{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00345805,0.0006311018,0.0007747384,0.002849464,0.0008983492,0.005236655,0.001271735,0.0007945259,0.003338252],"category_scores_gemma":[0.01654468,0.0005504311,0.0005312253,0.003509925,0.000995931,0.006149083,0.00327523,0.001097457,0.001813989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006931571,"about_ca_system_score_gemma":0.001047931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001170127,"about_ca_topic_score_gemma":0.001660068,"domain_scores_codex":[0.9970102,0.0005751465,0.0001979481,0.0004891585,0.001485716,0.0002418384],"domain_scores_gemma":[0.9853091,0.004875087,0.001399332,0.004145379,0.003811058,0.0004601526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003878134,0.0001479295,0.009283604,0.0003561134,0.00003667697,0.00007595711,0.001101206,0.002556447,0.04775671,0.004769624,0.005878533,0.9276494],"study_design_scores_gemma":[0.0001226283,0.0008920034,0.05421661,0.0007693511,0.0006561233,0.001901803,0.004863363,0.1864102,0.6112679,0.04317699,0.09543671,0.0002863533],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1904907,0.003463712,0.7745296,0.0009674774,0.0003046307,0.0004342252,0.0008753269,0.01078228,0.01815212],"genre_scores_gemma":[0.621321,0.001770077,0.3657281,0.0002247071,0.0002162165,0.0001263922,0.00107233,0.001852237,0.007688891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005236655,"threshold_uncertainty_score":0.01828814,"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."}}