{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006694529,0.0005961859,0.001139776,0.004790693,0.00141382,0.004930128,0.002053837,0.001366195,0.004262382],"category_scores_gemma":[0.02702393,0.0007447781,0.002676624,0.00507449,0.002297537,0.0043356,0.004604713,0.002251634,0.0007132704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003064626,"about_ca_system_score_gemma":0.002508932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00721861,"about_ca_topic_score_gemma":0.01431999,"domain_scores_codex":[0.9963633,0.00236861,0.0002422208,0.0004094162,0.0004967502,0.0001197512],"domain_scores_gemma":[0.9767134,0.01944295,0.0008516976,0.001931991,0.0007438837,0.0003160826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008725263,0.0001413917,0.003493929,0.0004164107,0.0002723312,0.0001805975,0.001544506,0.2389373,0.001098361,0.5987684,0.004586356,0.1504732],"study_design_scores_gemma":[0.00001367714,0.000009924783,0.0004311259,0.00002882038,0.00001879191,0.00001668549,0.0001137451,0.6980552,0.0001918984,0.2968749,0.004232477,0.00001274555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007687499,0.000659993,0.9881094,0.001163036,0.00003268703,0.0000715428,0.0001545818,0.0003366224,0.001784634],"genre_scores_gemma":[0.09606957,0.000372589,0.9005502,0.0002121072,0.00008862789,0.0005653366,0.0003678019,0.0001254767,0.001648352],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00721861,"threshold_uncertainty_score":0.03540444,"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."}}