{"id":"W2395903628","doi":"10.1007/978-3-662-49521-6_4","title":"Data Driven Discovery of Attribute Dictionaries","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Computer science; Information retrieval; Product (mathematics); Laptop; Task (project management); Relevance (law); Data mining; Value (mathematics); Scope (computer science); String (physics); Machine learning; Programming language","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007534345,0.0003670612,0.0005666949,0.0006705684,0.0001826711,0.0004636998,0.008026428,0.0001846976,0.00001241531],"category_scores_gemma":[0.0001679015,0.0002748934,0.0001123792,0.0005385575,0.001000164,0.002245754,0.005490168,0.0003580401,0.0000296333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091359,"about_ca_system_score_gemma":0.0006060858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001941827,"about_ca_topic_score_gemma":0.0000668256,"domain_scores_codex":[0.9964008,0.00003043189,0.0005354487,0.001626762,0.0009655506,0.0004409986],"domain_scores_gemma":[0.994934,0.0005812284,0.0003943531,0.003807651,0.0001865967,0.00009612613],"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":[0.000008921672,0.00006784962,0.001243303,0.00007713599,0.0001301127,0.0001036984,0.0004663948,0.006624495,0.0005080267,0.1070096,0.0004912005,0.8832693],"study_design_scores_gemma":[0.0007567737,0.0003514636,0.001230086,0.002409048,0.0001095831,0.0001128302,6.167198e-7,0.7875801,0.00237747,0.1824551,0.02056233,0.002054612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005354854,0.0003082393,0.9959021,0.001135776,0.0009322458,0.00009846048,0.0004616836,0.00007869885,0.001029291],"genre_scores_gemma":[0.387328,0.0003512459,0.6059947,0.0008991851,0.001403998,0.000006611319,0.0002948722,0.00006351516,0.003657821],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8812146,"threshold_uncertainty_score":0.9999703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03379014342007763,"score_gpt":0.2604976469360665,"score_spread":0.2267075035159889,"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."}}