{"id":"W4226382178","doi":"10.48550/arxiv.2201.11308","title":"Calibration with Privacy in Peer Review","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Access Control and Trust","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Carnegie Mellon University; National Science Foundation","keywords":"Computer science; Adversary; Pareto principle; Block (permutation group theory); Calibration; Identity (music); Theoretical computer science; Data mining; Computer security; Information retrieval; Mathematical optimization; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0642241,0.001054002,0.002801248,0.002584979,0.003868998,0.009946326,0.004404071,0.005146843,0.006842044],"category_scores_gemma":[0.2730292,0.001500626,0.001280127,0.003948901,0.008783778,0.01549738,0.008974268,0.005586054,0.002851619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004288412,"about_ca_system_score_gemma":0.008049539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001075137,"about_ca_topic_score_gemma":0.0007991745,"domain_scores_codex":[0.8774117,0.07776407,0.005296411,0.01681556,0.01942453,0.003287735],"domain_scores_gemma":[0.6518986,0.2208358,0.03039632,0.07023358,0.02129046,0.005345154],"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":[0.0005167121,0.0001278135,0.005077854,0.0007661534,0.0002361684,0.0003600983,0.002128158,0.04165786,0.00258518,0.7733263,0.01199466,0.1612232],"study_design_scores_gemma":[0.0001273454,0.0001417386,0.0008565384,0.0001332472,0.00004874152,0.0003693383,0.0003010932,0.06300984,0.002458,0.9110652,0.02141197,0.00007696707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04820344,0.003236876,0.8955134,0.01847796,0.0005693485,0.0007888491,0.0004262776,0.0007760968,0.03200783],"genre_scores_gemma":[0.8524495,0.002003052,0.1267278,0.001746995,0.001110329,0.0007057186,0.0002839669,0.0002458919,0.01472677],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9357759,"threshold_uncertainty_score":0.3396536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1088335609356486,"score_gpt":0.2441590464734186,"score_spread":0.13532548553777,"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."}}