{"id":"W4408028155","doi":"10.1145/3721127","title":"Accountability in Code Review: The Role of Intrinsic Drivers and the Impact of LLMs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Aalborg Universitet","keywords":"Accountability; Computer science; Code (set theory); Political science; Programming language","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":[0.002693548,0.00006857627,0.0002563763,0.00006829354,0.0001035448,0.000004869084,0.000192768,0.00007359125,0.00001999167],"category_scores_gemma":[0.004070922,0.00004239556,0.00007458567,0.0003303423,0.0006496846,0.0000477762,0.000009365554,0.0002003215,2.539075e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003716592,"about_ca_system_score_gemma":0.00006697102,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00756589,"about_ca_topic_score_gemma":0.001037773,"domain_scores_codex":[0.9989256,0.0005416321,0.00022635,0.0001140238,0.00007128604,0.000121134],"domain_scores_gemma":[0.99288,0.006764786,0.00004911114,0.0002289572,0.00005583085,0.00002132629],"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":[0.0004228657,0.0001302839,0.01425739,0.0003484872,0.0002760908,6.337572e-7,0.03404327,0.03030967,0.0006951038,0.03524908,0.0000548139,0.8842123],"study_design_scores_gemma":[0.005849501,0.001674708,0.2888158,0.007209421,0.002367405,0.00003994591,0.1062494,0.01240142,0.06622225,0.4156353,0.09107379,0.002461007],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5143952,0.01207553,0.4701984,0.001954408,0.0003599793,0.0007453171,0.00002295088,0.00006180844,0.0001863807],"genre_scores_gemma":[0.9841369,0.006812444,0.008934112,0.00006241409,0.000008302038,0.0000235167,2.418861e-7,0.000003615216,0.00001839208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8817513,"threshold_uncertainty_score":0.9990428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06464805720780835,"score_gpt":0.4021598462318052,"score_spread":0.3375117890239968,"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."}}