0.001094665,0.008739132,0.00007634452,0.00006751543,0.0002157697,0.001381548,0.001577655,0.01069746,0.50666,0.4577913,0.01163484],"study_design_scores_gemma":[0.0004870878,0.00006919802,0.00109721,0.00008447249,0.00002660216,0.00003515455,0.0008280834,0.00410158,0.00005313423,0.001168708,0.9915894,0.0004593481],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.006578422,0.001172595,0.001447439,0.00131941,0.00387031,0.002182048,0.0002346781,0.0008813916,0.9823137],"genre_scores_gemma":[0.7826695,0.00009920796,0.001963453,0.0008699835,0.001112843,0.0002818492,0.0003719814,0.0009042969,0.2117269],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7760911,"threshold_uncertainty_score":0.9987119,"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."}}