{"id":"W2133525847","doi":"10.1093/bioinformatics/btl235","title":"Integrating image data into biomedical text categorization","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Xerox Foundation","keywords":"Computer science; Annotation; Categorization; Information retrieval; Task (project management); Text categorization; Feature (linguistics); Artificial intelligence; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002103413,0.0001329272,0.0001200538,0.00005430243,0.0001012428,0.00005643402,0.0004742811,0.0002026163,0.00001598199],"category_scores_gemma":[0.0003676369,0.0001040749,0.00003227902,0.0001494919,0.00024048,0.00001283203,0.0003526437,0.00009435246,0.00006091693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001257314,"about_ca_system_score_gemma":0.00008570074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007881515,"about_ca_topic_score_gemma":0.0000462852,"domain_scores_codex":[0.999037,0.00002052934,0.0003666914,0.0001826985,0.0001859442,0.0002071253],"domain_scores_gemma":[0.9991942,0.0000186774,0.0001132421,0.0005507763,0.00005636639,0.00006675228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000470559,0.0002671909,0.001417037,0.0002705806,0.00007955966,0.000009451599,0.0006668491,0.00001012913,0.1989892,0.001868192,0.3606211,0.4357536],"study_design_scores_gemma":[0.0009132369,0.0003930226,0.001099081,0.00005098752,0.00003826678,0.00004147502,0.001967571,0.05210286,0.01997024,0.0009702352,0.9219054,0.0005475927],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09527966,0.0009655965,0.8895961,0.0009874966,0.0006739546,0.000269079,0.000105086,0.0001770119,0.01194603],"genre_scores_gemma":[0.5522034,0.0001095603,0.4368677,0.0004315426,0.0008783313,0.00001211039,0.008828098,0.0000282436,0.0006409833],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5612843,"threshold_uncertainty_score":0.4244052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01574011550689704,"score_gpt":0.2775507319346824,"score_spread":0.2618106164277854,"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."}}