{"id":"W2787171718","doi":"10.2218/ijdc.v13i1.620","title":"Data Mining Research with In-copyright and Use-limited Text Datasets: Preliminary Findings from a Systematic Literature Review and Stakeholder Interviews","year":2018,"lang":"en","type":"article","venue":"International Journal of Digital Curation","topic":"Library Collection Development and Digital Resources","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Institute of Museum and Library Services","keywords":"Intellectual property; Digitization; Harmonization; Standardization; Scholarly communication; Publishing; Stakeholder; Public relations; Data science; Best practice; Metadata; Political science; Knowledge management; Computer science; Library science; 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":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005132579,0.0001156775,0.0002206799,0.0004479436,0.00006743157,0.003143094,0.0008892429,0.00003614997,0.00000780283],"category_scores_gemma":[0.0006213369,0.00007834884,0.00001565551,0.0005196139,0.00007643674,0.02182724,0.0005649068,0.0001622977,0.000003671112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004134726,"about_ca_system_score_gemma":0.00008038036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001998924,"about_ca_topic_score_gemma":0.00001297652,"domain_scores_codex":[0.998363,0.00009412949,0.0005499436,0.0002677652,0.0006091067,0.0001160631],"domain_scores_gemma":[0.9985331,0.0004174934,0.0002635576,0.0002583285,0.000452388,0.0000751413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","study_design_scores_codex":[0.004985095,0.002445824,0.1738453,0.03248719,0.003859336,0.003774685,0.07315774,0.00001240348,0.0006054724,0.01419886,0.5286511,0.161977],"study_design_scores_gemma":[0.01174595,0.008673862,0.1278531,0.6507705,0.0004013458,0.01213248,0.003661176,0.0442048,0.001294194,0.01385443,0.122329,0.003079226],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8576657,0.09439445,0.02801798,0.01312681,0.001012831,0.0018523,0.001415958,0.00008742919,0.002426595],"genre_scores_gemma":[0.9920186,0.00244868,0.004285991,0.0004552272,0.0001233454,0.000007239734,0.000407092,0.00001041365,0.0002433777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6182833,"threshold_uncertainty_score":0.9978917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1379592423887494,"score_gpt":0.334114570782062,"score_spread":0.1961553283933126,"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."}}