{"id":"W7154110591","doi":"10.5281/zenodo.19546906","title":"Format Identification in Context: Patterns & Hazards in Digital Preservation Workflows","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Dementia Research Alliance; Library and Archives Canada","funders":"","keywords":"Digital preservation; Identification (biology); Workflow; Work (physics); Disparate system","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005196147,0.0002383618,0.0002348782,0.0009169362,0.001365973,0.005566023,0.0009681372,0.00004330599,0.003806148],"category_scores_gemma":[0.0002534228,0.0002691604,0.00009278347,0.0005061094,0.0002515067,0.002809135,0.00114029,0.0003482507,0.002585582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000303902,"about_ca_system_score_gemma":0.000009012196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009029867,"about_ca_topic_score_gemma":0.00003566687,"domain_scores_codex":[0.997626,0.0001532875,0.0007856477,0.0005399521,0.0004232984,0.0004718227],"domain_scores_gemma":[0.9989578,0.0000514146,0.000174464,0.0003977233,0.000326661,0.00009198016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001624733,0.0007720604,0.00008965902,0.000372556,0.0000632438,0.00001754817,0.007172612,0.0001662628,0.00001488934,0.4886108,0.02213256,0.4804253],"study_design_scores_gemma":[0.001052771,0.0001403144,0.03404129,0.0005399256,0.00001598401,0.000004308158,0.002965609,0.003030596,0.00001305606,0.02243351,0.9354854,0.0002773012],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1900237,0.0001375256,0.002832198,0.002473124,0.0004254077,0.001395349,0.00169007,0.0002917628,0.8007308],"genre_scores_gemma":[0.9837276,0.0001602187,0.000004893532,0.0002281452,0.0001169474,4.478036e-7,0.004233381,0.0003817878,0.01114661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9133528,"threshold_uncertainty_score":0.999976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02847358283132882,"score_gpt":0.2230646387635029,"score_spread":0.194591055932174,"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."}}