[{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"2853e7588ec1829b6947dc4201ae2c14dabaf2665f26ecee7a5dfd1c1d385c6f","section":"requirements","status":"invalid","value_json":null,"candidate_json":"{\"nodes\":[{\"children\":[],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing\",\"id\":\"n0\",\"kind\":\"condition\"}],\"notes\":[],\"root\":\"n0\",\"status\":\"parsed\"}","error":"Non-course conditions must preserve verbatim source text","model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":false},{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"2853e7588ec1829b6947dc4201ae2c14dabaf2665f26ecee7a5dfd1c1d385c6f","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Review of statistical convergence modes, M-estimation, and basics of Hilbert space.\"}],\"text\":\"Statistical convergence, M-estimation, and Hilbert space fundamentals\"}],\"search_phrases\":[\"semiparametric models\",\"nuisance tangent space\",\"efficient influence function\",\"machine learning estimation\",\"causal inference\",\"missing data analysis\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"derive the nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Deriving nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"estimate nuisance functions using machine learning methods, and their implementations in R and/or Python\"}],\"text\":\"Estimating nuisance functions with machine learning in R/Python\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of a variety of semiparametric models in missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applying semiparametric models to causal inference and data science\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"title\",\"quote\":\"SEMIPARAMETRIC METHODS IN DATA SCIENCE\"},{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of how to derive the nuisance tangent space, its complement, and the corresponding efficient influence function, from the geometric perspective of semiparametric models\"}],\"text\":\"Covers semiparametric methods, including deriving efficient influence functions and applying machine learning to causal inference and missing data.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"geometric perspective of semiparametric models\"}],\"text\":\"Geometric perspective of semiparametric models\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applications in causal inference, missing data, and transfer learning\"}]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":false},{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"2853e7588ec1829b6947dc4201ae2c14dabaf2665f26ecee7a5dfd1c1d385c6f","section":"student_experience","status":"insufficient_evidence","value_json":"{\"status\":\"insufficient_evidence\",\"themes\":[]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":false},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"914a7bc92633b3ed86ac748bf949f449fc768e707fdb7e315e2cf7a1afb07164","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[],\"condition\":\"Graduate/professional standing\",\"course\":null,\"evidence\":\"Graduate/professional standing\",\"id\":\"n0\",\"kind\":\"condition\"}],\"notes\":[],\"root\":\"n0\",\"status\":\"parsed\"}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":true},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"914a7bc92633b3ed86ac748bf949f449fc768e707fdb7e315e2cf7a1afb07164","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Review of statistical convergence modes, M-estimation, and basics of Hilbert space.\"}],\"text\":\"Statistical convergence, M-estimation, and Hilbert space fundamentals\"}],\"search_phrases\":[\"semiparametric models\",\"nuisance tangent space\",\"efficient influence function\",\"machine learning estimation\",\"causal inference\",\"missing data analysis\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"derive the nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Deriving nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"estimate nuisance functions using machine learning methods, and their implementations in R and/or Python\"}],\"text\":\"Estimating nuisance functions with machine learning in R/Python\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of a variety of semiparametric models in missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applying semiparametric models to causal inference and data science\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"title\",\"quote\":\"SEMIPARAMETRIC METHODS IN DATA SCIENCE\"},{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of how to derive the nuisance tangent space, its complement, and the corresponding efficient influence function, from the geometric perspective of semiparametric models\"}],\"text\":\"Covers semiparametric methods, including deriving efficient influence functions and applying machine learning to causal inference and missing data.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"geometric perspective of semiparametric models\"}],\"text\":\"Geometric perspective of semiparametric models\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applications in causal inference, missing data, and transfer learning\"}]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":true},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"914a7bc92633b3ed86ac748bf949f449fc768e707fdb7e315e2cf7a1afb07164","section":"student_experience","status":"insufficient_evidence","value_json":"{\"status\":\"insufficient_evidence\",\"themes\":[]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":true},{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-789789da373eecc1ff75f626","output_id":"1f316849a91a0e0fa981535ab2dac8ba2a014cb196d859d2887c6e99b07a68e8","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[],\"condition\":\"Graduate/professional standing\",\"course\":null,\"evidence\":\"Graduate/professional standing\",\"id\":\"n0\",\"kind\":\"condition\"}],\"notes\":[],\"root\":\"n0\",\"status\":\"parsed\"}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":false},{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-789789da373eecc1ff75f626","output_id":"1f316849a91a0e0fa981535ab2dac8ba2a014cb196d859d2887c6e99b07a68e8","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Review of statistical convergence modes, M-estimation, and basics of Hilbert space.\"}],\"text\":\"Statistical convergence, M-estimation, and Hilbert space fundamentals\"}],\"search_phrases\":[\"semiparametric models\",\"nuisance tangent space\",\"efficient influence function\",\"machine learning estimation\",\"causal inference\",\"missing data analysis\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"derive the nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Deriving nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"estimate nuisance functions using machine learning methods, and their implementations in R and/or Python\"}],\"text\":\"Estimating nuisance functions with machine learning in R/Python\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of a variety of semiparametric models in missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applying semiparametric models to causal inference and data science\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"title\",\"quote\":\"SEMIPARAMETRIC METHODS IN DATA SCIENCE\"},{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of how to derive the nuisance tangent space, its complement, and the corresponding efficient influence function, from the geometric perspective of semiparametric models\"}],\"text\":\"Covers semiparametric methods, including deriving efficient influence functions and applying machine learning to causal inference and missing data.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"geometric perspective of semiparametric models\"}],\"text\":\"Geometric perspective of semiparametric models\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applications in causal inference, missing data, and transfer learning\"}]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":false},{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-789789da373eecc1ff75f626","output_id":"1f316849a91a0e0fa981535ab2dac8ba2a014cb196d859d2887c6e99b07a68e8","section":"student_experience","status":"insufficient_evidence","value_json":"{\"status\":\"insufficient_evidence\",\"themes\":[]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":false},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"ab1573131b779da98e62b7a8e3712ba1381bf541e02b6cee225cd61342b74323","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[],\"condition\":\"Graduate/professional standing\",\"course\":null,\"evidence\":\"Graduate/professional standing\",\"id\":\"n0\",\"kind\":\"condition\"}],\"notes\":[],\"root\":\"n0\",\"status\":\"parsed\"}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":true},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"ab1573131b779da98e62b7a8e3712ba1381bf541e02b6cee225cd61342b74323","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Review of statistical convergence modes, M-estimation, and basics of Hilbert space.\"}],\"text\":\"Statistical convergence, M-estimation, and Hilbert space fundamentals\"}],\"search_phrases\":[\"semiparametric models\",\"nuisance tangent space\",\"efficient influence function\",\"machine learning estimation\",\"causal inference\",\"missing data analysis\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"derive the nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Deriving nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"estimate nuisance functions using machine learning methods, and their implementations in R and/or Python\"}],\"text\":\"Estimating nuisance functions with machine learning in R/Python\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of a variety of semiparametric models in missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applying semiparametric models to causal inference and data science\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"title\",\"quote\":\"SEMIPARAMETRIC METHODS IN DATA SCIENCE\"},{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"Introduction of how to derive the nuisance tangent space, its complement, and the corresponding efficient influence function, from the geometric perspective of semiparametric models\"}],\"text\":\"Covers semiparametric methods, including deriving efficient influence functions and applying machine learning to causal inference and missing data.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"geometric perspective of semiparametric models\"}],\"text\":\"Geometric perspective of semiparametric models\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"nuisance tangent space, its complement, and the corresponding efficient influence function\"}],\"text\":\"Nuisance tangent spaces and efficient influence functions\"},{\"evidence\":[{\"course_id\":\"BMI/STAT 828\",\"field\":\"description\",\"quote\":\"missing data analysis, causal inference, dimension reduction, precision medicine, semi-supervised learning, transfer learning and domain adaptation\"}],\"text\":\"Applications in causal inference, missing data, and transfer learning\"}]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":true},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"ab1573131b779da98e62b7a8e3712ba1381bf541e02b6cee225cd61342b74323","section":"student_experience","status":"insufficient_evidence","value_json":"{\"status\":\"insufficient_evidence\",\"themes\":[]}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":true},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_050cac70b4ff0bdca35ecad4","course_id":"BMI/STAT 828","catalog_version_id":"0051dd7a0230434a65c15b1f6c0607c02004cd33deafd77d2abd951727e3a68f","record_version_id":"4563d2e51bc429bc259c7922526a986d35d84373221aae31241118fd05141c81","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"ab1573131b779da98e62b7a8e3712ba1381bf541e02b6cee225cd61342b74323","section":"student_summary","status":"valid","value_json":"{\"context_hash\":\"4bb0268ab92f4010bfa1193797a9779ac96f186217228595de8d86dda7bab5a5\",\"course_id\":\"BMI/STAT 828\",\"current_instructors\":[],\"difficulty_workload\":[],\"errors\":[],\"historical_context\":[],\"message\":\"No course-specific reviews available\",\"offered\":false,\"profile_hash\":\"5cb4dabf887cdbcd8c00d5a1312e10828b95c63f30bc3ea76aea199565390d02\",\"quick_take\":[{\"citations\":[{\"course_id\":\"BMI/STAT 828\",\"run_id\":\"20260907T155543-ce3781c4\",\"source_record\":{\"entity_id\":\"bccdba17-5a9a-359e-9e73-185041f3950e\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1252\",\"type\":\"grade\"}],\"text\":\"Recent recorded grades — Fall 2024: 4.00 GPA, 100.0% A/AB (n=14 letter grades).\"}],\"student_experience\":[],\"task_hash\":\"74fb0997943e888960bbc9e47db8c4fd12e4292d55c20509d8d89db6a9910f68\",\"teaching_history\":[],\"term_id\":\"1272\",\"term_name\":\"2026 Fall\",\"version\":2}","candidate_json":null,"error":null,"model":"nvidia/Qwen3.6-35B-A3B-NVFP4","model_revision":"1355db6a052410cfd62085d94b58866fd0f2c3c5","selected_for_release":true}]