{"id":"W4402364429","doi":"10.1007/978-3-031-71167-1_2","title":"Assessing Logical Reasoning Capabilities of Encoder-Only Transformer Models","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Encoder; Transformer; Programming language; Electrical engineering; Operating system; Engineering","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":[0.002035826,0.0005094539,0.00064703,0.0006590955,0.0001756735,0.00077538,0.002869735,0.0004206386,0.00001578552],"category_scores_gemma":[0.0001348564,0.0004367758,0.0002098684,0.0007188137,0.001220498,0.002291534,0.0005201254,0.001027987,0.00001456943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000355558,"about_ca_system_score_gemma":0.0008782706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000255519,"about_ca_topic_score_gemma":0.00001498223,"domain_scores_codex":[0.995805,0.00006305251,0.0008315956,0.001489551,0.001198955,0.0006117991],"domain_scores_gemma":[0.9975001,0.0005148005,0.0002849414,0.001275255,0.0002921609,0.0001327832],"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":[0.000002969541,0.00001699619,0.000007215276,0.0001536454,0.000009149006,0.00001838612,0.002125609,0.04872911,0.000266253,0.5491207,0.000001806418,0.3995481],"study_design_scores_gemma":[0.00005488199,0.00008055213,0.00001812499,0.0005792421,0.00000831218,0.00007143777,0.000001238452,0.5722309,0.002248377,0.4242715,0.0001241694,0.0003112423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002469507,0.0009710284,0.9743296,0.0002326208,0.001665705,0.0003201369,0.000005129886,0.0001985155,0.02203032],"genre_scores_gemma":[0.1416396,0.00005328976,0.8576587,0.0001816106,0.0001791118,0.000008083522,0.000002273569,0.00003034482,0.0002469464],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5235018,"threshold_uncertainty_score":0.9998084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05022977370404413,"score_gpt":0.3112825095173428,"score_spread":0.2610527358132986,"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."}}