{"id":"W4401041961","doi":"10.18653/v1/2024.starsem-1.10","title":"Lexical Substitution as Causal Language Modeling","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"Substitution (logic); Computer science; Natural language processing; Artificial intelligence; Linguistics; Programming language; Philosophy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001802066,0.0008705279,0.0007168982,0.001291224,0.0005888433,0.002187792,0.001664752,0.001151171,0.009877467],"category_scores_gemma":[0.009470994,0.0006151283,0.001118741,0.001395703,0.001270725,0.003941754,0.002024831,0.001888548,0.00380687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007531852,"about_ca_system_score_gemma":0.001707505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002081828,"about_ca_topic_score_gemma":0.003950182,"domain_scores_codex":[0.9980679,0.001061199,0.00009779161,0.0004124657,0.0002742835,0.00008643325],"domain_scores_gemma":[0.996223,0.00244943,0.0002315667,0.0006996089,0.0003099916,0.00008641338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003155858,0.0001754822,0.004254349,0.0006854165,0.0001710603,0.0007767664,0.001113314,0.1377013,0.0152105,0.3007606,0.02182253,0.5170131],"study_design_scores_gemma":[0.00002078983,0.00004348957,0.0003067071,0.00004909939,0.0000318608,0.0002294137,0.0001263903,0.7897636,0.005803851,0.1870705,0.0165247,0.00002951716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007599977,0.0002525311,0.9816768,0.0005009662,0.0001026733,0.00006958727,0.000556155,0.005467335,0.003774021],"genre_scores_gemma":[0.4432885,0.000509466,0.5441485,0.0005981775,0.0002152032,0.0002628239,0.002515343,0.001362882,0.007099156],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009877467,"threshold_uncertainty_score":0.03304344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01690305588437108,"score_gpt":0.3108748777878408,"score_spread":0.2939718219034697,"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."}}