[{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"5a0f08c1dca7b8527a40dba7c0c291daa7a2107a4d22baaa539991457d692033","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[],\"condition\":null,\"course\":{\"course_number\":552,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"prior\"},\"evidence\":\"POP HLTH/B M I 552\",\"id\":\"n0\",\"kind\":\"course\"}],\"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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"5a0f08c1dca7b8527a40dba7c0c291daa7a2107a4d22baaa539991457d692033","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"Introduction to the primary statistical tools used in epidemiology and health services research: logistic regression for binary outcomes, multiple linear regression for continuous outcomes, multinomial regression models for categorical outcomes, and Poisson and negative binomial regression models for count outcomes.\"}],\"text\":\"Foundational regression methods for various outcome types\"}],\"search_phrases\":[\"advanced regression population health\",\"mixed linear models GEE BMI\",\"propensity weights longitudinal data BMI 651\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Extension of regression analysis to observational data with unequal variance, unequal sampling and propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Advanced regression analysis for complex observational data\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"using different variance structures, mixed linear models, generalized linear models and GEE\"}],\"text\":\"Application of mixed linear models, GLMs, and GEE\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Matrix notation will be introduced and underlying mathematical and statistical principles will be explained\"}],\"text\":\"Mathematical and statistical principles using matrix notation\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"title\",\"quote\":\"ADVANCED REGRESSION METHODS FOR POPULATION HEALTH\"},{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Extension of regression analysis to observational data with unequal variance, unequal sampling and propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Advanced regression methods for population health, extending analysis to complex observational data structures using mixed models and GEE.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Propensity weights, clustering, and longitudinal measurements\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"mixed linear models, generalized linear models and GEE\"}],\"text\":\"Mixed linear models, generalized linear models, and GEE\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Matrix notation will be introduced and underlying mathematical and statistical principles will be explained\"}],\"text\":\"Matrix notation and statistical principles\"}]}","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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"5a0f08c1dca7b8527a40dba7c0c291daa7a2107a4d22baaa539991457d692033","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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"8a86861823467737d83b13b1b664e517bf3c82abdeec31308c338766d84f4c35","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[],\"condition\":null,\"course\":{\"course_number\":552,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"prior\"},\"evidence\":\"POP HLTH/B M I 552\",\"id\":\"n0\",\"kind\":\"course\"}],\"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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"8a86861823467737d83b13b1b664e517bf3c82abdeec31308c338766d84f4c35","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"Introduction to the primary statistical tools used in epidemiology and health services research: logistic regression for binary outcomes, multiple linear regression for continuous outcomes, multinomial regression models for categorical outcomes, and Poisson and negative binomial regression models for count outcomes.\"}],\"text\":\"Foundational regression methods for various outcome types\"}],\"search_phrases\":[\"advanced regression population health\",\"mixed linear models GEE BMI\",\"propensity weights longitudinal data BMI 651\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Extension of regression analysis to observational data with unequal variance, unequal sampling and propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Advanced regression analysis for complex observational data\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"using different variance structures, mixed linear models, generalized linear models and GEE\"}],\"text\":\"Application of mixed linear models, GLMs, and GEE\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Matrix notation will be introduced and underlying mathematical and statistical principles will be explained\"}],\"text\":\"Mathematical and statistical principles using matrix notation\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"title\",\"quote\":\"ADVANCED REGRESSION METHODS FOR POPULATION HEALTH\"},{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Extension of regression analysis to observational data with unequal variance, unequal sampling and propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Advanced regression methods for population health, extending analysis to complex observational data structures using mixed models and GEE.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Propensity weights, clustering, and longitudinal measurements\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"mixed linear models, generalized linear models and GEE\"}],\"text\":\"Mixed linear models, generalized linear models, and GEE\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Matrix notation will be introduced and underlying mathematical and statistical principles will be explained\"}],\"text\":\"Matrix notation and statistical principles\"}]}","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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"8a86861823467737d83b13b1b664e517bf3c82abdeec31308c338766d84f4c35","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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"77b8add98aa6bef81604d854565b04fabf905f1d66fa8335bead890c92ae555d","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[],\"condition\":null,\"course\":{\"course_number\":552,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"prior\"},\"evidence\":\"POP HLTH/B M I 552\",\"id\":\"n0\",\"kind\":\"course\"}],\"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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"77b8add98aa6bef81604d854565b04fabf905f1d66fa8335bead890c92ae555d","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"Introduction to the primary statistical tools used in epidemiology and health services research: logistic regression for binary outcomes, multiple linear regression for continuous outcomes, multinomial regression models for categorical outcomes, and Poisson and negative binomial regression models for count outcomes.\"}],\"text\":\"Foundational regression methods for various outcome types\"}],\"search_phrases\":[\"advanced regression population health\",\"mixed linear models GEE BMI\",\"propensity weights longitudinal data BMI 651\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Extension of regression analysis to observational data with unequal variance, unequal sampling and propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Advanced regression analysis for complex observational data\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"using different variance structures, mixed linear models, generalized linear models and GEE\"}],\"text\":\"Application of mixed linear models, GLMs, and GEE\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Matrix notation will be introduced and underlying mathematical and statistical principles will be explained\"}],\"text\":\"Mathematical and statistical principles using matrix notation\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"title\",\"quote\":\"ADVANCED REGRESSION METHODS FOR POPULATION HEALTH\"},{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Extension of regression analysis to observational data with unequal variance, unequal sampling and propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Advanced regression methods for population health, extending analysis to complex observational data structures using mixed models and GEE.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"propensity weights, clusters and longitudinal measurements\"}],\"text\":\"Propensity weights, clustering, and longitudinal measurements\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"mixed linear models, generalized linear models and GEE\"}],\"text\":\"Mixed linear models, generalized linear models, and GEE\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 651\",\"field\":\"description\",\"quote\":\"Matrix notation will be introduced and underlying mathematical and statistical principles will be explained\"}],\"text\":\"Matrix notation and statistical principles\"}]}","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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"77b8add98aa6bef81604d854565b04fabf905f1d66fa8335bead890c92ae555d","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_a08aa529ddd844ebf5d43f6b","course_id":"BMI/POPHLTH 651","catalog_version_id":"d92ba542fa2453099bbeb9189d33573cfcbf53bcfe648d9bf514b2e785b067e7","record_version_id":"3f52d72978af96f4a2a2bd7ae97b099d1ee609fea25d646e5beee3e5aedfc4cd","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"77b8add98aa6bef81604d854565b04fabf905f1d66fa8335bead890c92ae555d","section":"student_summary","status":"valid","value_json":"{\"context_hash\":\"604f1ae0349860f81489400b4547b307a05b609f90e8b0b9a3725b8a6955167c\",\"course_id\":\"BMI/POPHLTH 651\",\"current_instructors\":[],\"difficulty_workload\":[],\"errors\":[],\"historical_context\":[],\"message\":\"No course-specific reviews available\",\"offered\":false,\"profile_hash\":\"5cb4dabf887cdbcd8c00d5a1312e10828b95c63f30bc3ea76aea199565390d02\",\"quick_take\":[{\"citations\":[{\"course_id\":\"BMI/POPHLTH 651\",\"run_id\":\"20260907T155543-ce3781c4\",\"source_record\":{\"entity_id\":\"dfcf0369-b486-3bb1-9799-7e69c0749b59\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1222\",\"type\":\"grade\"},{\"course_id\":\"BMI/POPHLTH 651\",\"run_id\":\"20260907T155543-ce3781c4\",\"source_record\":{\"entity_id\":\"dfcf0369-b486-3bb1-9799-7e69c0749b59\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1252\",\"type\":\"grade\"},{\"course_id\":\"BMI/POPHLTH 651\",\"run_id\":\"20260907T155543-ce3781c4\",\"source_record\":{\"entity_id\":\"dfcf0369-b486-3bb1-9799-7e69c0749b59\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1262\",\"type\":\"grade\"}],\"text\":\"Recent recorded grades — Fall 2021: 3.35 GPA, 50.0% A/AB (n=10 letter grades); Fall 2024: 3.65 GPA, 90.0% A/AB (n=10 letter grades); Fall 2025: 3.66 GPA, 87.5% A/AB (n=16 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}]