1,000 works · Opus 4.8 · GPT-5.6 (high) · Grok 4.5 · one locked rubric
The field’s boundary is not a line. It is a region.
Three frontier models screened the same 1,000 works, drawn from the real frame with known selection probabilities, against the same locked rubric on its full eight-field payload. Of the 51 works any model called metaresearch, only 19 (37.3%) were called metaresearch by all three, and 24 (47.1%) rest on a single model's opinion.
Two screeners can agree on a rate while finding almost entirely different works. At a ~1% base rate, the settled rejects buy 98% agreement for free — which is why an agreement statistic computed over the whole sample tells you nothing about the boundary, and why the table below, not a percentage, is the deliverable.
The three models are not interchangeable
How many of the 1,000 works each model called metaresearch (tier T1 or T2), on identical input. T3 is adjacent and does not count as in scope, which is why a model's count can never exceed the 51 works in the dossier.
Swap which model you call “the screener” and the size of the field moves. That spread — not the binomial confidence interval on any one model's labels — is the honest uncertainty on how big Canadian metaresearch is.
The disagreement dossier
All three verdicts, confidences and reasons side by side. These are the works against which the inclusion criteria have to be written — because these are the works on which reasonable screeners, given the same rubric and the same evidence, disagree.
| Work | Stratum | n_in | Opus 4.8 | GPT-5.6 | Grok 4.5 |
|---|---|---|---|---|---|
| Making it New! (the big sixties show) 2000 · book · en · Art Gallery of Windsor eBooks | about_only w=3321 | 0/3 | OUThigh other Exhibition catalogue of 1960s Canadian avant-garde art; art history and curation. | OUThigh other This exhibition catalogue documents Canadian art and does not study research itself. | OUThigh other Art exhibition catalogue documenting 1960s Canadian artists; cultural catalogue, not metaresearch. |
| Review of Andrew Irvine and John Russell (eds.), In the Agora: The Public Face of Canadian Philosophy 2011 · article · en · University of Toronto Quarterly | venue_new w=2684 | 0/3 | T3low editorial/commentary Book review of an edited volume on the public face of Canadian philosophy; commentary on Canadian scholars' public engagement, with no abstract to judge depth. | OUThigh editorial/commentary This is a review of a book about Canadian philosophy, not a study of research practice. | T3low editorial/commentary Book review of a volume on Canadian public philosophy; commentary, not analytic metaresearch. |
| Diseminasi Model Pemberdayaan Masyarakat Desa melalui Pengelolaan Agrowisata 2012 · article · en · MIMBAR Jurnal Sosial dan Pembangunan | aff_core w=5595 | 0/3 | OUThigh empirical Survey of rural community empowerment through agrotourism management; a development studies question. | OUThigh empirical The work studies rural-community empowerment through agrotourism management. | OUThigh empirical Rural community empowerment via agrotourism management; development studies, not metaresearch. |
| L'inquiétude de la vie facticielle. 2006 · article · fr · Les études philosophiques | french w=1554 | 0/3 | OUThigh conceptual Philosophical essay on Heidegger's reading of Aristotle; philosophy of existence, not of contemporary research practice. | OUThigh conceptual The article is a philosophical interpretation of Heidegger and Aristotle rather than a study of research practice. | OUThigh conceptual Phenomenological philosophy of Heidegger’s factical life; pure philosophy, not metaresearch. |
| Functional outcomes and gait analysis of patients after periacetabular sarcoma resection with and without ischiofemoral arthrodesis 2012 · article · en · Journal of Surgical Oncology | about_only w=3321 | 0/3 | OUThigh empirical Functional and gait outcomes after sarcoma resection; clinical outcomes study. | OUThigh empirical The study evaluates functional and gait outcomes after sarcoma surgery. | OUThigh empirical Functional outcomes and gait after periacetabular sarcoma surgery; clinical orthopedics. |
| Is telework effective for organizations? 2012 · article · en · Management Research Review | aff_core w=5595 | 0/3 | OUThigh empirical Meta-analysis using synthesis to answer whether telework benefits organizations; a management question, not a study of synthesis methods. | OUThigh empirical This uses meta-analysis to answer a substantive question about telework and organizations. | OUThigh empirical Uses meta-analysis to answer whether telework helps organizations; method-vs-object trap, domain management question. |
| Moral coherence and value pluralism 2013 · article · en · Canadian Journal of Philosophy | aff_core w=5595 | 0/3 | OUTmedium conceptual Philosophy paper on moral coherence, systematicity, and value pluralism; scientific reasoning appears only as an analogy, so the object is moral epistemology rather than research practice. | OUThigh conceptual This philosophical paper concerns moral reasoning and only uses scientific reasoning as an analogy, not as its object. | OUThigh conceptual Moral philosophy on value pluralism and coherence; science is only an analogy, not the object. |
| 戦争の記憶と場所「平和博物館」建設をめぐって--昭和館を中心に 2004 · article · ja · Mouseion Journal of the Classical Association of Canada | venue_new w=2684 | 0/3 | OUTmedium other Japanese article on war memory and peace museums; no abstract, but the object is public memory rather than research. | OUThigh conceptual The title concerns war memory and peace-museum construction rather than research itself. | OUTmedium conceptual Japanese title on war memory and peace-museum construction; memory/heritage studies, not research practice. |
| Managing Changes in First Nations’ Health Care Needs: Is Telehealth the Answer? 2009 · article · fr · The Journal of Community Informatics | french w=1554 | 0/3 | OUTmedium conceptual Commentary on telehealth for First Nations health care needs; notes that the topic is under-researched but the object is health service delivery. | OUThigh conceptual This discusses telehealth and First Nations healthcare needs rather than the research system. | OUThigh empirical Health services paper on telehealth for First Nations care needs; healthcare delivery, not research. |
| Differences in heart stroke volume between Han and Korean-Chinese nationalities and correlative factors. 2011 · article · en · PubMed | fund_new w=1679 | 0/3 | OUThigh empirical Comparison of cardiac stroke volume between ethnic groups; a clinical physiology question. | OUThigh empirical This compares cardiovascular measurements between population groups, not research itself. | OUThigh empirical Clinical physiology comparing stroke volume across ethnic groups; patient physiology, not research. |
| Oxidative Palladium(II)-catalyzed Arene C-H Bond Functionalization and Progress towards the Total Synthesis of 6-Deoxyerythronolide B 2012 · dissertation · en · Library and Archives Canada (Government of Canada) | venue_new w=2684 | 0/3 | OUThigh empirical Chemistry dissertation on palladium-catalyzed C-H functionalization and a total synthesis; synthetic methodology in the bench sense, not research practice. | OUThigh empirical The dissertation studies chemical synthesis and catalytic reactions rather than research methods as an object. | OUThigh empirical Chemistry dissertation on palladium-catalyzed arene C–H functionalization and natural-product synthesis. |
| Remote Sensing of River Delta Inundation: Exploiting the Potential of Coarse Spatial Resolution, Temporally-Dense MODIS Time Series 2015 · article · en · Remote Sensing | about_only w=3321 | 0/3 | OUThigh empirical Remote sensing of river delta inundation using MODIS time series; the object is hydrological monitoring. | OUThigh empirical The study uses remote sensing to characterize river-delta inundation, not to study research itself. | OUThigh empirical Remote sensing of river delta inundation; earth observation domain application. |
| René Audet et Andrée Mercier (dirs), La littérature et ses enjeux narratifs, Sainte-Foy, Les Presses de l’Université Laval, 2004, 314 p. 2006 · article · fr · Recherches sociographiques | french w=1554 | 0/3 | OUThigh editorial/commentary Book review of a literary studies volume. | OUThigh editorial/commentary It is a bibliographic review of a literary studies book, not research about research. | OUThigh editorial/commentary Book notice/review of a literary volume, not metaresearch. |
| Procedural Pain Management for Neonates Using Nonpharmacological Strategies 2011 · review · en · Advances in Neonatal Care | aff_core w=5595 | 0/3 | OUThigh empirical Clinical review of nonpharmacological strategies for neonatal procedural pain; the object is pain management. | OUThigh conceptual The review concerns pain-management strategies for neonates, not evidence-synthesis methodology. | OUThigh empirical Clinical review of nonpharmacological neonatal procedural pain management. |
| Developing countries given easier access to biomedical journals 2001 · article · en · Europe PMC (PubMed Central) | about_only w=3321 | 0/3 | T3medium editorial/commentary Journalistic news item on biomedical journal access for developing countries and on disputes over CMAJ editorial decisions; news about scholarly publishing and journal editorial independence, mapped but not pooled. | T3medium other This appears to be a news item about access to biomedical journals, making it contextual scholarly-communication material rather than analytic research. | T3medium editorial/commentary News-style item on biomedical journal access and CMAJ editorial controversy maps scholarly communication but is not analytic metaresearch. |
| Age and Task-Related Effects on Young Children’s Understanding of a Complex Picture Story 2009 · article · en · Alberta Journal of Educational Research | venue_new w=2684 | 0/3 | OUThigh empirical Developmental study of children's story comprehension; educational psychology, not a study of educational research. | OUThigh empirical The study examines children's narrative development and story comprehension. | OUThigh empirical Developmental study of children's story understanding; educational psychology, not metaresearch. |
| Biexponential longitudinal relaxation in white matter: Characterization and impact on T<sub>1</sub> mapping with IR‐FSE and MP2RAGE 2015 · article · en · Magnetic Resonance in Medicine | aff_core w=5595 | 0/3 | OUTmedium empirical MRI physics study of biexponential T1 relaxation; measurement reproducibility in the assay sense, not the reproducibility of research. | OUThigh empirical The study investigates MRI relaxation measurements and sequence parameters, not research reproducibility as a social or methodological practice. | OUThigh empirical MRI physics characterizing biexponential T1 relaxation to improve mapping is imaging-method development, not study of research practice. |
| <sup>29</sup>Si nuclear spins as a resource for donor spin qubits in silicon 2016 · article · en · New Journal of Physics | aff_core w=5595 | 0/3 | OUThigh empirical Theoretical study of silicon nuclear spins as qubit registers; quantum physics. | OUThigh empirical The study investigates silicon nuclear spins for quantum computing. | OUThigh empirical Silicon nuclear spins as quantum-computing resources; condensed-matter physics. |
| Gender, HIV/AIDS, and Human Security in Africa 2010 · article · fr · Canadian Journal of African Studies / Revue canadienne des études africaines | french w=1554 | 0/3 | OUThigh editorial/commentary Introduction to a special issue on gender, HIV/AIDS, and human security in Africa; the object is health, gender, and security, not research practice. | OUThigh empirical The work studies gender, HIV/AIDS, and security in Africa rather than research practice. | OUThigh conceptual Special-issue framing of gender, HIV/AIDS, and human security in Africa; domain social science. |
| Equity in Health and Health Care in Canada in International Perspective 2007 · other · en · Health care and disease management | about_only w=3321 | 0/3 | OUThigh empirical Analysis of income-related inequity in Canadian health care; the Canadian health system, not the research system. | OUThigh conceptual Canada's health-care system is a substantive object, but the work does not study research itself. | OUThigh policy Health-care equity and access in Canada; object is the care system, not the research system. |
| "Musak": The Office and the Language of Madness 2004 · article · en · International fiction review | venue_new w=2684 | 0/3 | OUThigh conceptual Literary close reading of a Benedetti short story; literary criticism. | OUThigh conceptual This provides a literary interpretation of a short story, not a study of research. | OUThigh conceptual Literary close reading of Benedetti's short fiction; humanities criticism, not research systems. |
| Le processus relationnel de groupe : avancées pour un modèle de psychothérapie de groupe en analyse transactionnelle 2015 · article · fr · Actualités en analyse transactionnelle/Actualités en analyse transactionnelle | french w=1554 | 0/3 | OUThigh conceptual Model of relational group psychotherapy in transactional analysis. | OUThigh conceptual The article concerns group psychotherapy theory rather than research itself. | OUThigh conceptual Psychotherapy model of relational group therapy, clinical practice not research methods. |
| Implementing tasks with interactive technologies in classroom CALL: towards a developmental framework / Vers un cadre de développement pour la mise en œuvre de tâches à l’aide de l’apprentissage des langues assisté par ordinateur (ALAO) 2014 · article · en · Canadian Journal of Learning and Technology | venue_new w=2684 | 0/3 | OUTmedium empirical Study of teachers implementing interactive technology in task-based language teaching; the object is classroom pedagogy and teacher development, not research practice. | OUThigh empirical It studies teachers' use of classroom technology and pedagogy, not research itself. | OUThigh empirical Language-education study of IWB tasks in classroom CALL; teaching practice, not research. |
| Magnetic resonance imaging and prediction of outcome in patients with major depressive disorder 2009 · article · en · Journal of Psychiatry and Neuroscience | aff_core w=5595 | 0/3 | OUThigh empirical Review of MRI findings predicting treatment outcome in depression; clinical neuroscience. | OUThigh conceptual It reviews clinical applications of neuroimaging for depression rather than studying evidence synthesis or research practice. | OUThigh empirical Clinical review of MRI predictors of treatment outcome in major depression; medical imaging, not metaresearch. |
| Distributed Search and Pattern Matching 2009 · book-chapter · en | aff_core w=5595 | 0/3 | OUThigh conceptual Book chapter on distributed search and pattern matching in peer-to-peer networks; a computer science topic. | OUThigh other The title clearly indicates a technical computer-science chapter rather than research itself. | OUThigh other Book chapter on distributed search and pattern matching; peer-to-peer CS topic, not research practice. |
| The Edinburgh Companion to Scottish Drama 2011 · book · en · Edinburgh University Press eBooks | about_only w=3321 | 0/3 | OUThigh conceptual Scholarly companion to Scottish drama; literary and theatre studies. | OUThigh other This book concerns Scottish drama and theatre, not research itself. | OUThigh conceptual Literary and theatre studies companion to Scottish drama; arts and humanities domain content. |
| Essais moraux, politiques et littéraires, Première partie (review) 2000 · article · fr · Hume studies | french w=1554 | 0/3 | OUThigh editorial/commentary Review of an edition of Hume's essays; philosophy book review. | T3high editorial/commentary This is explicitly a review and therefore contextual material rather than an analytic study. | OUTmedium editorial/commentary Book review of Hume essays; humanities commentary, not research practice. |
| Diabetes is rising in OECD countries, report warns 2015 · article · en · BMJ | about_only w=3321 | 0/3 | OUThigh editorial/commentary News item reporting an OECD report on rising diabetes; the object is population health, not research practice. | OUThigh other This news report concerns diabetes and public health policy, not the research system. | OUThigh editorial/commentary News-style report on rising diabetes in OECD countries; public health news, not metaresearch. |
| The effect of self-efficacy on coping behaviours, performance, and emotions in youth swimmers 2009 · book · en · cIRcle (University of British Columbia) | about_only w=3321 | 0/3 | OUThigh empirical Sport psychology thesis on self-efficacy, coping, performance, and emotion in youth swimmers; the object is athlete psychology. | OUThigh empirical The study examines psychological factors in youth swimming performance rather than research practice. | OUThigh empirical Sport psychology study of self-efficacy, coping, and performance in youth swimmers. |
| Methyl succinate antagonises biguanide‐induced AMPK‐activation and death of pancreatic <i>β</i>‐cells through restoration of mitochondrial electron transfer 2007 · article · en · British Journal of Pharmacology | fund_new w=1679 | 0/3 | OUThigh empirical Pharmacology experiment on biguanide-induced AMPK activation in beta-cells; the object is cell metabolism. | OUThigh empirical The study investigates metformin effects on pancreatic beta cells. | OUThigh empirical Biomedical pharmacology of biguanides on pancreatic beta cells. |
| Time-Domain Modelling of Group-Delay and Amplitude Characteristics in Ultra-Wideband Printed-Circuit Antennas 2008 · book-chapter · en · Springer proceedings in physics | aff_core w=5595 | 0/3 | OUThigh empirical Engineering chapter on time-domain modelling of ultra-wideband printed-circuit antennas. | OUTlow other The title identifies an antenna engineering study, but the abstract is missing. | OUThigh empirical Engineering study of UWB printed-circuit antenna characteristics; domain hardware modelling. |
| A Literature Review of Quality in Lower Gastrointestinal Endoscopy from the Patient Perspective 2011 · review · en · Canadian Journal of Gastroenterology | aff_core w=5595 | 0/3 | OUThigh empirical Systematic review used to answer a health-services question about endoscopy quality from the patient perspective; uses a synthesis method rather than studying one. | OUThigh other This review concerns patient-perceived quality of endoscopy services, not research practice. | OUThigh empirical Literature review of patient-perceived quality of clinical endoscopy services. |
| Traite des sensations 2010 · book · fr | french w=1554 | 0/3 | OUTmedium other Digitized classic philosophy text (Condillac's Traité des sensations); not a study of research practice. | OUThigh other It concerns a book and digital-library description, not research as an object of study. | OUTmedium other Classic philosophy treatise on sensation; abstract is digital-library boilerplate, not a study of research. |
| Performance Relevance of Capital Structure Choices 2015 · article · en · International Journal of Economics and Finance | venue_new w=2684 | 0/3 | OUThigh empirical Corporate finance study of leverage and firm productivity; although motivated by discrepancies across prior studies, it answers the finance question itself rather than studying the literature. | OUThigh empirical The study examines corporate leverage and firm performance, not research itself. | OUThigh empirical Corporate-finance study of leverage and firm performance; object is firm value, not science. |
| Structural Factors Associated with Higher Education Access for First-Generation Refugees in Canada: An Agenda for Research 2012 · article · en · Refuge Canada s Journal on Refuge | venue_new w=2684 | 0/3 | OUTmedium conceptual Literature review of structural barriers to higher education access for refugees in Canada, closing with a research agenda; the substantive object is refugee educational access rather than research practice, although its gap analysis and critique of aggregate immigrant categories edge toward the boundary. | OUThigh conceptual This review concerns refugees' access to higher education, not how research is conducted or evaluated. | OUThigh conceptual Agenda paper on refugees’ access to tertiary education; student access, not the research workforce or research practice. |
| The impact of climate change on the well‐being and lifestyle of a First Nation community in the western James Bay region 2013 · article · en · Canadian Geographies / Géographies canadiennes | aff_core w=5595 | 0/3 | OUThigh empirical Study of climate change impacts on a First Nation community; environmental and social effects, not research practice. | OUThigh empirical This studies climate-change impacts on a First Nation community, not the research system. | OUThigh empirical Community climate-impact ethnography of a First Nation; object is environment and well-being, not the research system. |
| Selected Maps of British Columbia Published During 1977 and 1978 2010 · article · en · Open Collections | about_only w=3321 | 0/3 | OUThigh other Listing of maps of British Columbia published in 1977-1978; a bibliographic list, not a bibliometric study. | OUThigh other It is a catalog-like listing of maps rather than research about research. | OUThigh other Bibliographic list of BC maps is cartographic inventory, not a study of research. |
| Minimally Invasive Sinus Lift Implant Device: A Multicenter Safety and Efficacy Trial Preliminary Results 2012 · article · en · Clinical Implant Dentistry and Related Research | venue_new w=2684 | 0/3 | OUThigh empirical Clinical safety and efficacy trial of a dental sinus lift implant device. | OUThigh empirical The trial evaluates a dental implant procedure, not research practice. | OUThigh empirical Dental implant clinical trial of a sinus-lift device, domain medicine. |
| Effects of transport time and location within truck on skin bruises and meat quality of market weight pigs in two seasons 2013 · article · en · Canadian Journal of Animal Science | aff_core w=5595 | 0/3 | OUThigh empirical Animal science study of pig transport conditions and meat quality. | OUThigh empirical This studies pig transport conditions and meat quality, not research itself. | OUThigh empirical Animal science study of pig transport effects on bruises and meat quality. |
| 10.1016/0967-0653(96)80394-2 2000 · article · en · Time to knit | venue_new w=2684 | 0/3 | OUThigh empirical Nutrient budget study of an estuary and its catchment; environmental science. | OUThigh empirical It investigates nutrient flows in an estuary and catchment, not research itself. | OUThigh empirical Environmental nutrient budget of an estuary; domain science, not research as object. |
| Crystal structure, biochemical and cellular activities demonstrate separate functions of MTH1 and MTH2 2015 · article · en · Nature Communications | fund_new w=1679 | 0/3 | OUThigh empirical Structural and cellular study separating the functions of MTH1 and MTH2/NUDT15; the object is enzyme biology. | OUThigh empirical The study investigates molecular functions in cancer biology rather than research itself. | OUThigh empirical Structural and cellular biochemistry of MTH1/MTH2 enzymes; cancer biology domain research. |
| Home fortification with micronutrient sprinkles – A new approach for the prevention and treatment of nutritional anemias 2003 · article · en · Paediatrics & Child Health | aff_core w=5595 | 0/3 | OUThigh other Overview of micronutrient Sprinkles for home fortification against iron deficiency anemia; the object is a nutrition intervention. | OUThigh conceptual The work concerns micronutrient treatment for anemia, not research practice. | OUThigh empirical Public-health intervention for nutritional anemia via micronutrient sprinkles; clinical/public-health object. |
| Smallest singular value of sparse random matrices 2012 · preprint · en · Studia Mathematica | aff_core w=5595 | 0/3 | OUThigh empirical Probability bounds on singular values of sparse random matrices; pure mathematics. | OUThigh conceptual This proves mathematical results about sparse random matrices, not research itself. | OUThigh empirical Pure mathematics on singular values of sparse random matrices. |
| A meta-analysis of the effect of inspired oxygen concentration on the incidence of surgical site infection following cesarean section 2013 · review · en · International Journal of Obstetric Anesthesia | aff_core w=5595 | 0/3 | OUThigh empirical Meta-analysis answering a clinical question about oxygen concentration and surgical site infection; a synthesis method used, not studied. | OUThigh empirical This meta-analysis answers a clinical question about surgical-site infection after cesarean section rather than studying synthesis methodology. | OUThigh empirical Meta-analysis answering a clinical SSI/cesarean oxygen question; uses synthesis, does not study it. |
| Complex I Deficiency Due to Selective Loss of Ndufs4 in the Mouse Heart Results in Severe Hypertrophic Cardiomyopathy 2014 · article · en · PLoS ONE | fund_new w=1679 | 0/3 | OUThigh empirical Mouse genetic model of complex I deficiency and cardiomyopathy. | OUThigh empirical The study investigates mitochondrial dysfunction and cardiomyopathy in mice. | OUThigh empirical Mouse model of cardiac complex I deficiency; biomedical pathophysiology. |
| Status report from VERITAS 2007 · article · en · Journal of Physics Conference Series | aff_core w=5595 | 0/3 | OUTmedium infrastructure/announcement Construction and performance status report for a gamma-ray telescope; an astronomy instrument announcement rather than infrastructure of the research ecosystem in the metaresearch sense. | T3high infrastructure/announcement This report announces construction status and performance characteristics of a research observatory. | OUThigh infrastructure/announcement Astronomy facility construction/performance status report, not research-ecosystem infrastructure as metaresearch object. |
| Learning to Relate Images 2013 · review · en · IEEE Transactions on Pattern Analysis and Machine Intelligence | aff_core w=5595 | 0/3 | OUThigh conceptual Review of relational deep-learning methods for image correspondence; a machine-learning methods contribution in its own domain. | OUThigh conceptual This reviews machine-learning methods for image relations, not methods or practices of research. | OUThigh conceptual Computer-vision methods review on learning image correspondences; domain ML/vision, not metaresearch. |
| La question du pouvoir exécutif dans l'évolution institutionnelle et le débat politique révolutionnaire 2000 · article · fr · Annales historiques de la Révolution française | french w=1554 | 0/3 | OUThigh conceptual Political history of executive power during the French Revolution. | OUThigh empirical The article studies revolutionary political history, not research itself. | OUThigh conceptual Historical analysis of executive power in the French Revolution, not contemporary research practice. |
| The significance of mathematical knowledge in teaching elementary methods courses: perspectives of mathematics teacher educators 2010 · article · en · Educational Studies in Mathematics | aff_core w=5595 | 0/3 | OUTmedium empirical Study of mathematics teacher educators' views on mathematical knowledge in methods courses; the object is teacher education, not research practice. | OUThigh empirical It studies mathematics knowledge in teacher education rather than research practice. | OUTmedium empirical Mathematics teacher education study of knowledge for teaching methods courses, not research methods or systems. |
| Quantifying the mechanisms for segmental duplications in mammalian genomes by statistical analysis and modeling 2005 · article · en · Proceedings of the National Academy of Sciences | fund_new w=1679 | 0/3 | OUThigh empirical Statistical modelling of the molecular mechanisms of segmental duplication in mammalian genomes. | OUThigh empirical It models mechanisms of mammalian genomic duplication, not research methods or research governance. | OUThigh empirical Genomics study of mechanisms of mammalian segmental duplications; domain biology. |
What the screen actually found
Three frontier models (Opus 4.8, GPT-5.6 high, Grok 4.5) screened the same 1,000 works from the REAL 4.3M frame, on the rubric's FULL eight-field payload, with randomized manifest-logged chunks and harness-written labels: every defect D1, D2, D11 and finding 16 identified, repaired. Design-weighted base rates span 1.89% to 3.54% (1.9x). But the sets are the finding, as finding 16 predicted: of the 51 works ANY model called metaresearch, only 19 (37%) were called metaresearch by ALL THREE, and 24 (47%) rest on a single model's opinion. THE FIELD'S BOUNDARY IS NOT A LINE THE MODELS SHARE; IT IS A REGION THEY EACH CUT DIFFERENTLY. GPT-5.6 also violated the locked output schema on 18 of 1,000 records, writing genre values into the tier field, which the manifest validator caught. The deliverable is not the base rate: it is the disagreement dossier, the 51 works that mark the empirical boundary of the field and against which the inclusion criteria must actually be written.
Computed 2026-07-12T19:52:14Z · all 22 findings · this dossier as JSON