{"id":"W2593550342","doi":"10.1371/journal.pone.0184188","title":"Multi-level computational methods for interdisciplinary research in the HathiTrust Digital Library","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Hospitality and Tourism Research Centre, Hong Kong Polytechnic University; National Endowment for the Humanities","keywords":"Computer science; Digital library; Argument (complex analysis); Reading (process); Information retrieval; Domain (mathematical analysis); Zoom; Set (abstract data type); Resource (disambiguation); Data science; Identification (biology); Library classification; World Wide Web; Linguistics","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":[0.001173461,0.00009960437,0.0001845126,0.0002113167,0.0005833826,0.001024957,0.002846078,0.00005228709,0.000003786292],"category_scores_gemma":[0.0003110344,0.00007559631,0.00007147437,0.0002348976,0.0001909994,0.002223856,0.002180027,0.0002918192,0.00001816627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002975072,"about_ca_system_score_gemma":0.00005500389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001760329,"about_ca_topic_score_gemma":0.000002826684,"domain_scores_codex":[0.9985949,0.0001796357,0.0002178753,0.0003688682,0.0003691378,0.0002695579],"domain_scores_gemma":[0.997693,0.001068142,0.000105272,0.0009742926,0.0001152886,0.00004402167],"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":[0.00009486365,0.007130599,0.008554856,0.0002072839,0.0003400273,0.00007180876,0.005703124,0.000155125,0.003610862,0.09506862,0.003147321,0.8759155],"study_design_scores_gemma":[0.0004091125,0.00013796,0.01523416,0.0001626011,0.00001042748,0.000003374196,0.0001125304,0.5085726,0.005096145,0.4697636,0.0002970761,0.0002003964],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004586084,0.00005924874,0.9864294,0.007055975,0.00001608051,0.0004282803,0.00002135139,0.0001196558,0.001283947],"genre_scores_gemma":[0.2975683,0.000004057857,0.7019054,0.000076996,0.00004307214,0.0001222052,0.00001361277,0.000009594679,0.0002567545],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8757151,"threshold_uncertainty_score":0.9883681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4036673539531947,"score_gpt":0.4951515611119401,"score_spread":0.09148420715874545,"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."}}