{"id":"W2601411009","doi":"10.29173/cais254","title":"A Pilot Study of Enhancing Subject Discovery of Textual Web Resources","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Subject (documents); World Wide Web; Computer science; Web page; Search engine indexing; Information retrieval; Library science; Humanities; Art","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001295029,0.0005754547,0.001489188,0.0005203522,0.0001519881,0.002289275,0.004953921,0.0001613809,0.00003772954],"category_scores_gemma":[0.01400978,0.0004731809,0.0003643467,0.001639417,0.001316992,0.02399628,0.002559831,0.0005497414,0.000003744364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000098043,"about_ca_system_score_gemma":0.0004912025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004761586,"about_ca_topic_score_gemma":0.0004319852,"domain_scores_codex":[0.9953707,0.0001322015,0.001770144,0.0007672901,0.001229279,0.0007303685],"domain_scores_gemma":[0.9440171,0.00058464,0.003265235,0.0007243928,0.05124644,0.0001621748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003659723,0.004395661,0.1915504,0.001791635,0.0008137929,0.00000372902,0.1341128,0.00003898371,0.6178169,0.03155838,0.001957235,0.01559449],"study_design_scores_gemma":[0.002247428,0.01525004,0.160133,0.004066923,0.0008467197,0.00005681876,0.03922616,0.004803023,0.7505832,0.01777744,0.003622399,0.001386869],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9921894,0.0008220744,0.001266583,0.0008844775,0.000170354,0.00106339,0.00009648946,0.00007084561,0.003436408],"genre_scores_gemma":[0.9943106,0.0002018831,0.003482632,0.00005711342,0.00009709765,0.00006798535,0.000001192437,0.00004119877,0.001740261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1327663,"threshold_uncertainty_score":0.999772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02870723248325691,"score_gpt":0.2627259957605843,"score_spread":0.2340187632773273,"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."}}