{"id":"W3177106525","doi":"","title":"The DELICES project: Indexing scientific literature through semantic expansion","year":2020,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Search engine indexing; Information retrieval; Natural language processing","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00325906,0.0002559586,0.0002372003,0.000123232,0.001503838,0.002443209,0.002950971,0.0001120946,0.000007453688],"category_scores_gemma":[0.001472507,0.0002001494,0.0001697659,0.002626731,0.0003262758,0.001304624,0.001158495,0.0004214345,0.00003626042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005361703,"about_ca_system_score_gemma":0.0001832518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001061158,"about_ca_topic_score_gemma":0.000262634,"domain_scores_codex":[0.9953209,0.002225181,0.0004589605,0.0009092833,0.0006478753,0.0004378355],"domain_scores_gemma":[0.9945873,0.00105915,0.0003544827,0.002108067,0.001759294,0.000131734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001251976,0.000268906,0.0007067114,0.00009721847,0.00007357468,0.00002084669,0.08131815,0.00005081629,0.0402476,0.684333,0.006209546,0.1866611],"study_design_scores_gemma":[0.0006717328,0.000002788323,0.0005718556,0.001485139,0.00004769627,0.0000345745,0.0005851933,0.2739337,0.4460319,0.04280538,0.2328217,0.001008309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01239874,0.002161162,0.9475592,0.02771207,0.0001144992,0.0003794697,0.000004206089,0.0007948873,0.008875728],"genre_scores_gemma":[0.7563465,0.0004498083,0.2402728,0.0005244226,0.00002913752,0.00005522138,0.00004199625,0.0000283164,0.002251745],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7439478,"threshold_uncertainty_score":0.9997961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01803808711150025,"score_gpt":0.2554298647587292,"score_spread":0.2373917776472289,"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."}}