{"id":"W2165050191","doi":"10.1109/ccece.2006.277719","title":"Extracting Document Semantics for Semantic Header","year":2006,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Header; Information retrieval; Semantics (computer science); Search engine indexing; Context (archaeology); Key (lock); Generator (circuit theory); Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0002556163,0.00008235617,0.0001120865,0.00006737574,0.0001203707,0.0002424639,0.0003668079,0.00002628389,0.00001692528],"category_scores_gemma":[0.0000213496,0.00006843453,0.00007419709,0.0001898318,0.00001074227,0.0003617873,0.00008640488,0.00004179013,0.00004587919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001342369,"about_ca_system_score_gemma":0.0000190283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001914808,"about_ca_topic_score_gemma":0.0000445829,"domain_scores_codex":[0.9991635,0.00001350864,0.0001830929,0.0002632598,0.0001457739,0.0002308672],"domain_scores_gemma":[0.9993829,0.0001187214,0.00005571586,0.0003681687,0.00004149502,0.00003296855],"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":[0.000006881681,0.0004187555,0.007975513,0.0001683988,0.0001739536,0.00004661984,0.0006295645,0.002969605,0.01030879,0.7371276,0.1330075,0.1071668],"study_design_scores_gemma":[0.0009213238,0.0001134626,0.002596422,0.00006744076,0.00009974519,0.00004388322,0.0002919448,0.8494125,0.02169831,0.02579961,0.0981843,0.0007710265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009559319,0.00004172053,0.9841059,0.003115088,0.0001156955,0.0000645301,0.000001249026,0.0001462699,0.002850156],"genre_scores_gemma":[0.770852,0.00000179703,0.2239109,0.000200197,0.000120471,0.000007272832,0.000008992565,0.000005234002,0.004893105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8464429,"threshold_uncertainty_score":0.2790679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0150686889982663,"score_gpt":0.2610216164655017,"score_spread":0.2459529274672354,"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."}}