{"id":"W4235954735","doi":"10.1145/1871840","title":"Proceedings of the fourth workshop on Analytics for noisy unstructured text data","year":2010,"lang":"en","type":"paratext","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Listing (finance); Analytics; Key (lock); Information retrieval; Data science; Library science; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003605658,0.0003922189,0.0004738446,0.0002002132,0.000142792,0.0003881791,0.01030707,0.0006603487,0.00008372161],"category_scores_gemma":[0.0004143144,0.0002259636,0.0001458875,0.0007183228,0.0001400871,0.0004226594,0.002256997,0.001109115,0.00003176662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004231878,"about_ca_system_score_gemma":0.0002596423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000158238,"about_ca_topic_score_gemma":0.00002960414,"domain_scores_codex":[0.9977538,0.000009862826,0.0004193702,0.0009212549,0.0005384459,0.0003572736],"domain_scores_gemma":[0.9965801,0.0001967212,0.0006470383,0.002012271,0.0004962565,0.00006763167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001497986,0.00003016505,0.000002309294,0.0002605866,0.00004673685,3.349521e-7,0.00009338052,0.000003783711,0.001437512,0.03249543,0.9223766,0.04323817],"study_design_scores_gemma":[0.0007318765,0.000212058,0.00001808944,0.001792249,0.0001933488,0.00004545217,0.00005408783,0.05807144,0.1330539,0.05061902,0.7534752,0.001733319],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001788367,0.002090166,0.8937391,0.006784919,0.006484035,0.003145142,0.0006670997,0.0007573481,0.08615335],"genre_scores_gemma":[0.00463625,0.00005399103,0.8961833,0.0008551338,0.0005140142,0.00002984011,0.0001057354,0.00005231457,0.0975694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1689014,"threshold_uncertainty_score":0.9950476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03335583564651252,"score_gpt":0.3122525185803998,"score_spread":0.2788966829338873,"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."}}