{"id":"W4210424226","doi":"10.1101/2022.01.24.22269596","title":"Comprehensive Quantitative Evaluation of Inter-observer Delineation Performance of MR-guided Delineation of Oropharyngeal Gross Tumor Volumes and High-risk Clinical Target Volumes: An R-IDEAL Stage 0 Prospective Study","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Medicine; Nuclear medicine; Stage (stratigraphy); Head and neck cancer; Radiology; Radiological weapon; Radiation therapy; Medical physics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005665265,0.0003757209,0.0003058845,0.0007365735,0.0003825756,0.0005634787,0.0004810078,0.0004178231,0.0009136273],"category_scores_gemma":[0.009912485,0.0002537968,0.0004157828,0.000330908,0.0007311741,0.000722099,0.000783503,0.0002699932,0.0003472292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000383693,"about_ca_system_score_gemma":0.0002825465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007759432,"about_ca_topic_score_gemma":0.001015584,"domain_scores_codex":[0.9978092,0.0008247893,0.0002587431,0.0005369643,0.0004587965,0.0001115513],"domain_scores_gemma":[0.9893351,0.003087419,0.002920827,0.001977491,0.002092241,0.0005868702],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002533244,0.0002780476,0.9801191,0.0000490206,0.0002597841,0.00005913069,0.0008073149,0.001036923,0.004844926,0.00006193688,0.0001817613,0.009768832],"study_design_scores_gemma":[0.0000807705,0.003068333,0.9877127,0.000009724286,0.000119649,0.0006266974,0.0004498577,0.004414589,0.002881217,0.0000843067,0.0005187555,0.00003331377],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9983281,0.00008269778,0.001231728,0.000003448555,0.000003135908,0.00003453652,0.00008027675,0.000019384,0.0002167764],"genre_scores_gemma":[0.9988112,0.00001493899,0.0008967966,0.000004089177,0.000003282104,0.00002399438,0.0001752024,0.000007631083,0.00006284691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9943348,"threshold_uncertainty_score":0.02996111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06902881699138823,"score_gpt":0.3954005328278371,"score_spread":0.3263717158364489,"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."}}