{"id":"W1486865875","doi":"10.48550/arxiv.cs/0308033","title":"Coherent Keyphrase Extraction via Web Mining","year":2003,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Extraction (chemistry); Web mining; World Wide Web; Web page","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"],"consensus_categories":[],"category_scores_codex":[0.0003965453,0.000448274,0.0004989083,0.0002955291,0.0001528121,0.0001485629,0.001396822,0.000357486,0.00008856856],"category_scores_gemma":[0.00009715125,0.0004654715,0.0002889007,0.0004249987,0.00005958653,0.0005081909,0.001109714,0.0008305334,0.0002202134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002740706,"about_ca_system_score_gemma":0.000159085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003540766,"about_ca_topic_score_gemma":0.00004516877,"domain_scores_codex":[0.9972146,0.0001626913,0.0005707777,0.001172021,0.0004338588,0.0004460345],"domain_scores_gemma":[0.9970845,0.0001030539,0.0005688661,0.001905648,0.0001795716,0.000158337],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000467456,0.001694163,0.5481009,0.0005904728,0.00112753,0.0008819703,0.00238842,0.004415721,0.1470184,0.007560967,0.01857356,0.2676011],"study_design_scores_gemma":[0.002603175,0.00067088,0.1954626,0.002001885,0.001023123,0.000372711,0.0003206511,0.234498,0.330547,0.09351613,0.1285353,0.01044865],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3406997,0.0003095153,0.6552979,0.0002051333,0.0006513252,0.0002586925,0.000002054571,0.0007689939,0.001806656],"genre_scores_gemma":[0.8700726,0.0001617552,0.1281973,0.0003090204,0.0001505136,0.0001316456,0.00001988276,0.00003851875,0.0009187944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5293729,"threshold_uncertainty_score":0.9997797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04399676745781409,"score_gpt":0.3191097352841954,"score_spread":0.2751129678263813,"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."}}