{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002348078,0.001611956,0.001339529,0.01308089,0.001206836,0.002983325,0.001472895,0.001349852,0.003104736],"category_scores_gemma":[0.01564712,0.0007922284,0.001548983,0.01069909,0.0008047823,0.004820709,0.002142414,0.001305333,0.004792546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000682753,"about_ca_system_score_gemma":0.001535089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001504788,"about_ca_topic_score_gemma":0.001909236,"domain_scores_codex":[0.9970228,0.0005550193,0.0004171316,0.0008034849,0.001010289,0.0001912325],"domain_scores_gemma":[0.9910777,0.00375469,0.00130085,0.00154199,0.002156946,0.0001677708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000436544,0.00022886,0.004738349,0.001168351,0.0001739014,0.0008314447,0.0005954363,0.007369768,0.06603757,0.009141454,0.01055716,0.8987212],"study_design_scores_gemma":[0.0002795307,0.0004848427,0.01587915,0.0004215928,0.0005277327,0.003632981,0.001743796,0.4729874,0.2514022,0.1298884,0.1224449,0.0003074726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03139867,0.001320103,0.9532977,0.000336591,0.00008056884,0.0005689046,0.002099376,0.008277277,0.002620727],"genre_scores_gemma":[0.123246,0.001027868,0.8659865,0.0001200852,0.0001225743,0.0003417538,0.006132848,0.0005982541,0.002424122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01308089,"threshold_uncertainty_score":0.01241797,"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."}}