{"id":"W1564589071","doi":"10.1007/978-3-540-69828-9_9","title":"An Entity Resolution Framework for Deduplicating Proteins","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Schema (genetic algorithms); Information retrieval; Data mining; Resolution (logic); Similarity (geometry); Database; Artificial intelligence; Image (mathematics)","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":[0.006426281,0.001271006,0.001773011,0.002571373,0.001619782,0.005336711,0.005450565,0.002083959,0.00588749],"category_scores_gemma":[0.009652432,0.001233105,0.002180192,0.004085881,0.001088641,0.007479455,0.004486597,0.002863995,0.002896417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001015376,"about_ca_system_score_gemma":0.001921783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0040728,"about_ca_topic_score_gemma":0.005778438,"domain_scores_codex":[0.9971147,0.000563525,0.0004543822,0.0004672328,0.001206678,0.0001934353],"domain_scores_gemma":[0.993811,0.00207249,0.0002990789,0.002654785,0.0009736445,0.0001891505],"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":[0.0006028975,0.0003104599,0.002031941,0.0007807752,0.0002074232,0.000748649,0.0007353271,0.04961132,0.008767749,0.1409927,0.07677922,0.7184315],"study_design_scores_gemma":[0.0001428982,0.0001288712,0.0006015293,0.0001868061,0.0003021574,0.001117801,0.0002952117,0.6097335,0.05553092,0.1946366,0.1371211,0.0002028069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002510475,0.0005798861,0.9797691,0.0003463678,0.0001295269,0.0001468163,0.001007005,0.01424278,0.001267871],"genre_scores_gemma":[0.03107495,0.0005664616,0.9589273,0.0002135296,0.00008030909,0.0001507502,0.003719239,0.001172675,0.00409476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006426281,"threshold_uncertainty_score":0.03398579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01361681863721773,"score_gpt":0.2551192057376525,"score_spread":0.2415023871004347,"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."}}