{"id":"W2950982165","doi":"","title":"Coherent Keyphrase Extraction via Web Mining","year":2003,"lang":"en","type":"preprint","venue":"NPARC","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Information retrieval; Task (project management); Cluster analysis; Search engine indexing; Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0003432683,0.0003273917,0.0003890276,0.000258324,0.0001010293,0.0001863876,0.001167595,0.0002784174,0.0002130094],"category_scores_gemma":[0.00005881532,0.000340928,0.0002169778,0.0002973562,0.00004095743,0.0003173082,0.0008780428,0.0006420348,0.00007399585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002281433,"about_ca_system_score_gemma":0.0001454951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006969637,"about_ca_topic_score_gemma":0.00001750884,"domain_scores_codex":[0.9977785,0.000132729,0.0004156922,0.0008785992,0.0004563522,0.0003381482],"domain_scores_gemma":[0.9977864,0.00007746082,0.0003968017,0.001478487,0.0001373578,0.0001235042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001544321,0.0005353153,0.0008061539,0.0002286291,0.000298872,0.0002424151,0.0008945004,0.001402345,0.2365303,0.03251776,0.03043401,0.6960942],"study_design_scores_gemma":[0.0004567455,0.0001182844,0.000444511,0.0003575189,0.0001506451,0.00008779627,0.00004113475,0.2889412,0.07819459,0.5884381,0.04090295,0.001866554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008318343,0.0001143364,0.9631808,0.0002929224,0.0005773955,0.0002713865,0.000002798427,0.0007920093,0.02644999],"genre_scores_gemma":[0.4581722,0.00008069454,0.5405839,0.0001655376,0.00008674183,0.000108307,0.00001153082,0.00002233117,0.0007687232],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6942276,"threshold_uncertainty_score":0.9999043,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02164678121118828,"score_gpt":0.3037006518615237,"score_spread":0.2820538706503354,"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."}}