{"id":"W3082570699","doi":"10.48550/arxiv.2106.14731","title":"The DELICES project: Indexing scientific literature through semantic expansion","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Search engine indexing; Computer science; Relevance (law); Information retrieval; Scientific literature; Digital library; Data science; World Wide Web; Linguistics; Political science","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005125207,0.0003934429,0.000366531,0.0003211709,0.001069307,0.002319549,0.003428602,0.0003323956,0.000003648486],"category_scores_gemma":[0.00008726837,0.0003359136,0.00035192,0.002909683,0.000289157,0.001578123,0.004436606,0.0009870736,0.00001212942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000205267,"about_ca_system_score_gemma":0.0004048792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001042434,"about_ca_topic_score_gemma":0.0001928739,"domain_scores_codex":[0.9969124,0.0002651812,0.0002864415,0.001798063,0.0002498399,0.0004880889],"domain_scores_gemma":[0.9960142,0.0001785679,0.0004042107,0.002730947,0.000598446,0.00007359446],"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":[0.00006484358,0.0005431639,0.002760303,0.000711508,0.0008861591,0.003804842,0.02203942,0.1047886,0.004127766,0.83924,0.003570139,0.01746326],"study_design_scores_gemma":[0.0003700296,0.00006006123,0.0002640423,0.001534039,0.0002184051,0.0000332754,0.001147437,0.6736758,0.007779569,0.305284,0.008139682,0.001493657],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1492249,0.001351943,0.8467357,0.0001507018,0.0006455109,0.0003821938,0.000003641282,0.0005710439,0.0009343613],"genre_scores_gemma":[0.980073,0.0009940203,0.01647764,0.00007721529,0.00006635446,0.000003693304,0.00003444593,0.00002149618,0.002252091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8308482,"threshold_uncertainty_score":0.9999093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06650420550289016,"score_gpt":0.2294048143742566,"score_spread":0.1629006088713665,"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."}}