{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T03:51:05Z","timestamp":1791258665321,"version":"4.1.0"},"reference-count":16,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Risk Analysis"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    How should the credibility of claims about the human health effects of exposures be evaluated when their support consists of multiple individually inconclusive lines of evidence? Health risk analysis typically draws on heterogeneous evidence streams\u2014including observational epidemiology, systematic reviews and meta\u2010analyses, mechanistic and toxicological evidence, and policy\u2010facing syntheses\u2014to support causal conclusions and risk management recommendations. However, important distinctions among observed associations, causal interpretations, mechanistic plausibility, and claims about intervention or policy effectiveness are often blurred in scientific reviews and evidence syntheses, making evaluations difficult to reproduce, audit, or systematically critique. This article introduces ASP1 (Automated Scientific Paper reviewer 1), available online at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/moirai.shinyapps.io\/asp1_pdf_runner\/\">https:\/\/moirai.shinyapps.io\/asp1_pdf_runner\/<\/jats:ext-link>\n                    , an AI\u2010assisted framework for systematic, transparent evaluation of heterogeneous scientific evidence and of the conclusions drawn from it. ASP1 combines modular review components, structured claim extraction, explicit linkage between evaluative judgments and supporting text, and cross\u2010module synthesis to expose and systematically examine the evidentiary and inferential chain connecting a document's evidence to its conclusions. We illustrate it using a mini\u2010corpus of recent publications concerning ultra\u2010processed foods (UPFs) and health spanning prospective cohort studies, case\u2013control studies, umbrella reviews, mechanistic syntheses, and policy\u2010facing evidence reviews. Results can be browsed at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/moirai.shinyapps.io\/asp1_bundle_browser\/\">https:\/\/moirai.shinyapps.io\/asp1_bundle_browser\/<\/jats:ext-link>\n                    . Across these diverse study designs, ASP1 consistently distinguished evidence of association from stronger causal and interventional claims and identified important limitations involving residual confounding, exposure misclassification, mechanistic uncertainty, category heterogeneity, and overextension of policy conclusions beyond direct evidentiary support. Comparison with independent expert human commentary on a recent\n                    <jats:italic>Lancet<\/jats:italic>\n                    review showed substantial overlap in major inferential concerns identified by ASP1 and by skilled human reviewers, while also revealing complementary strengths. ASP1 was generally stronger in explicit inferential decomposition, claim\u2010specific support classification, consistency, and auditability; human experts contributed richer contextual understanding, sharper methodological intuition, and more vivid and concrete examples of evidentiary limitations. These results suggest that current AI systems guided by structured evaluative frameworks can support more transparent, reproducible, and disciplined review of heterogeneous scientific evidence at realistic scales. The greatest promise of such systems may lie less in automating scientific judgment than in helping make scientific reasoning more explicit, inspectable, auditable, and open to challenge.\n                  <\/jats:p>","DOI":"10.1111\/risa.70356","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:00:31Z","timestamp":1789531231000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward AI\u2010Assisted Methodological Evaluations of Health Risk Analyses Using Diverse Types of Evidence"],"prefix":"10.1111","volume":"46","author":[{"suffix":"Jr.","given":"Louis Anthony","family":"Cox","sequence":"first","affiliation":[{"name":"Cox Associates, Entanglement, and University of Colorado Denver Denver Colorado USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/10408444.2025.2611827"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/qje\/qjaf037"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11121\u2010022\u201001336\u2010w"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00415\u2010023\u201012033\u20101"},{"key":"e_1_2_10_6_1","volume-title":"Some Organophosphate Insecticides and Herbicides","author":"IARC Working Group on the Evaluation of Carcinogenic Risks to Humans","year":"2017"},{"key":"e_1_2_10_7_1","unstructured":"Kraft A. T. F.Bateson B.Glenn et\u00a0al.2024.IRIS Toxicological Review of Formaldehyde (Inhalation) CASRN 50\u201000\u20100.U.S. Environmental Protection Agency.https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK612576\/."},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj\u20102023\u2010077310"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(26)00132\u20107"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lana.2024.100859"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers17132064"},{"key":"e_1_2_10_12_1","volume-title":"Co\u2010Intelligence: Living and Working With AI","author":"Mollick E.","year":"2024"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(25)01565\u2010X"},{"key":"e_1_2_10_14_1","unstructured":"Science Media Centre.2025.Expert Reaction to Paper 1 in the Lancet Series on Ultra\u2010Processed Foods Reviewing the Scientific Evidence on UPF and Health as Published in The Lancet.Science Media Centre.https:\/\/www.sciencemediacentre.org\/expert\u2010reaction\u2010to\u2010paper\u20101\u2010in\u2010the\u2010lancet\u2010series\u2010on\u2010ultra\u2010processed\u2010foods\u2010reviewing\u2010the\u2010scientific\u2010evidence\u2010on\u2010upf\u2010and\u2010health\u2010as\u2010published\u2010in\u2010the\u2010lancet\/."},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140\u20106736(25)01566\u20101"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18105457"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.0040297"}],"container-title":["Risk Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70356","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/risa.70356","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T03:02:09Z","timestamp":1791255729000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/risa.70356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":16,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1111\/risa.70356"],"URL":"https:\/\/doi.org\/10.1111\/risa.70356","archive":["Portico"],"relation":{},"ISSN":["0272-4332","1539-6924"],"issn-type":[{"value":"0272-4332","type":"print"},{"value":"1539-6924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]},"assertion":[{"value":"2026-05-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-30","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70356"}}