{"id":"W2147565428","doi":"10.1023/a:1025720518994","title":"Extending Dublin Core Metadata to Support the Description and Discovery of Language Resources","year":2003,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Metadata; Computer science; World Wide Web; Reuse; Computational linguistics; Information retrieval; Natural language processing; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005343618,0.00009584328,0.0001470489,0.0000716164,0.0002906409,0.001044352,0.0005169466,0.00001912384,0.000001439169],"category_scores_gemma":[0.00004736401,0.00005006407,0.0000272622,0.00009898462,0.0003052672,0.0007293458,0.0003579009,0.00008783895,3.005523e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007491564,"about_ca_system_score_gemma":0.00001179952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009026449,"about_ca_topic_score_gemma":0.00002669446,"domain_scores_codex":[0.9993474,0.00008938657,0.0001414883,0.0001692933,0.0001333445,0.0001191095],"domain_scores_gemma":[0.9993799,0.0001831677,0.00007962592,0.0003121344,0.00002959369,0.00001560174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000105421,0.000007134649,0.00003375335,0.0000271042,0.00001447835,0.000005007731,0.01631833,0.000001149705,0.0003606961,0.9762457,0.0005128667,0.00646323],"study_design_scores_gemma":[0.005074997,0.001728446,0.00307833,0.001319292,0.0003241335,0.001143784,0.03377709,0.02114188,0.0383055,0.814691,0.0771773,0.002238235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.394622,0.01214563,0.5913869,0.0004794148,0.0002658948,0.0003038728,0.0000069856,0.0001414322,0.0006479376],"genre_scores_gemma":[0.9645044,0.00004193656,0.03403421,0.0006625314,0.00003339439,0.000007165126,0.000001413632,0.00000549142,0.0007095187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5698823,"threshold_uncertainty_score":0.9999927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0398088240749413,"score_gpt":0.2605981528609337,"score_spread":0.2207893287859924,"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."}}