{"id":"W2951739148","doi":"10.48550/arxiv.1204.2231","title":"Investigating Keyphrase Indexing with Text Denoising","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Search engine indexing; Computer science; Benchmark (surveying); Noise reduction; Artificial intelligence; Natural language processing; Noise (video); Information retrieval; Energy (signal processing); Pattern recognition (psychology); Mathematics; Image (mathematics); Statistics","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":[0.0003479116,0.0004438925,0.0004457258,0.0004512676,0.0002810803,0.0002060073,0.00208224,0.0002854422,0.00001142858],"category_scores_gemma":[0.00005886357,0.0004693749,0.0001681037,0.001144411,0.0002071049,0.001234295,0.002800883,0.0009410742,0.0000347444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003573972,"about_ca_system_score_gemma":0.0002056924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001520517,"about_ca_topic_score_gemma":0.00006568347,"domain_scores_codex":[0.9976532,0.000148586,0.0002527656,0.001203749,0.0001711349,0.0005705249],"domain_scores_gemma":[0.9971755,0.0001299166,0.0005326294,0.001668559,0.0001910949,0.0003023361],"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":[0.00001783861,0.0002005934,0.08381144,0.0002300396,0.0004350955,0.0006236873,0.001809124,0.2893041,0.001459577,0.6149612,0.0001609676,0.006986335],"study_design_scores_gemma":[0.0008942173,0.0001123824,0.003886767,0.001264233,0.0005106092,0.00005010952,0.0003385163,0.6407052,0.007511601,0.3411063,0.0006134129,0.003006655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2167121,0.00008367448,0.7802585,0.00003696461,0.00008020008,0.0001830119,0.000001781227,0.0007243922,0.00191941],"genre_scores_gemma":[0.8897059,0.00002941472,0.1096941,0.000118837,0.00008236375,0.00000139428,0.000007879587,0.00003302349,0.0003270408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6729938,"threshold_uncertainty_score":0.9997758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07049531634463828,"score_gpt":0.2029032402727294,"score_spread":0.1324079239280911,"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."}}