{"id":"W4400909973","doi":"10.1109/icde60146.2024.00436","title":"CAMO: Explaining Consensus Across MOdels","year":2024,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Waterloo","funders":"","keywords":"Computer science","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":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006232726,0.00008914599,0.0001220431,0.0001578334,0.0002199165,0.00238014,0.000690314,0.00002600469,0.000642625],"category_scores_gemma":[0.0007314152,0.00005822405,0.0000774099,0.0009673535,0.00008386941,0.0002368052,0.0005906897,0.00008258069,0.002926547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001925917,"about_ca_system_score_gemma":0.00003655921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007631892,"about_ca_topic_score_gemma":0.00004762567,"domain_scores_codex":[0.9973965,0.00006148365,0.0004004401,0.0007823309,0.001056173,0.0003030885],"domain_scores_gemma":[0.997584,0.001318524,0.00003216577,0.0008793259,0.00009311848,0.000092802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003409017,0.00001059944,0.00007821468,0.000003824331,0.00001128784,0.00007503488,0.00189313,0.00716925,0.00003104196,0.08849581,0.6221886,0.2800398],"study_design_scores_gemma":[0.00005822034,0.000008421956,0.00008855902,0.00001580856,0.000002446892,0.00001131696,0.003914884,0.7034518,0.00004507229,0.06113101,0.2311771,0.00009540217],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3420071,0.0005229196,0.3297426,0.003606481,0.007339138,0.0001709689,0.00006857928,0.000806122,0.3157361],"genre_scores_gemma":[0.9432055,0.000001455484,0.003336373,0.0002389828,0.00007917787,0.000002664925,0.000003397113,0.000005826284,0.05312663],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6962826,"threshold_uncertainty_score":0.9986555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3283073698216383,"score_gpt":0.4690964426371528,"score_spread":0.1407890728155145,"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."}}