[{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-49752a259f17fab0f49665b3","output_id":"fd1beb6baa84d3ff06ab0c9b06137354ae28cdef6bf1746a4b28fa1d49b036f0","section":"requirements","status":"needs_review","value_json":"{\"nodes\":[{\"children\":[\"req_541\",\"req_551\"],\"condition\":null,\"course\":null,\"evidence\":\"STAT/B M I 541orPOP HLTH/B M I 551\",\"id\":\"root_any\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":541,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"STAT\"],\"timing\":\"unspecified\"},\"evidence\":\"STAT/B M I 541\",\"id\":\"req_541\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":551,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"unspecified\"},\"evidence\":\"POP HLTH/B M I 551\",\"id\":\"req_551\",\"kind\":\"course\"}],\"notes\":[\"Normalized 'POP HLTH/B M I 551' to the linked course reference BMI/POPHLTH 551.\"],\"root\":\"root_any\",\"status\":\"parsed\"}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":true},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-49752a259f17fab0f49665b3","output_id":"fd1beb6baa84d3ff06ab0c9b06137354ae28cdef6bf1746a4b28fa1d49b036f0","section":"search_profile","status":"valid","value_json":"{\"activity_tags\":[{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"},{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":0,\"quote\":\"State the assumptions underlying linear, logistic, multinomial and Poisson regression models, recognize and address violations of those assumptions, and estimate and interpret regression models to answer epidemiologic and public health research questions.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"label\":\"data-analysis\"}],\"assumed_background\":[],\"search_phrases\":[\"Regression methods for population health\",\"Logistic regression for binary outcomes\",\"Poisson regression for count outcomes\",\"Statistical tools in epidemiology\",\"Multinomial regression models\"],\"skills_taught\":[{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Estimation and interpretation of linear, logistic, multinomial, and Poisson regression models.\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":1,\"quote\":\"Critique uses of linear, logistic, multinomial and Poisson regression models in the epidemiologic and public health literature.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Critiquing the application of regression models in epidemiologic and public health literature.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"title\",\"quote\":\"REGRESSION METHODS FOR POPULATION HEALTH\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"},{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"This course introduces primary statistical tools for epidemiology and health services research, covering logistic, linear, multinomial, and Poisson regression models for various outcome types.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Logistic, linear, multinomial, and Poisson/negative binomial regression models.\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":0,\"quote\":\"State the assumptions underlying linear, logistic, multinomial and Poisson regression models, recognize and address violations of those assumptions, and estimate and interpret regression models to answer epidemiologic and public health research questions.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Assumptions, violations, estimation, and interpretation of regression models in epidemiologic research.\"}]}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":true},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-49752a259f17fab0f49665b3","output_id":"fd1beb6baa84d3ff06ab0c9b06137354ae28cdef6bf1746a4b28fa1d49b036f0","section":"student_experience","status":"insufficient_evidence","value_json":"{\"status\":\"insufficient_evidence\",\"themes\":[]}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":true},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-49752a259f17fab0f49665b3","output_id":"fd1beb6baa84d3ff06ab0c9b06137354ae28cdef6bf1746a4b28fa1d49b036f0","section":"student_summary","status":"valid","value_json":"{\"context_hash\":\"74462ed7ecc376b81bc9b96cc38323671a6646a68c18d07c02d31175c7a94085\",\"course_id\":\"BMI/POPHLTH 552\",\"current_instructors\":[{\"instructor_uid\":\"instructor_e5d5c185a04a2235ae0a87f8\",\"message\":\"No course-specific reviews available\",\"name\":\"Mary Baumann\",\"review_status\":\"no_course_reviews\",\"rmp_instructor_id\":null,\"summary\":[]}],\"difficulty_workload\":[],\"errors\":[],\"historical_context\":[],\"message\":\"No course-specific reviews available\",\"offered\":true,\"profile_hash\":\"3f5110430805ccdd533c0c072df62d68a8a5f5441c4530bbdb15d419a199a09c\",\"quick_take\":[{\"citations\":[{\"course_id\":\"BMI/POPHLTH 552\",\"run_id\":\"20261014T203208-0851c9a1\",\"source_record\":{\"entity_id\":\"2a7b75ad-7acf-33e3-a2bd-4fe1da87982f\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1244\",\"type\":\"grade\"},{\"course_id\":\"BMI/POPHLTH 552\",\"run_id\":\"20261014T203208-0851c9a1\",\"source_record\":{\"entity_id\":\"2a7b75ad-7acf-33e3-a2bd-4fe1da87982f\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1254\",\"type\":\"grade\"},{\"course_id\":\"BMI/POPHLTH 552\",\"run_id\":\"20261014T203208-0851c9a1\",\"source_record\":{\"entity_id\":\"2a7b75ad-7acf-33e3-a2bd-4fe1da87982f\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1264\",\"type\":\"grade\"}],\"text\":\"Recent recorded grades — Spring 2024: 3.58 GPA, 69.2% A/AB (n=13 letter grades); Spring 2025: 3.74 GPA, 88.2% A/AB (n=17 letter grades); Spring 2026: 3.47 GPA, 73.7% A/AB (n=19 letter grades).\"}],\"student_experience\":[],\"task_hash\":\"9dea82ef7f2113a5605c1c6030c4f9b19967eb742cc93a78268fb92357d29f5c\",\"teaching_history\":[],\"term_id\":\"1274\",\"term_name\":\"2027 Sprng\",\"version\":3}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":true},{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"73b29f08204874f6ad7761ad40d86f0d8c18d25be620a3849df4302e053d0abb","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[\"n1\",\"n2\"],\"condition\":null,\"course\":null,\"evidence\":\"STAT/B M I 541orPOP HLTH/B M I 551\",\"id\":\"n0\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":541,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/B M I 541\",\"id\":\"n1\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":551,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"prior\"},\"evidence\":\"POP HLTH/B M I 551\",\"id\":\"n2\",\"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_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"73b29f08204874f6ad7761ad40d86f0d8c18d25be620a3849df4302e053d0abb","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 541\",\"field\":\"description\",\"quote\":\"Topics include: descriptive statistics, hypothesis testing, estimation, confidence intervals, t-tests, chi-squared tests, analysis of variance, linear regression, correlation, nonparametric tests, survival analysis and odds ratio.\"},{\"course_id\":\"BMI/POPHLTH 551\",\"field\":\"description\",\"quote\":\"Topics include descriptive statistics, elementary probability, probability distributions, one- and two-sample normal inference (point estimation, hypothesis testing, confidence intervals), power and sample size calculations, one- and two-sample binomial inference, underlying assumptions and diagnostic work.\"}],\"text\":\"Foundational biostatistics including hypothesis testing, confidence intervals, and basic regression.\"}],\"search_phrases\":[\"logistic regression epidemiology\",\"Poisson regression health services\",\"multinomial regression models\",\"biostatistics for population health\",\"BMI 552 regression methods\"],\"skills_taught\":[{\"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\":\"Applying logistic, linear, multinomial, Poisson, and negative binomial regression models.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"title\",\"quote\":\"REGRESSION METHODS FOR POPULATION HEALTH\"},{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"Introduction to the primary statistical tools used in epidemiology and health services research\"}],\"text\":\"Teaches regression methods for population health, including logistic, linear, multinomial, Poisson, and negative binomial models.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"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\":\"Regression models for binary, continuous, categorical, and count outcomes.\"}]}","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_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"73b29f08204874f6ad7761ad40d86f0d8c18d25be620a3849df4302e053d0abb","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_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"2a3631b63246dcb9e4db1dadbcd9f6e64c0055449e849397eb1246b1e82ba1b1","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[\"n1\",\"n2\"],\"condition\":null,\"course\":null,\"evidence\":\"STAT/B M I 541orPOP HLTH/B M I 551\",\"id\":\"n0\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":541,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/B M I 541\",\"id\":\"n1\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":551,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"prior\"},\"evidence\":\"POP HLTH/B M I 551\",\"id\":\"n2\",\"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":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"2a3631b63246dcb9e4db1dadbcd9f6e64c0055449e849397eb1246b1e82ba1b1","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 541\",\"field\":\"description\",\"quote\":\"Topics include: descriptive statistics, hypothesis testing, estimation, confidence intervals, t-tests, chi-squared tests, analysis of variance, linear regression, correlation, nonparametric tests, survival analysis and odds ratio.\"},{\"course_id\":\"BMI/POPHLTH 551\",\"field\":\"description\",\"quote\":\"Topics include descriptive statistics, elementary probability, probability distributions, one- and two-sample normal inference (point estimation, hypothesis testing, confidence intervals), power and sample size calculations, one- and two-sample binomial inference, underlying assumptions and diagnostic work.\"}],\"text\":\"Foundational biostatistics including hypothesis testing, confidence intervals, and basic regression.\"}],\"search_phrases\":[\"logistic regression epidemiology\",\"Poisson regression health services\",\"multinomial regression models\",\"biostatistics for population health\",\"BMI 552 regression methods\"],\"skills_taught\":[{\"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\":\"Applying logistic, linear, multinomial, Poisson, and negative binomial regression models.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"title\",\"quote\":\"REGRESSION METHODS FOR POPULATION HEALTH\"},{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"Introduction to the primary statistical tools used in epidemiology and health services research\"}],\"text\":\"Teaches regression methods for population health, including logistic, linear, multinomial, Poisson, and negative binomial models.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"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\":\"Regression models for binary, continuous, categorical, and count outcomes.\"}]}","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_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"2a3631b63246dcb9e4db1dadbcd9f6e64c0055449e849397eb1246b1e82ba1b1","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":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-6556a505c10f448d98d02466","output_id":"7261b31bbbbbceb69cbd09e5d4a6511f2771f1b89a9bac723809506a5d17f150","section":"requirements","status":"invalid","value_json":null,"candidate_json":"{\"nodes\":[{\"children\":[\"req_541\",\"req_551\"],\"condition\":null,\"course\":null,\"evidence\":\"STAT/B M I 541orPOP HLTH/B M I 551\",\"id\":\"root_any\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":541,\"minimum_grade\":null,\"subjects\":[\"STAT\",\"BMI\"],\"timing\":\"prior\"},\"evidence\":\"STAT/B M I 541\",\"id\":\"req_541\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":551,\"minimum_grade\":null,\"subjects\":[\"POP HLTH\",\"BMI\"],\"timing\":\"prior\"},\"evidence\":\"POP HLTH/B M I 551\",\"id\":\"req_551\",\"kind\":\"course\"}],\"notes\":[],\"root\":\"root_any\",\"status\":\"parsed\"}","error":"Node req_551: course {'course_number': 551, 'minimum_grade': None, 'subjects': ['POP HLTH', 'BMI'], 'timing': 'prior'} is absent from the source links (linked_courses). Standing, declared programs, and subject credit counts are condition nodes, not courses. Never invent course 0. For a source reference absent from linked_courses, use kind=condition, course=null, condition=<verbatim source clause>, children=[], and needs_review with an explanatory note. Allowed course references: [{'course_number': 541, 'subjects': ['BMI', 'STAT']}, {'course_number': 551, 'subjects': ['BMI', 'POPHLTH']}].","model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":false},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-6556a505c10f448d98d02466","output_id":"7261b31bbbbbceb69cbd09e5d4a6511f2771f1b89a9bac723809506a5d17f150","section":"search_profile","status":"valid","value_json":"{\"activity_tags\":[{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"},{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":0,\"quote\":\"State the assumptions underlying linear, logistic, multinomial and Poisson regression models, recognize and address violations of those assumptions, and estimate and interpret regression models to answer epidemiologic and public health research questions.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"label\":\"data-analysis\"}],\"assumed_background\":[],\"search_phrases\":[\"Regression methods for population health\",\"Logistic regression for binary outcomes\",\"Poisson regression for count outcomes\",\"Statistical tools in epidemiology\",\"Multinomial regression models\"],\"skills_taught\":[{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Estimation and interpretation of linear, logistic, multinomial, and Poisson regression models.\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":1,\"quote\":\"Critique uses of linear, logistic, multinomial and Poisson regression models in the epidemiologic and public health literature.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Critiquing the application of regression models in epidemiologic and public health literature.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"title\",\"quote\":\"REGRESSION METHODS FOR POPULATION HEALTH\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"},{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"This course introduces primary statistical tools for epidemiology and health services research, covering logistic, linear, multinomial, and Poisson regression models for various outcome types.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Logistic, linear, multinomial, and Poisson/negative binomial regression models.\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":0,\"quote\":\"State the assumptions underlying linear, logistic, multinomial and Poisson regression models, recognize and address violations of those assumptions, and estimate and interpret regression models to answer epidemiologic and public health research questions.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Assumptions, violations, estimation, and interpretation of regression models in epidemiologic research.\"}]}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":false},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-6556a505c10f448d98d02466","output_id":"7261b31bbbbbceb69cbd09e5d4a6511f2771f1b89a9bac723809506a5d17f150","section":"student_experience","status":"insufficient_evidence","value_json":"{\"status\":\"insufficient_evidence\",\"themes\":[]}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":false},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-79348710a077dbb34341f483","output_id":"191ed1a73240a43d5d2b84a8425f95f8232f19cd4129bc29b9b94828a2a66eae","section":"requirements","status":"needs_review","value_json":"{\"nodes\":[{\"children\":[\"req_541\",\"req_551\"],\"condition\":null,\"course\":null,\"evidence\":\"STAT/B M I 541orPOP HLTH/B M I 551\",\"id\":\"root_any\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":541,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"STAT\"],\"timing\":\"unspecified\"},\"evidence\":\"STAT/B M I 541\",\"id\":\"req_541\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":551,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"unspecified\"},\"evidence\":\"POP HLTH/B M I 551\",\"id\":\"req_551\",\"kind\":\"course\"}],\"notes\":[\"Normalized 'POP HLTH/B M I 551' to the linked course reference BMI/POPHLTH 551.\"],\"root\":\"root_any\",\"status\":\"parsed\"}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":false},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-79348710a077dbb34341f483","output_id":"191ed1a73240a43d5d2b84a8425f95f8232f19cd4129bc29b9b94828a2a66eae","section":"search_profile","status":"valid","value_json":"{\"activity_tags\":[{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"},{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":0,\"quote\":\"State the assumptions underlying linear, logistic, multinomial and Poisson regression models, recognize and address violations of those assumptions, and estimate and interpret regression models to answer epidemiologic and public health research questions.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"label\":\"data-analysis\"}],\"assumed_background\":[],\"search_phrases\":[\"Regression methods for population health\",\"Logistic regression for binary outcomes\",\"Poisson regression for count outcomes\",\"Statistical tools in epidemiology\",\"Multinomial regression models\"],\"skills_taught\":[{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Estimation and interpretation of linear, logistic, multinomial, and Poisson regression models.\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":1,\"quote\":\"Critique uses of linear, logistic, multinomial and Poisson regression models in the epidemiologic and public health literature.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Critiquing the application of regression models in epidemiologic and public health literature.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"title\",\"quote\":\"REGRESSION METHODS FOR POPULATION HEALTH\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"},{\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"This course introduces primary statistical tools for epidemiology and health services research, covering logistic, linear, multinomial, and Poisson regression models for various outcome types.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"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.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Logistic, linear, multinomial, and Poisson/negative binomial regression models.\"},{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"official_learning_outcomes\",\"outcome_index\":0,\"quote\":\"State the assumptions underlying linear, logistic, multinomial and Poisson regression models, recognize and address violations of those assumptions, and estimate and interpret regression models to answer epidemiologic and public health research questions.\",\"source_url\":\"https://guide.wisc.edu/courses/b_m_i/\"}],\"text\":\"Assumptions, violations, estimation, and interpretation of regression models in epidemiologic research.\"}]}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":false},{"run_id":"20261014T203208-0851c9a1","observed_at":"2026-10-14 17:50:09.728220+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"40fe729ebf432096116c610509fa304410ceea77a190505ac69edc2e094c36d5","record_version_id":"77067ac8d1b8628b076415f753d4b698a2424c164fc85e1f477209212655f8e5","job_id":"enrich-79348710a077dbb34341f483","output_id":"191ed1a73240a43d5d2b84a8425f95f8232f19cd4129bc29b9b94828a2a66eae","section":"student_experience","status":"insufficient_evidence","value_json":"{\"status\":\"insufficient_evidence\",\"themes\":[]}","candidate_json":null,"error":null,"model":"Qwen/Qwen3.8-27B","model_revision":"1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0","selected_for_release":false},{"run_id":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"fe666577dbaf5939729ca942567c0784e9e310b0ef31b6fb0dbf97199d3e2f26","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[\"n1\",\"n2\"],\"condition\":null,\"course\":null,\"evidence\":\"STAT/B M I 541orPOP HLTH/B M I 551\",\"id\":\"n0\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":541,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/B M I 541\",\"id\":\"n1\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":551,\"minimum_grade\":null,\"subjects\":[\"BMI\",\"POPHLTH\"],\"timing\":\"prior\"},\"evidence\":\"POP HLTH/B M I 551\",\"id\":\"n2\",\"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":"20260907T155543-ce3781c4","observed_at":"2026-09-07 15:55:43.033547+00:00","course_uid":"course_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"fe666577dbaf5939729ca942567c0784e9e310b0ef31b6fb0dbf97199d3e2f26","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"BMI/STAT 541\",\"field\":\"description\",\"quote\":\"Topics include: descriptive statistics, hypothesis testing, estimation, confidence intervals, t-tests, chi-squared tests, analysis of variance, linear regression, correlation, nonparametric tests, survival analysis and odds ratio.\"},{\"course_id\":\"BMI/POPHLTH 551\",\"field\":\"description\",\"quote\":\"Topics include descriptive statistics, elementary probability, probability distributions, one- and two-sample normal inference (point estimation, hypothesis testing, confidence intervals), power and sample size calculations, one- and two-sample binomial inference, underlying assumptions and diagnostic work.\"}],\"text\":\"Foundational biostatistics including hypothesis testing, confidence intervals, and basic regression.\"}],\"search_phrases\":[\"logistic regression epidemiology\",\"Poisson regression health services\",\"multinomial regression models\",\"biostatistics for population health\",\"BMI 552 regression methods\"],\"skills_taught\":[{\"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\":\"Applying logistic, linear, multinomial, Poisson, and negative binomial regression models.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"title\",\"quote\":\"REGRESSION METHODS FOR POPULATION HEALTH\"},{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"Introduction to the primary statistical tools used in epidemiology and health services research\"}],\"text\":\"Teaches regression methods for population health, including logistic, linear, multinomial, Poisson, and negative binomial models.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"BMI/POPHLTH 552\",\"field\":\"description\",\"quote\":\"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\":\"Regression models for binary, continuous, categorical, and count outcomes.\"}]}","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_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"fe666577dbaf5939729ca942567c0784e9e310b0ef31b6fb0dbf97199d3e2f26","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_bc8b66a9d302c5aed1303634","course_id":"BMI/POPHLTH 552","catalog_version_id":"22ae8b4bf4b2feea97c1fee1e49ed2850024a96a7b11a673e49f64a7d56f3477","record_version_id":"8e3c0740c70b87d658c0426789e9ae7a8cb6cbce1912eeba303d1273649d1444","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"fe666577dbaf5939729ca942567c0784e9e310b0ef31b6fb0dbf97199d3e2f26","section":"student_summary","status":"valid","value_json":"{\"context_hash\":\"3b7fa56e02070f7abb6803c955f40465d17b0d6c32be17551454266c802c47b4\",\"course_id\":\"BMI/POPHLTH 552\",\"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 552\",\"run_id\":\"20260907T155543-ce3781c4\",\"source_record\":{\"entity_id\":\"2a7b75ad-7acf-33e3-a2bd-4fe1da87982f\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1244\",\"type\":\"grade\"},{\"course_id\":\"BMI/POPHLTH 552\",\"run_id\":\"20260907T155543-ce3781c4\",\"source_record\":{\"entity_id\":\"2a7b75ad-7acf-33e3-a2bd-4fe1da87982f\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1254\",\"type\":\"grade\"},{\"course_id\":\"BMI/POPHLTH 552\",\"run_id\":\"20260907T155543-ce3781c4\",\"source_record\":{\"entity_id\":\"2a7b75ad-7acf-33e3-a2bd-4fe1da87982f\",\"file\":\"tables/observations.parquet\",\"kind\":\"grades\",\"source\":\"madgrades\"},\"table\":\"grades_latest\",\"term_id\":\"1264\",\"type\":\"grade\"}],\"text\":\"Recent recorded grades — Spring 2024: 3.58 GPA, 69.2% A/AB (n=13 letter grades); Spring 2025: 3.74 GPA, 88.2% A/AB (n=17 letter grades); Spring 2026: 3.47 GPA, 73.7% A/AB (n=19 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":false}]