{"id":"W147474551","doi":"10.1007/978-3-319-12823-8_1","title":"Content Profiling for Preservation: Improving Scale, Depth and Quality","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Profiling (computer programming); Computer science; Heuristics; Data mining; Metadata; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.0003190789,0.0001850117,0.0002132997,0.0001404447,0.0002594309,0.0005032645,0.00029795,0.0000243383,0.000009199342],"category_scores_gemma":[0.00003156982,0.0001487906,0.00005967942,0.00001532284,0.0006542602,0.0002942247,0.0002261988,0.00013261,0.000003213895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003162321,"about_ca_system_score_gemma":0.00004077348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003741141,"about_ca_topic_score_gemma":0.0004753002,"domain_scores_codex":[0.9987642,0.000007386489,0.0002623932,0.0004860709,0.0002753728,0.0002046141],"domain_scores_gemma":[0.9992285,0.0002839915,0.0001346136,0.0001863657,0.0001142181,0.00005230815],"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":[0.000007814971,0.000007886614,0.00003067358,0.000150368,0.000006169591,5.45583e-7,0.0006074341,0.0001780273,0.000005399111,0.6758056,0.00000497987,0.3231951],"study_design_scores_gemma":[0.0003917508,0.0002833306,0.001527198,0.000345159,0.00001900579,0.000002339266,0.000002872471,0.04152207,0.0001445743,0.9299765,0.02525344,0.0005317152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007970862,0.00005559541,0.9084824,0.0005264597,0.0005978751,0.0005762156,0.00004413785,0.00004335746,0.08887693],"genre_scores_gemma":[0.9264126,0.00000942007,0.05576487,0.002433949,0.002103794,0.00006218901,0.00009852795,0.0000364978,0.01307812],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9256155,"threshold_uncertainty_score":0.6067507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09244986003165974,"score_gpt":0.2507538816507074,"score_spread":0.1583040216190477,"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."}}