{"id":"W57713726","doi":"10.20965/jaciii.2009.p0115","title":"Automatic Acquisition of Image Filtering and Object Extraction Procedures from Ground-Truth Samples","year":2009,"lang":"en","type":"article","venue":"Journal of Advanced Computational Intelligence and Intelligent Informatics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Ontario Tech University","funders":"","keywords":"Computer science; Artificial intelligence; Ground truth; Image processing; Sample (material); Object (grammar); Parameterized complexity; Image (mathematics); Computer vision; Digital image processing; Pattern recognition (psychology); Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0003691348,0.0001660486,0.0002987769,0.0002988972,0.00008011796,0.0001809523,0.0003245667,0.00005567953,0.00003050076],"category_scores_gemma":[0.0003016157,0.0001434986,0.00006873076,0.0002339028,0.0001058396,0.00275104,0.00006797425,0.0001927998,0.000002719365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005474073,"about_ca_system_score_gemma":0.00009229806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004847427,"about_ca_topic_score_gemma":4.002035e-7,"domain_scores_codex":[0.9978526,0.00003998409,0.00131604,0.0001146763,0.000527335,0.0001493624],"domain_scores_gemma":[0.9976249,0.0005673705,0.001057131,0.0001288052,0.0004983671,0.0001234735],"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":[0.00003839509,0.0001213961,0.00003595945,0.000164636,0.00004970565,0.000006763732,0.005329105,0.01466291,0.004512852,0.007875795,0.00006523779,0.9671372],"study_design_scores_gemma":[0.0002929802,0.001478574,0.005349983,0.001028837,0.00004471685,0.0004318591,0.004239248,0.4736912,0.229361,0.2836661,0.00004878586,0.0003667468],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09392165,0.0003432632,0.9052392,0.0001311956,0.0001301989,0.0001332267,0.000004912284,0.00003942569,0.00005687798],"genre_scores_gemma":[0.4647084,0.0006703457,0.5343435,0.0002380863,0.0000269988,0.000001398924,0.00000654412,0.000003082877,0.000001657837],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9667705,"threshold_uncertainty_score":0.5851705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02182776305152547,"score_gpt":0.3156307259324421,"score_spread":0.2938029628809167,"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."}}