{"id":"W4414763854","doi":"10.1055/a-2706-0201","title":"Artificial intelligence for colorectal polyp sizing: clinical promise and methodological challenges","year":2025,"lang":"en","type":"article","venue":"Endoscopy","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Colonoscopy; Colorectal Polyp; MEDLINE; Applications of artificial intelligence; Colonic disease","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":[0.001005058,0.0001183287,0.0003514474,0.00008498682,0.000094148,0.00001819892,0.00005288673,0.0001631148,0.00002054081],"category_scores_gemma":[0.002061461,0.00009781661,0.0001127817,0.0001302101,0.0001344641,0.00003019961,0.00004748654,0.0002334281,0.00000415766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003485787,"about_ca_system_score_gemma":0.00009501622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001378164,"about_ca_topic_score_gemma":0.00002908666,"domain_scores_codex":[0.9988511,0.0001394458,0.0003395553,0.0003775345,0.00009403427,0.0001983805],"domain_scores_gemma":[0.9982719,0.001378264,0.00005675136,0.0001299153,0.00006303767,0.0001001364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.02201682,0.0001999534,0.003622609,0.0001582616,0.0001072272,0.000009722427,0.0002416893,0.000001774098,0.005052987,0.008271606,0.0001979856,0.9601194],"study_design_scores_gemma":[0.003754881,0.04076639,0.1361307,0.0007609642,0.0008582,0.00009000283,0.002301905,0.01347822,0.6895095,0.07527677,0.03620944,0.0008631051],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8940007,0.005118523,0.08884683,0.005905105,0.001177947,0.001115739,0.000005702861,0.0002277805,0.003601682],"genre_scores_gemma":[0.9597314,0.0005748878,0.03873542,0.0002367742,0.0003457296,0.0001412706,0.000003107503,0.000009334148,0.000222083],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9592562,"threshold_uncertainty_score":0.3988846,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2457071866755708,"score_gpt":0.4667422370531577,"score_spread":0.2210350503775869,"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."}}