{"id":"W4392981558","doi":"10.1109/acdsa59508.2024.10467565","title":"Exploring an AI Data Dredging Birthday Paradox","year":2024,"lang":"en","type":"article","venue":"","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dredging; Computer science; Data science; Oceanography; Geology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.04762097,0.0005705362,0.001264326,0.004249867,0.00642657,0.009673203,0.003227122,0.004174393,0.00335643],"category_scores_gemma":[0.2484801,0.0008537573,0.0009303635,0.004240898,0.02038738,0.02515655,0.009444132,0.009559426,0.0004297118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002371075,"about_ca_system_score_gemma":0.001705021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001554748,"about_ca_topic_score_gemma":0.001203374,"domain_scores_codex":[0.9669191,0.02369742,0.001148839,0.003853255,0.003798013,0.0005833564],"domain_scores_gemma":[0.6610286,0.2967031,0.01565602,0.01871838,0.005559341,0.002334512],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001512746,0.00006401254,0.006933734,0.0001993526,0.00007109884,0.001096092,0.01111826,0.00410916,0.0003324324,0.9464179,0.003611196,0.02589556],"study_design_scores_gemma":[0.00001946877,0.0000289435,0.0008864172,0.0001175408,0.00001787606,0.0006059501,0.002410556,0.01320715,0.0004038309,0.9734908,0.00877628,0.00003533282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2779907,0.005304384,0.5555748,0.10793,0.001030907,0.0002216962,0.001067177,0.0004042653,0.05047603],"genre_scores_gemma":[0.8965825,0.001396884,0.09348612,0.005094682,0.0007515287,0.0001979205,0.0003463285,0.0001733981,0.001970692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.952379,"threshold_uncertainty_score":0.2518467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4739323664381699,"score_gpt":0.3641336581032815,"score_spread":0.1097987083348884,"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."}}