{"id":"W4389072922","doi":"10.4230/lipics.itcs.2024.47","title":"Distribution Testing with a Confused Collector","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Staatssekretariat für Bildung, Forschung und Innovation; Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Cluster analysis; Oracle; Computer science; Mathematics; Property testing; Sample (material); Artificial intelligence; Combinatorics; Algorithm; Physics","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":[],"consensus_categories":[],"category_scores_codex":[0.02238299,0.001933811,0.002833838,0.001381616,0.001475079,0.00384112,0.006679968,0.004266087,0.003713373],"category_scores_gemma":[0.1299473,0.001091495,0.003280442,0.001399884,0.009720647,0.01358659,0.009256754,0.007096933,0.001408437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003513222,"about_ca_system_score_gemma":0.004228366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001669007,"about_ca_topic_score_gemma":0.001355005,"domain_scores_codex":[0.9689559,0.01327841,0.001633154,0.007303307,0.00675736,0.002071765],"domain_scores_gemma":[0.8472545,0.1028756,0.007637789,0.03359704,0.005567781,0.003067373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007648954,0.001159554,0.04103904,0.0006491471,0.0006866712,0.002168052,0.002148569,0.3216101,0.029742,0.4075113,0.009432666,0.176204],"study_design_scores_gemma":[0.0004321185,0.0008874952,0.001867243,0.0000808008,0.00009349176,0.0007785963,0.0003313386,0.6755354,0.03564782,0.2818344,0.002402006,0.0001093055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1192166,0.0002728107,0.8718,0.001896384,0.0001035133,0.0002597972,0.0002872836,0.003297552,0.002865999],"genre_scores_gemma":[0.8199518,0.00009963895,0.1749568,0.001115192,0.0001223329,0.000347981,0.0006892564,0.0004630176,0.002253984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02238299,"threshold_uncertainty_score":0.118374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1153048172818834,"score_gpt":0.1998867443031431,"score_spread":0.08458192702125973,"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."}}