[{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-2978ec7e9ac23a465ccaacbb","output_id":"9dc1eda9767301ea698c2dc4716bfd69ca60fb209d4b4b7d43da49cb5c296906","section":"requirements","status":"invalid","value_json":null,"candidate_json":"{\"nodes\":[{\"children\":[\"n1\",\"n2\",\"n3\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709) or declared in graduate Business Exchange program\",\"id\":\"n0\",\"kind\":\"any\"},{\"children\":[\"n4\",\"n5\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n1\",\"kind\":\"all\"},{\"children\":[\"n6\"],\"condition\":\"declared in graduate Business Exchange program\",\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n2\",\"kind\":\"condition\"},{\"children\":[\"n7\",\"n8\",\"n9\",\"n10\"],\"condition\":null,\"course\":null,\"evidence\":\"(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n3\",\"kind\":\"any\"},{\"children\":[],\"condition\":\"Graduate/professional standing\",\"course\":{\"course_number\":779,\"minimum_grade\":null,\"subjects\":[\"MARKETNG\"],\"timing\":\"unspecified\"},\"evidence\":\"Graduate/professional standing\",\"id\":\"n4\",\"kind\":\"condition\"},{\"children\":[],\"condition\":\"declared in graduate Business Exchange program\",\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n5\",\"kind\":\"condition\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":656,\"minimum_grade\":null,\"subjects\":[\"GENBUS\"],\"timing\":\"prior\"},\"evidence\":\"GEN BUS 656\",\"id\":\"n6\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":704,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 704\",\"id\":\"n7\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 709\",\"id\":\"n8\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":609,\"minimum_grade\":null,\"subjects\":[\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT 609\",\"id\":\"n9\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"MATH\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/MATH 709\",\"id\":\"n10\",\"kind\":\"course\"}],\"notes\":[\"The phrase 'Graduate/professional standing and ...' is parsed as an AND node (n1) requiring both standing and one of the listed courses.\",\"The phrase 'or declared in graduate Business Exchange program' is parsed as an alternative (n2) to the standing+course requirement.\",\"The course list '(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)' is parsed as an ANY node (n3) of the listed courses.\",\"Note: 'ECON 709' and 'STAT/MATH 709' are distinct course IDs in the linked_courses list.\"],\"root\":\"n0\",\"status\":\"parsed\"}","error":"Node n8: evidence 'ECON 709' must quote an exact source substring.","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-2978ec7e9ac23a465ccaacbb","output_id":"9dc1eda9767301ea698c2dc4716bfd69ca60fb209d4b4b7d43da49cb5c296906","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"STAT 609\",\"field\":\"description\",\"quote\":\"Review of probability, random variables and vectors and their distributions, moments and inequalities, generating functions, transformations of random variables, sampling and distribution theory, convergence concepts for sequences of random variables, laws of large numbers, central limit and other limit theorems.\"},{\"course_id\":\"GENBUS 656\",\"field\":\"description\",\"quote\":\"An introduction to predictive modeling for business applications beginning with some of the foundations. Leads to development of linear regression and classification models, and discussion of building models for prediction. Topics include selection, regularization, and the bias-variance tradeoff.\"},{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"Econometric methods, theory, and applications. Matrix algebra will be used. Topics include linear regression, least-squares estimation, inference, and hypothesis testing.\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"Probability distributions, statistical inference; multiple linear regression; introduction to econometric methods.\"}],\"text\":\"Probability theory, statistical inference, linear regression, and econometric methods.\"},{\"evidence\":[{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"}],\"text\":\"Calculus and linear algebra.\"}],\"search_phrases\":[\"Bayesian optimization marketing\",\"hierarchical modeling consumer choice\",\"Bayesian deep learning prediction\",\"marketing analytics graduate course\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"Consumer choice prediction, market analysis, and product development using Bayesian methods.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"title\",\"quote\":\"BAYESIAN MACHINE LEARNING FOR MARKETING\"},{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"This course teaches Bayesian statistical learning methods for marketing tasks like consumer choice prediction and product development.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"consumer choice prediction, market analysis, and product development\"}],\"text\":\"Consumer choice prediction, market analysis, and product development.\"}]}","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-2978ec7e9ac23a465ccaacbb","output_id":"9dc1eda9767301ea698c2dc4716bfd69ca60fb209d4b4b7d43da49cb5c296906","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":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"d815a7e45edceee8593d9902188794860793d6fcfe83675c92451050d74083e5","section":"requirements","status":"invalid","value_json":null,"candidate_json":"{\"nodes\":[{\"children\":[\"n1\",\"n2\",\"n3\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709) or declared in graduate Business Exchange program\",\"id\":\"n0\",\"kind\":\"any\"},{\"children\":[\"n4\",\"n5\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n1\",\"kind\":\"all\"},{\"children\":[\"n6\"],\"condition\":null,\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n2\",\"kind\":\"condition\"},{\"children\":[\"n7\",\"n8\",\"n9\",\"n10\"],\"condition\":null,\"course\":null,\"evidence\":\"(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n3\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":779,\"minimum_grade\":null,\"subjects\":[\"MARKETNG\"],\"timing\":\"unspecified\"},\"evidence\":\"Graduate/professional standing\",\"id\":\"n4\",\"kind\":\"condition\"},{\"children\":[],\"condition\":\"declared in graduate Business Exchange program\",\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n5\",\"kind\":\"condition\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":656,\"minimum_grade\":null,\"subjects\":[\"GENBUS\"],\"timing\":\"prior\"},\"evidence\":\"GEN BUS 656\",\"id\":\"n6\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":704,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 704\",\"id\":\"n7\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 709\",\"id\":\"n8\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":609,\"minimum_grade\":null,\"subjects\":[\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT 609\",\"id\":\"n9\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"MATH\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/MATH 709\",\"id\":\"n10\",\"kind\":\"course\"}],\"notes\":[\"The phrase 'Graduate/professional standing and ...' is parsed as an AND node (n1) requiring both standing and one of the listed courses.\",\"The phrase 'or declared in graduate Business Exchange program' is parsed as an alternative (n2) to the standing+course requirement.\",\"The course list '(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)' is parsed as an ANY node (n3) of the listed courses.\",\"Note: 'ECON 709' and 'STAT/MATH 709' are distinct course IDs in the linked_courses list.\"],\"root\":\"n0\",\"status\":\"parsed\"}","error":"Node n8: evidence 'ECON 709' must quote an exact source substring.","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"d815a7e45edceee8593d9902188794860793d6fcfe83675c92451050d74083e5","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"STAT 609\",\"field\":\"description\",\"quote\":\"Review of probability, random variables and vectors and their distributions, moments and inequalities, generating functions, transformations of random variables, sampling and distribution theory, convergence concepts for sequences of random variables, laws of large numbers, central limit and other limit theorems.\"},{\"course_id\":\"GENBUS 656\",\"field\":\"description\",\"quote\":\"An introduction to predictive modeling for business applications beginning with some of the foundations. Leads to development of linear regression and classification models, and discussion of building models for prediction. Topics include selection, regularization, and the bias-variance tradeoff.\"},{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"Econometric methods, theory, and applications. Matrix algebra will be used. Topics include linear regression, least-squares estimation, inference, and hypothesis testing.\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"Probability distributions, statistical inference; multiple linear regression; introduction to econometric methods.\"}],\"text\":\"Probability theory, statistical inference, linear regression, and econometric methods.\"},{\"evidence\":[{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"}],\"text\":\"Calculus and linear algebra.\"}],\"search_phrases\":[\"Bayesian optimization marketing\",\"hierarchical modeling consumer choice\",\"Bayesian deep learning prediction\",\"marketing analytics graduate course\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"Consumer choice prediction, market analysis, and product development using Bayesian methods.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"title\",\"quote\":\"BAYESIAN MACHINE LEARNING FOR MARKETING\"},{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"This course teaches Bayesian statistical learning methods for marketing tasks like consumer choice prediction and product development.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"consumer choice prediction, market analysis, and product development\"}],\"text\":\"Consumer choice prediction, market analysis, and product development.\"}]}","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-5291a20b802b9bbbe22b24cb","output_id":"d815a7e45edceee8593d9902188794860793d6fcfe83675c92451050d74083e5","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"c05371fbebc56d4ca94dea272c3019efee7d045d1c710650edefa25e3e9e6510","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[\"req_grad_standing_and_prereq\",\"req_exchange_program\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709) or declared in graduate Business Exchange program\",\"id\":\"req_root\",\"kind\":\"any\"},{\"children\":[\"req_grad_standing\",\"req_prereq_any\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"req_grad_standing_and_prereq\",\"kind\":\"all\"},{\"children\":[],\"condition\":\"declared in graduate Business Exchange program\",\"course\":null,\"evidence\":\"or declared in graduate Business Exchange program\",\"id\":\"req_exchange_program\",\"kind\":\"condition\"},{\"children\":[],\"condition\":\"Graduate/professional standing\",\"course\":null,\"evidence\":\"Graduate/professional standing\",\"id\":\"req_grad_standing\",\"kind\":\"condition\"},{\"children\":[\"req_genbus_656\",\"req_econ_704\",\"req_econ_709\",\"req_stat_609\",\"req_math_stat_709\"],\"condition\":null,\"course\":null,\"evidence\":\"(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"req_prereq_any\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":656,\"minimum_grade\":null,\"subjects\":[\"GENBUS\"],\"timing\":\"prior\"},\"evidence\":\"GEN BUS 656\",\"id\":\"req_genbus_656\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":704,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 704\",\"id\":\"req_econ_704\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"709\",\"id\":\"req_econ_709\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":609,\"minimum_grade\":null,\"subjects\":[\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT 609\",\"id\":\"req_stat_609\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"MATH\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/MATH 709\",\"id\":\"req_math_stat_709\",\"kind\":\"course\"}],\"notes\":[],\"root\":\"req_root\",\"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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"c05371fbebc56d4ca94dea272c3019efee7d045d1c710650edefa25e3e9e6510","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"STAT 609\",\"field\":\"description\",\"quote\":\"Review of probability, random variables and vectors and their distributions, moments and inequalities, generating functions, transformations of random variables, sampling and distribution theory, convergence concepts for sequences of random variables, laws of large numbers, central limit and other limit theorems.\"},{\"course_id\":\"GENBUS 656\",\"field\":\"description\",\"quote\":\"An introduction to predictive modeling for business applications beginning with some of the foundations. Leads to development of linear regression and classification models, and discussion of building models for prediction. Topics include selection, regularization, and the bias-variance tradeoff.\"},{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"Econometric methods, theory, and applications. Matrix algebra will be used. Topics include linear regression, least-squares estimation, inference, and hypothesis testing.\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"Probability distributions, statistical inference; multiple linear regression; introduction to econometric methods.\"}],\"text\":\"Probability theory, statistical inference, linear regression, and econometric methods.\"},{\"evidence\":[{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"}],\"text\":\"Calculus and linear algebra.\"}],\"search_phrases\":[\"Bayesian optimization marketing\",\"hierarchical modeling consumer choice\",\"Bayesian deep learning prediction\",\"marketing analytics graduate course\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"Consumer choice prediction, market analysis, and product development using Bayesian methods.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"title\",\"quote\":\"BAYESIAN MACHINE LEARNING FOR MARKETING\"},{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"This course teaches Bayesian statistical learning methods for marketing tasks like consumer choice prediction and product development.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"consumer choice prediction, market analysis, and product development\"}],\"text\":\"Consumer choice prediction, market analysis, and product development.\"}]}","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-5590a4969e0a630fe46a86e8","output_id":"c05371fbebc56d4ca94dea272c3019efee7d045d1c710650edefa25e3e9e6510","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-789789da373eecc1ff75f626","output_id":"dae0c804710d66cf56631909e32cb685949e967d4765a6d5d167074e04697e66","section":"requirements","status":"invalid","value_json":null,"candidate_json":"{\"nodes\":[{\"children\":[\"n1\",\"n2\",\"n3\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709) or declared in graduate Business Exchange program\",\"id\":\"n0\",\"kind\":\"any\"},{\"children\":[\"n4\",\"n5\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n1\",\"kind\":\"all\"},{\"children\":[\"n6\"],\"condition\":null,\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n2\",\"kind\":\"condition\"},{\"children\":[\"n7\",\"n8\",\"n9\",\"n10\"],\"condition\":null,\"course\":null,\"evidence\":\"(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n3\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":779,\"minimum_grade\":null,\"subjects\":[\"MARKETNG\"],\"timing\":\"unspecified\"},\"evidence\":\"Graduate/professional standing\",\"id\":\"n4\",\"kind\":\"condition\"},{\"children\":[],\"condition\":\"declared in graduate Business Exchange program\",\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n5\",\"kind\":\"condition\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":656,\"minimum_grade\":null,\"subjects\":[\"GENBUS\"],\"timing\":\"prior\"},\"evidence\":\"GEN BUS 656\",\"id\":\"n6\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":704,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 704\",\"id\":\"n7\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 709\",\"id\":\"n8\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":609,\"minimum_grade\":null,\"subjects\":[\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT 609\",\"id\":\"n9\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"MATH\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/MATH 709\",\"id\":\"n10\",\"kind\":\"course\"}],\"notes\":[\"The phrase 'Graduate/professional standing and ...' is parsed as an AND node (n1) requiring both standing and one of the listed courses.\",\"The phrase 'or declared in graduate Business Exchange program' is parsed as an alternative (n2) to the standing+course requirement.\",\"The course list '(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)' is parsed as an ANY node (n3) of the listed courses.\",\"Note: 'ECON 709' and 'STAT/MATH 709' are distinct course IDs in the linked_courses list.\"],\"root\":\"n0\",\"status\":\"parsed\"}","error":"Node n8: evidence 'ECON 709' must quote an exact source substring.","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-789789da373eecc1ff75f626","output_id":"dae0c804710d66cf56631909e32cb685949e967d4765a6d5d167074e04697e66","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"STAT 609\",\"field\":\"description\",\"quote\":\"Review of probability, random variables and vectors and their distributions, moments and inequalities, generating functions, transformations of random variables, sampling and distribution theory, convergence concepts for sequences of random variables, laws of large numbers, central limit and other limit theorems.\"},{\"course_id\":\"GENBUS 656\",\"field\":\"description\",\"quote\":\"An introduction to predictive modeling for business applications beginning with some of the foundations. Leads to development of linear regression and classification models, and discussion of building models for prediction. Topics include selection, regularization, and the bias-variance tradeoff.\"},{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"Econometric methods, theory, and applications. Matrix algebra will be used. Topics include linear regression, least-squares estimation, inference, and hypothesis testing.\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"Probability distributions, statistical inference; multiple linear regression; introduction to econometric methods.\"}],\"text\":\"Probability theory, statistical inference, linear regression, and econometric methods.\"},{\"evidence\":[{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"}],\"text\":\"Calculus and linear algebra.\"}],\"search_phrases\":[\"Bayesian optimization marketing\",\"hierarchical modeling consumer choice\",\"Bayesian deep learning prediction\",\"marketing analytics graduate course\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"Consumer choice prediction, market analysis, and product development using Bayesian methods.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"title\",\"quote\":\"BAYESIAN MACHINE LEARNING FOR MARKETING\"},{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"This course teaches Bayesian statistical learning methods for marketing tasks like consumer choice prediction and product development.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"consumer choice prediction, market analysis, and product development\"}],\"text\":\"Consumer choice prediction, market analysis, and product development.\"}]}","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-789789da373eecc1ff75f626","output_id":"dae0c804710d66cf56631909e32cb685949e967d4765a6d5d167074e04697e66","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"2fdcc0ef62ca869d4e84b06b6b44d902c647d0cb5ffbcc517985fde189a7bf29","section":"requirements","status":"valid","value_json":"{\"nodes\":[{\"children\":[\"req_grad_standing_and_prereq\",\"req_exchange_program\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709) or declared in graduate Business Exchange program\",\"id\":\"req_root\",\"kind\":\"any\"},{\"children\":[\"req_grad_standing\",\"req_prereq_any\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"req_grad_standing_and_prereq\",\"kind\":\"all\"},{\"children\":[],\"condition\":\"declared in graduate Business Exchange program\",\"course\":null,\"evidence\":\"or declared in graduate Business Exchange program\",\"id\":\"req_exchange_program\",\"kind\":\"condition\"},{\"children\":[],\"condition\":\"Graduate/professional standing\",\"course\":null,\"evidence\":\"Graduate/professional standing\",\"id\":\"req_grad_standing\",\"kind\":\"condition\"},{\"children\":[\"req_genbus_656\",\"req_econ_704\",\"req_econ_709\",\"req_stat_609\",\"req_math_stat_709\"],\"condition\":null,\"course\":null,\"evidence\":\"(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"req_prereq_any\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":656,\"minimum_grade\":null,\"subjects\":[\"GENBUS\"],\"timing\":\"prior\"},\"evidence\":\"GEN BUS 656\",\"id\":\"req_genbus_656\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":704,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 704\",\"id\":\"req_econ_704\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"709\",\"id\":\"req_econ_709\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":609,\"minimum_grade\":null,\"subjects\":[\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT 609\",\"id\":\"req_stat_609\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"MATH\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/MATH 709\",\"id\":\"req_math_stat_709\",\"kind\":\"course\"}],\"notes\":[],\"root\":\"req_root\",\"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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"2fdcc0ef62ca869d4e84b06b6b44d902c647d0cb5ffbcc517985fde189a7bf29","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"STAT 609\",\"field\":\"description\",\"quote\":\"Review of probability, random variables and vectors and their distributions, moments and inequalities, generating functions, transformations of random variables, sampling and distribution theory, convergence concepts for sequences of random variables, laws of large numbers, central limit and other limit theorems.\"},{\"course_id\":\"GENBUS 656\",\"field\":\"description\",\"quote\":\"An introduction to predictive modeling for business applications beginning with some of the foundations. Leads to development of linear regression and classification models, and discussion of building models for prediction. Topics include selection, regularization, and the bias-variance tradeoff.\"},{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"Econometric methods, theory, and applications. Matrix algebra will be used. Topics include linear regression, least-squares estimation, inference, and hypothesis testing.\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"Probability distributions, statistical inference; multiple linear regression; introduction to econometric methods.\"}],\"text\":\"Probability theory, statistical inference, linear regression, and econometric methods.\"},{\"evidence\":[{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"}],\"text\":\"Calculus and linear algebra.\"}],\"search_phrases\":[\"Bayesian optimization marketing\",\"hierarchical modeling consumer choice\",\"Bayesian deep learning prediction\",\"marketing analytics graduate course\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"Consumer choice prediction, market analysis, and product development using Bayesian methods.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"title\",\"quote\":\"BAYESIAN MACHINE LEARNING FOR MARKETING\"},{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"This course teaches Bayesian statistical learning methods for marketing tasks like consumer choice prediction and product development.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"consumer choice prediction, market analysis, and product development\"}],\"text\":\"Consumer choice prediction, market analysis, and product development.\"}]}","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"2fdcc0ef62ca869d4e84b06b6b44d902c647d0cb5ffbcc517985fde189a7bf29","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-8b774950c2b6adfdc46d1b82","output_id":"2fdcc0ef62ca869d4e84b06b6b44d902c647d0cb5ffbcc517985fde189a7bf29","section":"student_summary","status":"valid","value_json":"{\"context_hash\":\"02d7a7a66d8b25d55296a7130d16d58b97e093ef6f17486e3f29426fa66f0fde\",\"course_id\":\"MARKETNG 779\",\"current_instructors\":[],\"difficulty_workload\":[],\"errors\":[],\"historical_context\":[],\"message\":\"No course-specific reviews available\",\"offered\":false,\"profile_hash\":\"5cb4dabf887cdbcd8c00d5a1312e10828b95c63f30bc3ea76aea199565390d02\",\"quick_take\":[],\"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},{"run_id":"20260906T231458-5fdd2fff","observed_at":"2026-09-06 23:14:58.172943+00:00","course_uid":"course_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-dab8f6acaa72f26086773521","output_id":"7a6d070d63212a67fbd7a03e55bcd75e793f57ae6c19af0799b468e519ac884c","section":"requirements","status":"invalid","value_json":null,"candidate_json":"{\"nodes\":[{\"children\":[\"n1\",\"n2\",\"n3\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709) or declared in graduate Business Exchange program\",\"id\":\"n0\",\"kind\":\"any\"},{\"children\":[\"n4\",\"n5\"],\"condition\":null,\"course\":null,\"evidence\":\"Graduate/professional standing and (GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n1\",\"kind\":\"all\"},{\"children\":[\"n6\"],\"condition\":null,\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n2\",\"kind\":\"condition\"},{\"children\":[\"n7\",\"n8\",\"n9\",\"n10\"],\"condition\":null,\"course\":null,\"evidence\":\"(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)\",\"id\":\"n3\",\"kind\":\"any\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":779,\"minimum_grade\":null,\"subjects\":[\"MARKETNG\"],\"timing\":\"unspecified\"},\"evidence\":\"Graduate/professional standing\",\"id\":\"n4\",\"kind\":\"condition\"},{\"children\":[],\"condition\":\"declared in graduate Business Exchange program\",\"course\":null,\"evidence\":\"declared in graduate Business Exchange program\",\"id\":\"n5\",\"kind\":\"condition\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":656,\"minimum_grade\":null,\"subjects\":[\"GENBUS\"],\"timing\":\"prior\"},\"evidence\":\"GEN BUS 656\",\"id\":\"n6\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":704,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 704\",\"id\":\"n7\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"ECON\"],\"timing\":\"prior\"},\"evidence\":\"ECON 709\",\"id\":\"n8\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":609,\"minimum_grade\":null,\"subjects\":[\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT 609\",\"id\":\"n9\",\"kind\":\"course\"},{\"children\":[],\"condition\":null,\"course\":{\"course_number\":709,\"minimum_grade\":null,\"subjects\":[\"MATH\",\"STAT\"],\"timing\":\"prior\"},\"evidence\":\"STAT/MATH 709\",\"id\":\"n10\",\"kind\":\"course\"}],\"notes\":[\"The phrase 'Graduate/professional standing and ...' is parsed as an AND node (n1) requiring both standing and one of the listed courses.\",\"The phrase 'or declared in graduate Business Exchange program' is parsed as an alternative (n2) to the standing+course requirement.\",\"The course list '(GEN BUS 656,ECON 704,709,STAT 609, orSTAT/MATH 709)' is parsed as an ANY node (n3) of the listed courses.\",\"Note: 'ECON 709' and 'STAT/MATH 709' are distinct course IDs in the linked_courses list.\"],\"root\":\"n0\",\"status\":\"parsed\"}","error":"Node n8: evidence 'ECON 709' must quote an exact source substring.","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-dab8f6acaa72f26086773521","output_id":"7a6d070d63212a67fbd7a03e55bcd75e793f57ae6c19af0799b468e519ac884c","section":"search_profile","status":"valid","value_json":"{\"assumed_background\":[{\"evidence\":[{\"course_id\":\"STAT 609\",\"field\":\"description\",\"quote\":\"Review of probability, random variables and vectors and their distributions, moments and inequalities, generating functions, transformations of random variables, sampling and distribution theory, convergence concepts for sequences of random variables, laws of large numbers, central limit and other limit theorems.\"},{\"course_id\":\"GENBUS 656\",\"field\":\"description\",\"quote\":\"An introduction to predictive modeling for business applications beginning with some of the foundations. Leads to development of linear regression and classification models, and discussion of building models for prediction. Topics include selection, regularization, and the bias-variance tradeoff.\"},{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"Econometric methods, theory, and applications. Matrix algebra will be used. Topics include linear regression, least-squares estimation, inference, and hypothesis testing.\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"Probability distributions, statistical inference; multiple linear regression; introduction to econometric methods.\"}],\"text\":\"Probability theory, statistical inference, linear regression, and econometric methods.\"},{\"evidence\":[{\"course_id\":\"ECON 704\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"},{\"course_id\":\"ECON 709\",\"field\":\"description\",\"quote\":\"It is expected that students will have completed three semesters calculus (such asMATH 234) and linear algebra (such asMATH 340).\"}],\"text\":\"Calculus and linear algebra.\"}],\"search_phrases\":[\"Bayesian optimization marketing\",\"hierarchical modeling consumer choice\",\"Bayesian deep learning prediction\",\"marketing analytics graduate course\"],\"skills_taught\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"Consumer choice prediction, market analysis, and product development using Bayesian methods.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"}],\"summary\":{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"title\",\"quote\":\"BAYESIAN MACHINE LEARNING FOR MARKETING\"},{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"Learn to resolve common marketing tasks such as consumer choice prediction, market analysis, and product development by using Bayesian statistical learning methods.\"}],\"text\":\"This course teaches Bayesian statistical learning methods for marketing tasks like consumer choice prediction and product development.\"},\"topics\":[{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"A broad range of methods are covered, from standard approaches such as hierarchical modeling to more advanced techniques, including Bayesian Optimization and Bayesian Deep Learning.\"}],\"text\":\"Hierarchical modeling, Bayesian Optimization, and Bayesian Deep Learning.\"},{\"evidence\":[{\"course_id\":\"MARKETNG 779\",\"field\":\"description\",\"quote\":\"consumer choice prediction, market analysis, and product development\"}],\"text\":\"Consumer choice prediction, market analysis, and product development.\"}]}","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_80fc82a35bff4d7a426ffb0b","course_id":"MARKETNG 779","catalog_version_id":"d9d52a69c73e16e4f506cceadcec36211fad85963b8239395d6d262ce26c20c4","record_version_id":"8ebab7c010332f2968a024680c2731ae92ae14d6c7c38a9b5dfdb13ba8d7ace6","job_id":"enrich-dab8f6acaa72f26086773521","output_id":"7a6d070d63212a67fbd7a03e55bcd75e793f57ae6c19af0799b468e519ac884c","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}]