[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82336-en":3,"doc-seo-82336-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82336,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Two Vocabularies One Phenomenon Metadata Bias in AI Evidence Synthesis on Fertility Decline","Declining fertility increasingly enters policy through AI-driven evidence synthesis, yet the same underlying reality yields different outcomes depending on the vocabulary used. This work contrasts clinical and social framings of (in)fertility using controlled OpenAlex title-only queries, comparing metadata completeness, open access, output type, and institutional provenance. Social framing is less machine-legible, with indexing depth rather than paywalls driving gaps, compounding prior LLM extraction bias. Governance implications call for auditing discoverability infrastructure alongside models, prompts, and inclusion criteria.","Two Vocabularies, One Phenomenon: Metadata Bias in AI Evidence Synthesis on Fertility Decline  \nDeclining fertility is one of the defining policy questions of the next decade, and increasingly, what policymakers know about it is shaped by AI-synthesising the evidence base. But ask such a tool about reproduction and the answer depends on the word you use. The same phenomenon, framed clinically (e.g, infertility, IVF) or socially (e.g. , childlessness, fertility intentions), is catalogued with radically different completeness. And the catalogue as much if not more than the underlying scholarship, is what AI synthesis begins with (Bolaños et al. , 2024) . That databases under-index the social sciences, books, and grey literature is well established (Visser et al. , 2021) . What is new here is holding the topic fixed and asking whether metadata gaps act as a hidden policy filter on a single contested issue: the determinants of (in)fertility.  \nWe use two OpenAlex queries on the same phenomenon: a clinical basket (infertility, subfertility, ART, IVF, fecundity; n=101,645) and a social basket (childlessness, social infertility, fertility intentions, reproductive decision-making; n=3,646) . We compare them on metadata completeness, open access, output type, and institutional provenance. The social framing is consistently less machine-legible: output skewed to books and dissertations, authorship university-rather than healthcare-based. Open access rates are essentially equal (43 . 1% vs 41.3%), so the gap is in indexing depth, not paywalls, suggesting simple OA mandates will not fix it. On this same mixed literature, even before any coverage bias enters the picture, LLM tools already miss more than they catch when asked to extract hypotheses and claims (Uprety et al. , 2025); the bias documented here compounds an already-imperfect extraction stage.  \nThe governance implication is direct: discoverability infrastructure should be audited alongside models, prompts, and inclusion criteria. Metadata gaps are not housekeeping; they are an equity question about what counts as evidence.  \n1. Introduction  \nIn 2023 the American Society for Reproductive Medicine redefined infertility as a need for medical intervention rather than biological failure (ASRM, 2023), extending the clinical category into terrain that social-science scholarship had long studied under different vocabulary (e.g. , desire, partnership, access) . The two framings now describe overlapping phenomena from incompatible starting points, and which framing reaches policy depends on AI-assisted synthesis tools that mediate the search, selection, and presentation of evidence (Sousa et al. , 2026) .  \nThis paper is organised around two interrelated research questions on discoverability and its implications for governance. RQ1: Is the social-science evidence on fertilitydeterminants as machine-findable as the medical evidence, across indexing depth, identifier coverage, and full-text availability? RQ2: Should discoverability infrastructure be  \ntreated as a governance variable for AI evidence synthesis, audited alongside models, prompts, and inclusion criteria?  \n2. Data and Research Methodology  \nMapping how this discourse has evolved, from clinical success rates to family-enabling policies, requires seeing both vocabularies clearly. We operationalise the two framings through controlled title-only queries against OpenAlex conducted on 30/05/26, chosen to maximise inclusivity across output types, including those without abstracts:  \n• [CLINICAL] “infertility”OR “subfertility”OR“assisted reproductive technology”OR“in vitro fertilization” OR“fecundity”  \n• [SOCIAL] “childlessness”OR “involuntary childlessness”OR “social infertility”OR“fertility intentions”OR “reproductive decision-making”  \nThe resulting database of publications (101,645 clinical publications and 3,646 social publications) is compared across five dimensions: growth over time, metadata completeness, open access status,","cbCaicKrMUtOJfu6","https://ap.wps.com/l/cbCaicKrMUtOJfu6","pdf",500870,3,1,6,"English","en",105,"# Introduction\n# Data and Research Methodology\n# Key Findings","[{\"question\":\"How does vocabulary choice affect AI evidence synthesis on fertility decline?\",\"answer\":\"The document explains that framing fertility clinically versus socially leads to radically different completeness in the catalogued evidence, which then shapes what AI synthesis tools can retrieve and present for policy.\"},{\"question\":\"What method is used to compare clinical and social evidence?\",\"answer\":\"Two controlled OpenAlex title-only queries are run on the same topic: a clinical basket and a social basket, and the resulting corpora are compared across metadata completeness, open access, output type, and institutional provenance.\"},{\"question\":\"What is the main reason the social framing is harder for machines to surface?\",\"answer\":\"The evidence gap is attributed to lower indexing depth and less conforming metadata rather than differences in open access rates, implying that simple OA mandates would not fully fix discoverability.\"}]",1784179729,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"two-vocabularies-one-phenomenon-metadata-bias-in-ai-evidence-synthesis-on-fertility-decline","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/two-vocabularies-one-phenomenon-metadata-bias-in-ai-evidence-synthesis-on-fertility-decline/82336/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-20","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does vocabulary choice affect AI evidence synthesis on fertility decline?","Question",{"text":75,"@type":76},"The document explains that framing fertility clinically versus socially leads to radically different completeness in the catalogued evidence, which then shapes what AI synthesis tools can retrieve and present for policy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What method is used to compare clinical and social evidence?",{"text":80,"@type":76},"Two controlled OpenAlex title-only queries are run on the same topic: a clinical basket and a social basket, and the resulting corpora are compared across metadata completeness, open access, output type, and institutional provenance.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the main reason the social framing is harder for machines to surface?",{"text":84,"@type":76},"The evidence gap is attributed to lower indexing depth and less conforming metadata rather than differences in open access rates, implying that simple OA mandates would not fully fix discoverability.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]