{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33193087", "kind": "science-record", "revision": 7, "content_hash": "sha256:ddafcc19c28c7560f528eaddb251229efea731ea50b0ae2d62415ccb9cbccf1f", "created_at": "2026-11-01T15:41:15Z", "updated_at": "2026-11-01T22:02:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Immune Cell Confrontation in the Papillary Thyroid Carcinoma Microenvironment.", "doi": "10.3389/fendo.2020.570604", "pmid": "33193087", "authors": ["Zhenyu Xie", "Xin Li", "Yuzhen He", "Song Wu", "Shiyue Wang", "Jianjian Sun", "Yuchen He", "Yu Lun", "Jian Zhang"], "journal": "Frontiers in endocrinology", "year": 2020, "abstract": "Background: Papillary thyroid cancer has been associated with chronic inflammation. A systematic understanding of immune cell infiltration in PTC is essential for subsequent immune research and new diagnostic and therapeutic strategies.\nMethods: Three different algorithms, single-sample gene set enrichment analysis (ssGSEA), immune cell marker and CIBERSORT, were used to evaluate immune cell infiltration levels (abundance and proportion) in 10 data sets (The Cancer Genome Atlas [TCGA], GSE3467, GSE3678, GSE5364, GSE27155, GSE33630, GSE50901, GSE53157, GSE58545, and GSE60542; a total of 799 PTC and 194 normal thyroid samples). Consensus unsupervised clustering divided PTC patients into low-immunity and high-immunity groups. Weighted gene coexpression network analysis (WGCNA) and gene set enrichment analysis (GSEA) were used to analyze the potential mechanisms causing differences in the immune response.\nResults: Compared with normal tissues, PTC tissues had a higher overall immune level and higher abundance levels and proportions of M2 macrophages, Tregs, monocytes, neutrophils, dendritic cells (DCs), mast cells (MCs), and M0 macrophages. Compared with early PTC, advanced PTC showed higher immune infiltration and higher abundance levels and proportions of M2 macrophages, Tregs, monocytes, neutrophils, DCs, MCs, and M0 macrophages. Compared to the low-immunity group, the high-immunity group exhibited more advanced stages, larger tumor sizes, greater lymph node metastases, higher tall-cell PTCs, lower follicular PTC proportions, more BRAF mutations, and fewer RAS mutations. Epstein-Barr virus (EBV) infection was the most significantly enriched Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway for key module genes.\nConclusions: In human PTC, M2 macrophages, Tregs, monocytes, neutrophils, DCs, MCs, and M0 macrophages appear to play a tumor-promoting role, while M1 macrophages, CD8+ T cells, B cells, NK cells, and T follicular helper (TFH) cells (including eosinophils, γδ T cells, and Th17 cells with weak supporting evidence) appear to play an antitumor role. During the occurrence and development of PTC, the overall immune level was increased, and the abundance and proportion of tumor-promoting immune cells were significantly increased, indicating that immune escape had been aggravated. Finally, we speculate that EBV may play an important role in changing the immune microenvironment of PTC tumors.", "claims": [{"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33193087", "locator": "sections[26] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33193087"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE27155"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_mann_whitney", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE27155"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_mann_whitney"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33193087", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fendo.2020.570604", "sha256": "sha256:0efcaa43804db7c89c0527c02e8911a7e40731fa9d4e1e33379d8141330115ab", "bytes": 63559, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fendo.2020.570604", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7642595", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE27155", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27155", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27155", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM671255", "GSM671256", "GSM671257", "GSM671258", "GSM671259", "GSM671260", "GSM671261", "GSM671262", "GSM671263", "GSM671264", "GSM671265", "GSM671266", "GSM671267", "GSM671268", "GSM671269", "GSM671270", "GSM671271", "GSM671272", "GSM671273", "GSM671274", "GSM671275", "GSM671276", "GSM671277", "GSM671278", "GSM671279", "GSM671280", "GSM671281", "GSM671282", "GSM671283", "GSM671284", "GSM671285", "GSM671286", "GSM671287", "GSM671288", "GSM671289", "GSM671290", "GSM671291", "GSM671292", "GSM671293", "GSM671294", "GSM671295", "GSM671296", "GSM671297", "GSM671298", "GSM671299", "GSM671300", "GSM671301", "GSM671302", "GSM671303", "GSM671304", "GSM671305", "GSM671306", "GSM671307", "GSM671308", "GSM671309", "GSM671310", "GSM671311", "GSM671312", "GSM671313", "GSM671314", "GSM671315", "GSM671316", "GSM671317", "GSM671318", "GSM671319", "GSM671320", "GSM671321", "GSM671322", "GSM671323", "GSM671324", "GSM671325", "GSM671326", "GSM671327", "GSM671328", "GSM671329", "GSM671330", "GSM671331", "GSM671332", "GSM671333", "GSM671334", "GSM671335", "GSM671336", "GSM671337", "GSM671338", "GSM671339", "GSM671340", "GSM671341", "GSM671342", "GSM671343", "GSM671344", "GSM671345", "GSM671346", "GSM671347", "GSM671348", "GSM671349", "GSM671350", "GSM671351", "GSM671352", "GSM671353"], "sample_count": 99, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Human thyroid adenomas, carcinomas, and normals", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE33630", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33630", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33630", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM831749", "GSM831750", "GSM831751", "GSM831752", "GSM831753", "GSM831754", "GSM831755", "GSM831756", "GSM831757", "GSM831758", "GSM831759", "GSM831760", "GSM831761", "GSM831762", "GSM831763", "GSM831764", "GSM831765", "GSM831766", "GSM831767", "GSM831768", "GSM831769", "GSM831770", "GSM831771", "GSM831772", "GSM831773", "GSM831774", "GSM831775", "GSM831776", "GSM831777", "GSM831778", "GSM831779", "GSM831780", "GSM831781", "GSM831782", "GSM831783", "GSM831784", "GSM831785", "GSM831786", "GSM831787", "GSM831788", "GSM831789", "GSM831790", "GSM831791", "GSM831792", "GSM831793", "GSM831794", "GSM831795", "GSM831796", "GSM831797", "GSM831798", "GSM831799", "GSM831800", "GSM831801", "GSM831802", "GSM831803", "GSM831804", "GSM831805", "GSM831806", "GSM831807", "GSM831808", "GSM831809", "GSM831810", "GSM831811", "GSM831812", "GSM831813", "GSM831814", "GSM831815", "GSM831816", "GSM831817", "GSM831818", "GSM831819", "GSM831820", "GSM831821", "GSM831822", "GSM831823", "GSM831824", "GSM831825", "GSM831826", "GSM831827", "GSM831828", "GSM831829", "GSM831830", "GSM831831", "GSM831832", "GSM831833", "GSM831834", "GSM831835", "GSM831836", "GSM831837", "GSM831838", "GSM831839", "GSM831840", "GSM831841", "GSM831842", "GSM831843", "GSM831844", "GSM831845", "GSM831846", "GSM831847", "GSM831848", "GSM831849", "GSM831850", "GSM831851", "GSM831852", "GSM831853"], "sample_count": 105, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Normal thyrocytes vs papillary vs anaplastic thyroid carcinomas", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE3467", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3467", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3467", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM77362", "GSM77363", "GSM77364", "GSM77365", "GSM77366", "GSM77367", "GSM77368", "GSM77369", "GSM77370", "GSM77371", "GSM77372", "GSM77373", "GSM77374", "GSM77375", "GSM77376", "GSM77377", "GSM77378", "GSM77379"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "The role of micro-RNA genes in papillary thyroid carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE3678", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3678", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3678", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM85215", "GSM85216", "GSM85217", "GSM85218", "GSM85219", "GSM85220", "GSM85221", "GSM85222", "GSM85223", "GSM85224", "GSM85225", "GSM85226", "GSM85227", "GSM85228"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "PTC versus paired normal thyroid tissue", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE50901", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50901", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50901", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1232174", "GSM1232175", "GSM1232176", "GSM1232177", "GSM1232178", "GSM1232179", "GSM1232180", "GSM1232181", "GSM1232182", "GSM1232183", "GSM1232184", "GSM1232185", "GSM1232186", "GSM1232187", "GSM1232188", "GSM1232189", "GSM1232190", "GSM1232191", "GSM1232192", "GSM1232193", "GSM1232194", "GSM1232195", "GSM1232196", "GSM1232197", "GSM1232198", "GSM1232199", "GSM1232200", "GSM1232201", "GSM1232202", "GSM1232203", "GSM1232204", "GSM1232205", "GSM1232206", "GSM1232207", "GSM1232208", "GSM1232209", "GSM1232210", "GSM1232211", "GSM1232212", "GSM1232213", "GSM1232214", "GSM1232215", "GSM1232216", "GSM1232217", "GSM1232218", "GSM1232219", "GSM1232220", "GSM1232221", "GSM1232222", "GSM1232223", "GSM1232224", "GSM1232225", "GSM1232226", "GSM1232227", "GSM1232228", "GSM1232229", "GSM1232230", "GSM1232231", "GSM1232232", "GSM1232233", "GSM1232234", "GSM1232235", "GSM1232236", "GSM1232237", "GSM1232238"], "sample_count": 65, "group_sizes": null, "group_sizes_basis": null, "platform": "13607", "taxon": "Homo sapiens", "title": "Expression profiling identifies deregulated pathways and top diagnostic markers in papillary thyroid carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE53157", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53157", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53157", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1283115", "GSM1283116", "GSM1283117", "GSM1283118", "GSM1283119", "GSM1283120", "GSM1283121", "GSM1283122", "GSM1283123", "GSM1283124", "GSM1283125", "GSM1283126", "GSM1283127", "GSM1283128", "GSM1283129", "GSM1283130", "GSM1283131", "GSM1283132", "GSM1283133", "GSM1283134", "GSM1283135", "GSM1283136", "GSM1283137", "GSM1283138", "GSM1283139", "GSM1283140", "GSM1283141"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling associated with the progression to poorly differentiated thyroid carcinomas", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE5364", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE5364", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE5364", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM121673", "GSM121674", "GSM121675", "GSM121676", "GSM121677", "GSM121678", "GSM121679", "GSM121680", "GSM121681", "GSM121682", "GSM121683", "GSM121684", "GSM121685", "GSM121686", "GSM121687", "GSM121688", "GSM121689", "GSM121690", "GSM121691", "GSM121692", "GSM121693", "GSM121694", "GSM121695", "GSM121696", "GSM121697", "GSM121698", "GSM121699", "GSM121700", "GSM121701", "GSM121702", "GSM121703", "GSM121704", "GSM121705", "GSM121706", "GSM121707", "GSM121708", "GSM121709", "GSM121710", "GSM121711", "GSM121712", "GSM121713", "GSM121714", "GSM121715", "GSM121716", "GSM121717", "GSM121718", "GSM121719", "GSM121720", "GSM121721", "GSM121722", "GSM121723", "GSM121724", "GSM121725", "GSM121726", "GSM121727", "GSM121728", "GSM121729", "GSM121730", "GSM121731", "GSM121732", "GSM121733", "GSM121734", "GSM121735", "GSM121736", "GSM121737", "GSM121738", "GSM121739", "GSM121740", "GSM121741", "GSM121742", "GSM121743", "GSM121744", "GSM121745", "GSM121746", "GSM121747", "GSM121748", "GSM121749", "GSM121750", "GSM121751", "GSM121752", "GSM121753", "GSM121754", "GSM121755", "GSM121756", "GSM121757", "GSM121758", "GSM121759", "GSM121760", "GSM121761", "GSM121762", "GSM121763", "GSM121764", "GSM121765", "GSM121766", "GSM121767", "GSM121768", "GSM121769", "GSM121770", "GSM121772", "GSM121773", "GSM121774", "GSM121775", "GSM121776", "GSM121777", "GSM121778", "GSM121779", "GSM121780", "GSM121781", "GSM121782", "GSM121783", "GSM121784", "GSM121785", "GSM121786", "GSM121787", "GSM121788", "GSM121789", "GSM121790", "GSM121791", "GSM121792", "GSM121793", "GSM121794", "GSM121795", "GSM121796", "GSM121797", "GSM121798", "GSM121799", "GSM121800", "GSM121801", "GSM121802", "GSM121803", "GSM121804", "GSM121805", "GSM121806", "GSM121807", "GSM121808", "GSM121809", "GSM121810", "GSM121811", "GSM121812", "GSM121813", "GSM121814", "GSM121815", "GSM121816", "GSM121817", "GSM121818", "GSM121819", "GSM121820", "GSM121821", "GSM121822", "GSM121823", "GSM121824", "GSM121825", "GSM121826", "GSM121827", "GSM121828", "GSM121829", "GSM121830", "GSM121831", "GSM121832", "GSM121833", "GSM121834", "GSM121835", "GSM121836", "GSM121837", "GSM121838", "GSM121839", "GSM121840", "GSM121841", "GSM121842", "GSM121843", "GSM121844", "GSM121845", "GSM121846", "GSM121847", "GSM121848", "GSM121849", "GSM121850", "GSM121851", "GSM121852", "GSM121853", "GSM121854", "GSM121855", "GSM121856", "GSM121857", "GSM121858", "GSM121859", "GSM121860", "GSM121861", "GSM121862", "GSM121863", "GSM121864", "GSM121865", "GSM121866", "GSM121867", "GSM121868", "GSM121869", "GSM121872", "GSM121873", "GSM121874", "GSM121875", "GSM121876", "GSM121877", "GSM121878", "GSM121879", "GSM121880", "GSM121881", "GSM121882", "GSM121883", "GSM121884", "GSM121885", "GSM121886", "GSM121887", "GSM121888", "GSM121889", "GSM121892", "GSM121893", "GSM121894", "GSM121895", "GSM121896", "GSM121897", "GSM121898", "GSM121899", "GSM121900", "GSM121901", "GSM121902", "GSM121903", "GSM121904", "GSM121905", "GSM121906", "GSM121907", "GSM121909", "GSM121917", "GSM121918", "GSM121919", "GSM121920", "GSM121921", "GSM121922", "GSM121923", "GSM121924", "GSM121925", "GSM121927", "GSM121928", "GSM121929", "GSM121930", "GSM121931", "GSM121932", "GSM121933", "GSM121934", "GSM121935", "GSM121936", "GSM121937", "GSM121938", "GSM121939", "GSM121940", "GSM121941", "GSM121942", "GSM121943", "GSM121944", "GSM121945", "GSM121946", "GSM121947", "GSM121950", "GSM121951", "GSM121952", "GSM121953", "GSM121954", "GSM121955", "GSM121956", "GSM121957", "GSM121958", "GSM121959", "GSM121960", "GSM121961", "GSM121962", "GSM121963", "GSM121964", "GSM121965", "GSM121966", "GSM121967", "GSM121968", "GSM121969", "GSM121970", "GSM121971", "GSM121972", "GSM121973", "GSM121974", "GSM121975", "GSM121976", "GSM121977", "GSM121978", "GSM121979", "GSM121980", "GSM121981", "GSM121982", "GSM121983", "GSM121984", "GSM121985", "GSM121986", "GSM121987", "GSM121988", "GSM121989", "GSM121990", "GSM121991", "GSM121992", "GSM121993", "GSM121994", "GSM121995", "GSM121996", "GSM121997", "GSM121998", "GSM121999", "GSM122000", "GSM122001", "GSM122002", "GSM122003", "GSM122004", "GSM122005", "GSM122006", "GSM122007", "GSM122008", "GSM122009", "GSM122010", "GSM122011", "GSM122012", "GSM122013", "GSM122014", "GSM122015", "GSM122016", "GSM122017", "GSM122018", "GSM122019", "GSM122020", "GSM122021", "GSM122022", "GSM122023", "GSM122024", "GSM122025", "GSM122026", "GSM122027", "GSM122028", "GSM122029"], "sample_count": 341, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "A Precisely Regulated Gene Expression Cassette Potently Modulates Metastasis and Survival in Multiple Solid Cancers", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE58545", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE58545", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58545", "version": null, "note": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1413225", "GSM1413226", "GSM1413227", "GSM1413228", "GSM1413229", "GSM1413230", "GSM1413231", "GSM1413232", "GSM1413233", "GSM1413234", "GSM1413235", "GSM1413236", "GSM1413237", "GSM1413238", "GSM1413239", "GSM1413240", "GSM1413241", "GSM1413242", "GSM1413243", "GSM1413244", "GSM1413245", "GSM1413246", "GSM1413247", "GSM1413248", "GSM1413249", "GSM1413250", "GSM1413251", "GSM1413252", "GSM1413253", "GSM1413254", "GSM1413255", "GSM1413256", "GSM1413257", "GSM1413258", "GSM1413259", "GSM1413260", "GSM1413261", "GSM1413262", "GSM1413263", "GSM1413264", "GSM1413265", "GSM1413266", "GSM1413267", "GSM1413268", "GSM1413269"], "sample_count": 45, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression signature associated with BRAFV600E mutation in human papillary thyroid carcinoma based on transgenic mouse model (human)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33193087:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:be303dbc1f184feb092693a0ae15625bcc42184c801e6c67f6576ef57fe85201", "bytes": 5612, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T1", "version": null, "note": "Immune cells in the PTC microenvironment.", "structure": {"pmcid": "PMC7642595", "section_index": 17, "section_title": "Increased Proportion of Tumor-Promoting Immune Cells in PTC", "row_count": 41, "column_count": 3}, "table": {"label": "Table 1", "caption": "Immune cells in the PTC microenvironment.", "rows": [["Immune cells", "Reported data", "References"], ["B cells", "• In DTCs, B cells were positively correlated with reduced tumor sizes.", "(26)"], ["TAMs", "• Macrophages are present in the immune environment of PTC and are significantly elevated in the BRAF V600E+ group.", "(27)"], ["• The density of macrophages in PTC tissues is significantly higher than that in normal tissues.", "(28, 29),"], ["• Compared with thyroid goiter and follicular adenoma, PTC tumors have significantly higher TAM densities.", "(30)"], ["• The expression of DCs MCs and macrophages in follicular variant of PTC (FVPTC) is higher than that in adenomas and may be involved in tumor development and invasion.", "(31)"], ["• TAM density is positively correlated with PTC stage, tumor size, lymph node metastasis, and distant metastases.", "(24, 29, 30, 32, 33)"], ["• In diffuse sclerosing variants of PTC (DSV-PTC), M2 TAMs are associated with lymphatic invasion.", "(34)"], ["• CXCL16 signaling mediates the effect of macrophages on PTC tumor cell invasion and changes the macrophage phenotype to M2 TAMs in the PTC microenvironment.", "(35)"], ["• In DTCs, TAMs are positively correlated with reduced tumor sizes and a favorable prognosis.", "(26)"], ["", "• High TAM density in PTC is associated with poor survival.", "(28)"], ["DCs", "• DCs are higher in papillary cancer tissues than in normal thyroid tissues, adenomas and other thyroid tumors.", "(36–31)"], ["• Immature DCs (iDCs) in PTC are difficult to induce T cell and NK cell-mediated responses, and they can even suppress immune responses by producing suppressive cytokines such as IL-10 and TGF-β.", "(37)"], ["• Tregs and pDCs together help tumor escape in patients with PTC plus nontoxic goiter (MNG).", "(38)"], ["• The expression of DCs, MCs, and macrophages in FVPTC is higher than that in adenomas and may be involved in tumor development and invasion.", "(31)"], ["• High CD1a+ DC density is associated with improved disease-free survival (DFS) of PTC.", "(39)"], ["• There is no significant correlation between DC density and DFS.", "(36)"], ["• DC immunotherapy can be used in patients with papillary or follicular TC without significant side effects.", "(40)"], ["MCs", "• MCs are recruited into PTC and promote the proliferation, survival and invasion of cancer cells, thereby promoting the growth and aggressiveness of PTC.", "(41)"], ["• Increased MC density in TC correlates with increased aggressiveness.", "(42)"], ["Neutrophils", "• NLR is not significantly increased in patients with PTC.", "(43)"], ["• NLR significantly increased in papillary thyroid microcarcinoma (PTMC) and TC patients.", "(44)"], ["• TC cells can recruit neutrophils by releasing CXCL8/IL-8. Additionally, in human TC samples, neutrophil density is related to tumor size and has a potential tumor-promoting effect.", "(45)"], ["• Elevated neutrophils in PTC can predict bilaterality and lymph node metastasis.", "(46)"], ["• Elevated NLR does not appear to be a reliable indicator of DTC progression.", "(47)"], ["• With the increase in the NLR value of PTC, the histopathological characteristics become worse and the clinical behavior becomes more aggressive.", "(48–49)"], ["• There is no significant association between preoperative NLR and prognostic factors in patients with PTC.", "(48, 50),"], ["• Elevated NLR is associated with a high risk of relapse. After treatment, those patients with low stage and good prognosis of DTC were observed to have a significant decrease in NLR.", "(51–53),"], ["• Higher NLR is associated with higher thyroglobulin levels in DTC, which indicates poorer survival.", "(54)"], ["NK cells", "• Compared with goiter and healthy thyroid, tumor-infiltrating NK cells increase in PTC, while no differences are found in peripheral blood NK cells.", "(55–57),"], ["• In PTC patients, NK cell infiltration is inversely related to the stage of the disease and plays a role of immune surveillance center by killing cancer cells.", "(56, 58–60),"], ["T cells", "• In PTC, CD8+ T cells kill tumor cells through cytotoxicity and are negatively related to tumor size and lymph node metastasis.", "(26, 60–62),"], ["• In PTC patients, CD8+ T cell infiltration is positively correlated with better prognosis.", "(26, 62, 63),"], ["• A study in patients with DTC showed that the combination of CD8+ cells enrichment and Cox-2 overexpression correlates with the highest risk of disease recurrence.", "(64)"], ["• In human PTC, lymphocyte density is associated with improved overall survival and reduced relapse.", "(65, 66),"], ["• In terms of CD4+ cell frequency, no difference was found between PTC and MNG patients.", "(38)"], ["• In DTC, the extent of tumor-infiltrating CD4+ cells does not seem to predict the patient’s prognosis.", "(64)"], ["• Compared with patients with thyroid adenoma, PTC patients have significantly increased CD4+ CD25+ regulatory T cells in the peripheral blood.", "(67)"], ["• Increased Treg infiltration is positively correlated with advanced PTC.", "(58–68)"], ["• FoxP3 expression in PTC is associated with extrathyroidal invasion and distant metastasis but has nothing to do with overall survival.", "(69)"], ["• Compared with healthy controls, Th17 levels in the peripheral blood and tissue samples of patients with PTC increased, and Th17 cells in the peripheral blood were negatively correlated with tumor size.", "(70)"]], "row_count": 41, "column_count": 3, "numeric_cells": 47, "header_rows": 1, "locator": "section[17]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33193087:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7ed51c09c4f0f456b16662fdaa0f4339ad746c7774c946a436a792bfbad8ec15", "bytes": 1653, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#T2", "version": null, "note": "Comparison of the clinical parameters between the H-immunity and L-immunity groups in PTC.", "structure": {"pmcid": "PMC7642595", "section_index": 22, "section_title": "Comparison of Clinical Characteristics Between the H-Immunity and L-Immunity Groups", "row_count": 44, "column_count": 4}, "table": {"label": "Table 2", "caption": "Comparison of the clinical parameters between the H-immunity and L-immunity groups in PTC.", "rows": [["Clinical parameters", "H-immunity (n = 293, %)", "L-immunity (n = 209, %)", "p-value"], ["Age (y)", "", "", ""], ["<55", "199 (67.9)", "136 (65.1)", "0.505"], ["≥55", "94 (32.1)", "73 (34.9)"], ["Gender", "", "", ""], ["Female", "215 (73.4)", "152 (72.7)", "0.871"], ["Male", "78 (26.6)", "57 (27.3)"], ["Stage", "", "", ""], ["I", "161 (54.9)", "120 (58.0)", "0.001"], ["II", "19 (6.5)", "33 (15.9)"], ["III", "76 (25.9)", "36 (17.4)"], ["IV", "37 (12.6)", "18 (8.7)"], ["NA", "0", "2", ""], ["Metastasis", "", "", ""], ["M0", "184 (97.9)", "98 (95.1)", "0.199"], ["M1", "4 (2.1)", "5 (4.9)"], ["NA", "105", "106", ""], ["N classification", "", "", ""], ["N0", "123 (43.9)", "106 (61.6)", "<0.001"], ["N1", "157 (56.1)", "66 (38.4)"], ["NA", "13", "37", ""], ["T classification", "", "", ""], ["T1", "87 (29.8)", "56 (26.9)", "0.018"], ["T2", "80 (27.4)", "84 (40.4)"], ["T3", "109 (37.3)", "61 (29.3)"], ["T4", "16 (5.5)", "7 (3.4)"], ["NA", "1", "1", ""], ["Radiation therapy", "", "", ""], ["Yes", "175 (62.7)", "130 (64.0)", "0.767"], ["No", "104 (37.3)", "73 (36.0)"], ["NA", "14", "6", ""], ["Pathological type", "", "", ""], ["Classical", "231 (78.8)", "125 (59.8)", "<0.001"], ["Follicular", "23 (7.8)", "78 (37.3)"], ["Tall cell", "35 (11.9)", "1 (0.5)"], ["Other", "4 (1.4)", "5 (2.4)"], ["BRAF", "", "", ""], ["Wild-type", "63 (22.4)", "132 (65.7)", "<0.001"], ["Mutated", "218 (77.6)", "69 (34.3)"], ["NA", "12", "8", ""], ["RAS", "", "", ""], ["Wild-type", "275 (97.9)", "147 (73.1)", "<0.001"], ["Mutated", "6 (2.1)", "54 (26.9)"], ["NA", "12", "8", ""]], "row_count": 44, "column_count": 4, "numeric_cells": 80, "header_rows": 1, "locator": "section[22]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:GSE27155 not downloaded", "asset:data:geo:GSE27155 licence not read", "asset:data:geo:GSE33630 not downloaded", "asset:data:geo:GSE33630 licence not read", "asset:data:geo:GSE3467 not downloaded", "asset:data:geo:GSE3467 licence not read", "asset:data:geo:GSE3678 not downloaded", "asset:data:geo:GSE3678 licence not read", "asset:data:geo:GSE50901 not downloaded", "asset:data:geo:GSE50901 licence not read", "asset:data:geo:GSE53157 not downloaded", "asset:data:geo:GSE53157 licence not read", "asset:data:geo:GSE5364 not downloaded", "asset:data:geo:GSE5364 licence not read", "asset:data:geo:GSE58545 not downloaded", "asset:data:geo:GSE58545 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "mann_whitney", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Mann-Whitney"}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-3", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "principal component analysis"}}, {"id": "method-4", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-5", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-6", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "chi-square"}}], "targets": [], "gaps": ["method.group_comparison_mann_whitney"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: mann_whitney."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE3467", "GSE3678", "GSE5364", "GSE27155", "GSE33630", "GSE50901", "GSE53157", "GSE58545", "and GSE60542"], "resolved_accessions": ["GSE3467", "GSE3678", "GSE5364", "GSE27155", "GSE33630", "GSE50901", "GSE53157", "GSE58545"], "statements": ["The original contributions presented in the study are included in the article/ Supplementary Materials , further inquiries can be directed to the corresponding author/s."], "basis": "The paper names GSE3467, GSE3678, GSE5364, GSE27155, GSE33630, GSE50901, GSE53157, GSE58545 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33193087", "data:geo:GSE27155", "asset:table:pmid:33193087:1", "asset:table:pmid:33193087:2"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_mann_whitney", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE27155"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:15:42Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 51435, "completion_tokens": 1951, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:33193087", "type": "paper", "label": "pmid:33193087"}, {"id": "source:pmid:33193087", "type": "manuscript", "label": "PMID 33193087 full text"}, {"id": "data:geo:GSE27155", "type": "dataset", "label": "GEO GSE27155"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33193087", "type": "paper", "label": "pmid:33193087"}, {"id": "source:pmid:33193087", "type": "manuscript", "label": "PMID 33193087 full text"}, {"id": "data:geo:GSE27155", "type": "dataset", "label": "GEO GSE27155"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33193087", "type": "extraction", "used": ["source:pmid:33193087"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE27155", "type": "accession_resolution", "used": ["data:geo:GSE27155"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:33193087", "parent_hash": "sha256:ef5259924577c30ecf72106ee02de7bc630dd9a8252f9444a1c78688d733560f", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE27155 licence not read", "asset:data:geo:GSE27155 not downloaded", "asset:data:geo:GSE33630 licence not read", "asset:data:geo:GSE33630 not downloaded", "asset:data:geo:GSE3467 licence not read", "asset:data:geo:GSE3467 not downloaded", "asset:data:geo:GSE3678 licence not read", "asset:data:geo:GSE3678 not downloaded", "asset:data:geo:GSE50901 licence not read", "asset:data:geo:GSE50901 not downloaded", "asset:data:geo:GSE53157 licence not read", "asset:data:geo:GSE53157 not downloaded", "asset:data:geo:GSE5364 licence not read", "asset:data:geo:GSE5364 not downloaded", "asset:data:geo:GSE58545 licence not read", "asset:data:geo:GSE58545 not downloaded", "execution.not_run", "method.group_comparison_mann_whitney", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_mann_whitney"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Materials and Methods Materials The RNA-seq data (level-three, FPKM) of the thyroid carc"], "order_basis": "paper_text_order:2518", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["(https://xena.ucsc.edu/). The other nine PTC microarray datasets were downloaded from the Gene Expre"], "order_basis": "paper_text_order:2891", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Mann-Whitney"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:43:57+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}