{"id":"W2940481073","doi":"10.1002/gdj3.62","title":"From books to bytes: A new data rescue tool","year":2019,"lang":"en","type":"article","venue":"Geoscience Data Journal","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; McGill University","keywords":"Metadata; Computer science; Data mapping; Open data; World Wide Web; Traceability; Linked data; Data science; Schema (genetic algorithms); Unstructured data; Context (archaeology); Information retrieval; Database; Data mining; Semantic Web; Software engineering; Big data","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.001639684,0.0001596985,0.0002368443,0.0001486923,0.0003457922,0.002035139,0.01514793,0.00003929845,0.0002445775],"category_scores_gemma":[0.0004516591,0.0001272825,0.0000424194,0.0007399169,0.00002622846,0.00555841,0.008269971,0.0003081394,0.0008157278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003361679,"about_ca_system_score_gemma":0.0004858098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001278007,"about_ca_topic_score_gemma":0.0001669496,"domain_scores_codex":[0.9971216,0.00005512437,0.0004306077,0.001056697,0.0007764708,0.0005594871],"domain_scores_gemma":[0.9941145,0.00005603527,0.0001714729,0.00517493,0.00007406108,0.0004090308],"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":[0.00002067284,0.0000575618,0.001974927,0.000004528088,0.0000539899,0.00008842229,0.001148052,0.0005562534,0.003323767,0.001650892,0.2342018,0.7569191],"study_design_scores_gemma":[0.0003305419,0.000129666,0.003457422,0.00009596306,0.0000232868,0.00020263,0.0004844381,0.5135775,0.00006802092,0.001164092,0.4800527,0.0004137218],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03006372,0.0002700344,0.9613078,0.005144536,0.001711538,0.0001492139,0.0006239506,0.00006420759,0.000665012],"genre_scores_gemma":[0.08041698,0.00008854015,0.905214,0.003974387,0.002655618,0.000001315994,0.000523938,0.00002741414,0.007097772],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7565054,"threshold_uncertainty_score":0.9999623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0669314535514649,"score_gpt":0.2863183443244633,"score_spread":0.2193868907729984,"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."}}