{"id":"W4404964783","doi":"10.4467/26581264arc.24.006.20201","title":"Artificial Intelligence and Machine Learning at the Intersection of Privacy and Archives","year":2024,"lang":"en","type":"article","venue":"Archeion","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Internet privacy; Intersection (aeronautics); Context (archaeology); Information privacy; Computer science; Data science; Engineering; History","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0002438279,0.00006714743,0.00006459805,0.00007630168,0.0001102684,0.00008255729,0.002244521,0.00002775372,0.000004654092],"category_scores_gemma":[0.001837041,0.00004681983,0.00001658633,0.0001859697,0.0002406456,0.0002138391,0.0273897,0.0002372464,0.000002991916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000116587,"about_ca_system_score_gemma":0.000009460064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002591281,"about_ca_topic_score_gemma":0.00001499149,"domain_scores_codex":[0.999343,0.00006734163,0.0001299129,0.000263093,0.00008721914,0.0001094283],"domain_scores_gemma":[0.9985443,0.0004117438,0.00003286025,0.0009880746,0.00000468104,0.00001836509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000010031,0.000007381372,0.0006825119,0.00004359584,0.00001160046,0.000003844234,0.001655938,0.00001108091,0.0147011,0.0282331,0.0001969235,0.9544429],"study_design_scores_gemma":[0.000008652231,0.00006765563,0.0007047774,0.00005865617,0.000003148687,0.00003198902,0.00006288951,0.5114862,0.04900797,0.4376538,0.0008649922,0.0000492575],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3376524,0.001292712,0.6474203,0.01291164,0.0001441122,0.00008485212,0.000002329449,0.0002428132,0.0002488383],"genre_scores_gemma":[0.9712194,0.0002951299,0.02840351,0.00001287284,0.00001501426,0.000004151461,0.000002623207,0.000004424448,0.00004293168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9543936,"threshold_uncertainty_score":0.9804766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06150934361323983,"score_gpt":0.2872432723693877,"score_spread":0.2257339287561478,"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."}}