{"id":"W4412900999","doi":"10.2139/ssrn.5368489","title":"Can Author Manipulation of AI Referees Be Welfare Improving?","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"FinTech, Crowdfunding, Digital Finance","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Welfare; Computer science; Psychology; Artificial intelligence; Political science; Law","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01683513,0.0005849899,0.001379595,0.003852047,0.00322462,0.008330057,0.002116306,0.005056082,0.06126009],"category_scores_gemma":[0.1306666,0.000359326,0.0008889041,0.004162716,0.003515831,0.009899858,0.003117863,0.002553141,0.009061397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002576318,"about_ca_system_score_gemma":0.005293053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005229221,"about_ca_topic_score_gemma":0.004632398,"domain_scores_codex":[0.9867574,0.006862638,0.0005619288,0.00155881,0.002468938,0.001790315],"domain_scores_gemma":[0.8533724,0.09057004,0.01683801,0.02059625,0.01413413,0.004489084],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001718486,0.001036408,0.02405095,0.0009039961,0.0003833803,0.0007265572,0.003126408,0.004127686,0.005834414,0.4993582,0.1105127,0.3482209],"study_design_scores_gemma":[0.0005308369,0.000533724,0.01625935,0.0003082876,0.0004162917,0.0006337966,0.002940123,0.01080896,0.004704024,0.8380563,0.1247149,0.00009353633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2032087,0.007478878,0.07946002,0.1293696,0.003550665,0.0004637109,0.002392624,0.002388001,0.5716878],"genre_scores_gemma":[0.9015695,0.002410111,0.01034996,0.009377114,0.002413165,0.0002210684,0.00039118,0.0003265052,0.07294134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9831648,"threshold_uncertainty_score":0.2049354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0180302053224359,"score_gpt":0.2536146709493167,"score_spread":0.2355844656268808,"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."}}