{"id":"W7082270936","doi":"10.48448/90a6-5210","title":"Deontological Keyword Bias: The Impact of Modal Verbs on Normative Judgments of Language Models","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Normative; Modal; Deontic logic; Phenomenon; Work (physics); Normative social influence","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":[],"consensus_categories":[],"category_scores_codex":[0.0006926163,0.0002489577,0.0003842246,0.0002711901,0.0001044151,0.00004685052,0.002655836,0.0001659569,0.0001549062],"category_scores_gemma":[0.0003130056,0.0001421578,0.0001371552,0.0009439068,0.000785905,0.0001553469,0.0006298274,0.0002789466,0.00001085247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007334647,"about_ca_system_score_gemma":0.0005781892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008226213,"about_ca_topic_score_gemma":0.00003390307,"domain_scores_codex":[0.9981403,0.00008279983,0.0003382496,0.0004799252,0.0005974318,0.0003612806],"domain_scores_gemma":[0.9981857,0.0002033187,0.000445388,0.0009110196,0.0001824888,0.00007206394],"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":[0.0001748524,0.002639579,0.001642479,0.0008140079,0.0008355146,0.0001125765,0.01490379,0.213638,0.009399449,0.4606701,0.1706948,0.1244749],"study_design_scores_gemma":[0.0009165995,0.0008331703,0.0009957911,0.0009460588,0.00004045217,0.00001761975,0.0008265865,0.9344342,0.009772334,0.04838157,0.002075911,0.0007596938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.002423391,0.0002009373,0.08040074,0.0005737999,0.0002201096,0.0003389967,0.00006160332,0.0001039153,0.9156765],"genre_scores_gemma":[0.9462246,0.00002603658,0.00645462,0.0001308362,0.00004635967,0.000009187152,0.000008363137,0.000008708412,0.04709124],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9438013,"threshold_uncertainty_score":0.5797028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03666181359114068,"score_gpt":0.3066115706599349,"score_spread":0.2699497570687942,"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."}}