{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33161156", "kind": "science-record", "revision": 7, "content_hash": "sha256:52a1a7b373c1e42a480452130c24de7b3cb302b196f50a197d1163852baeb1ec", "created_at": "2026-11-01T15:41:15Z", "updated_at": "2026-11-01T21:24:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Inflammation-Associated Senescence Promotes Helicobacter pylori-Induced Atrophic Gastritis.", "doi": "10.1016/j.jcmgh.2020.10.015", "pmid": "33161156", "authors": ["Qinbo Cai", "Peng Shi", "Yujie Yuan", "Jianjun Peng", "Xinde Ou", "Wen Zhou", "Jin Li", "Taiqiang Su", "Liangliang Lin", "Shirong Cai", "Yulong He", "Jianbo Xu"], "journal": "Cellular and molecular gastroenterology and hepatology", "year": 2021, "abstract": "BACKGROUND & AIMS: The association between cellular senescence and Helicobacter pylori-induced atrophic gastritis is not clear. Here, we explore the role of cellular senescence in H pylori-induced atrophic gastritis and the underlying mechanism.\nMETHODS: C57BL/6J mice were infected with H pylori for biological and mechanistic studies in vivo. Gastric precancerous lesions from patients and mouse models were collected and analyzed using senescence-associated beta-galactosidase, Sudan Black B, and immunohistochemical staining to analyze senescent cells, signaling pathways, and H pylori infection. Chromatin immunoprecipitation, luciferase reporter assays, and other techniques were used to explore the underlying mechanism in vitro.\nRESULTS: Gastric mucosa atrophy was highly associated with cellular senescence. H pylori promoted gastric epithelial cell senescence in vitro and in vivo in a manner that depended on C-X-C motif chemokine receptor 2 (CXCR2) signaling. Interestingly, H pylori infection not only up-regulated the expression of CXCR2 ligands, C-X-C motif chemokine ligands 1 and 8, but also transcriptionally up-regulated the expression of CXCR2 via the nuclear factor-κB subunit 1 directly. In addition, CXCR2 formed a positive feedback loop with p53 to continually enhance senescence. Pharmaceutical inhibition of CXCR2 in an H pylori-infected mouse model attenuated mucosal senescence and atrophy, and delayed further precancerous lesion progression.\nCONCLUSIONS: Our study showed a new mechanism of H pylori-induced atrophic gastritis through CXCR2-mediated cellular senescence. Inhibition of CXCR2 signaling is suggested as a potential preventive therapy for targeting H pylori-induced atrophic gastritis. GEO data set accession numbers: GSE47797 and GSE3556.", "claims": [{"id": "claim-method", "statement": "Data were analyzed using GSEA.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33161156", "locator": "sections[28] \"GEO Data Analysis and Transcription Factor Prediction\" paragraph 2", "quote": "Data were analyzed using GSEA."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33161156", "locator": "sections[7] \"H pylori Promotes Senescence in Gastric Mucosa via CXCR2 Signaling\" paragraph 3", "quote": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:33161156"], "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:GSE3556"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "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:GSE3556"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33161156", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.jcmgh.2020.10.015", "sha256": "sha256:64bb7266d23d5512d9c1922d5df5ed930ee914fd1672c2adafdc72c43b6bdc90", "bytes": 81324, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.jcmgh.2020.10.015", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7859172", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE3556", "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=GSE3556", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3556", "version": null, "note": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM81696", "GSM81697", "GSM81698", "GSM81699", "GSM81700", "GSM81701", "GSM81702", "GSM81703", "GSM81704", "GSM81705", "GSM81706", "GSM81707", "GSM81708", "GSM81709", "GSM81710", "GSM81711", "GSM81712", "GSM81713", "GSM81714", "GSM81715", "GSM81716", "GSM81717", "GSM81718", "GSM81719", "GSM81720", "GSM81721", "GSM81722", "GSM81723", "GSM81724", "GSM81725", "GSM81726", "GSM81727", "GSM81728", "GSM81729", "GSM81730", "GSM81731", "GSM81732", "GSM81733", "GSM81734", "GSM81735", "GSM81736", "GSM81737", "GSM81738", "GSM81739", "GSM81740", "GSM81741", "GSM81742", "GSM81743", "GSM81744", "GSM81745", "GSM81746", "GSM81747", "GSM81748", "GSM81749"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "3002;3011;178;2935", "taxon": "Homo sapiens", "title": "Cag pathogenicity island-specific responses of gastric epithelial cells to Helicobacter pylori infection.", "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:GSE47797", "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=GSE47797", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE47797", "version": null, "note": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1159807", "GSM1159808", "GSM1159809", "GSM1159810", "GSM1159811", "GSM1159812", "GSM1159813", "GSM1159814", "GSM1159815", "GSM1159816", "GSM1159817", "GSM1159818", "GSM1159819", "GSM1159820", "GSM1159821", "GSM1159822", "GSM1484286", "GSM1484287", "GSM1484288", "GSM1484289", "GSM1484290", "GSM1484291", "GSM1484292", "GSM1484293"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "17077;13497", "taxon": "Homo sapiens", "title": "Effect of Helicobacter pylori on ATM-dependent DNA damage responses", "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:GSE65458", "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=GSE65458", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65458", "version": null, "note": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1597988", "GSM1597989", "GSM1597990", "GSM1597991", "GSM1597992", "GSM1597993", "GSM1597994", "GSM1597995", "GSM1597996", "GSM1597997", "GSM1597998", "GSM1597999", "GSM1598000", "GSM1598001", "GSM1598002", "GSM1598003", "GSM1598004", "GSM1598005", "GSM1598006", "GSM1598007", "GSM1598008", "GSM1598009", "GSM1598010", "GSM1598011"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Proteasome machinery is instrumental in a common gain-of-function program of the p53 missense mutants in cancer.", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33161156:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e4569a2a1f2691cfcb1161387ea228b2ddd92a562fa9d8d30cf43f1fbebf2628", "bytes": 1335, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#tbl4", "version": null, "note": "Primers Used for Quantitative Real-Time PCR", "structure": {"pmcid": "PMC7859172", "section_index": 18, "section_title": "Lentiviral Transduction, Plasmid Transfection, and RNA Interference", "row_count": 37, "column_count": 2}, "table": {"label": "Table 4", "caption": "Primers Used for Quantitative Real-Time PCR", "rows": [["Gene (protein name)", "Primer sequence"], ["CXCR2 (CXCR2)", ""], ["Forward", "CCTGTCTTACTTTTCCGAAGGAC"], ["Reverse", "TTGCTGTATTGTTGCCCATGT"], ["CXCL1 (CXCL1)", ""], ["Forward", "ATTCACCCCAAGAACATCCA"], ["Reverse", "GATGCAGGATTGAGGCAAG"], ["CXCL8 (CXCL8)", ""], ["Forward", "ACTGAGAGTGATTGAGAGTGGAC"], ["Reverse", "AACCCTCTGCACCCAGTTTTC"], ["TP53 (p53)", ""], ["Forward", "GAGGTTGGCTCTGACTGTACC"], ["Reverse", "TCCGTCCCAGTAGATTACCAC"], ["CDKN1A (p21)", ""], ["Forward", "TGTCCGTCAGAACCCATGC"], ["Reverse", "AAAGTCGAAGTTCCATCGCTC"], ["CDKN2A (p16)", ""], ["Forward", "ATGGAGCCTTCGGCTGACT"], ["Reverse", "GTAACTATTCGGTGCGTTGGG"], ["CDKN1B (p27)", ""], ["Forward", "ATCACAAACCCCTAGAGGGCA"], ["Reverse", "GGGTCTGTAGTAGAACTCGGG"], ["RB1 (Rb)", ""], ["Forward", "CACTTTGTGAACGCCTTCTGT"], ["Reverse", "CACGTTTGAATGTCTCCTGAACA"], ["GAPDH (GAPDH)", ""], ["Forward", "ACAACTTTGGTATCGTGGAAGG"], ["Reverse", "GCCATCACGCCACAGTTTC"], ["Cxcr2 (Cxcr2)", ""], ["Forward", "ATGCCCTCTATTCTGCCAGAT"], ["Reverse", "GTGCTCCGGTTGTATAAGATGAC"], ["Cxcl1 (Cxcl1)", ""], ["Forward", "CTGGGATTCACCTCAAGAACATC"], ["Reverse", "CAGGGTCAAGGCAAGCCTC"], ["Gapdh (Gapdh)", ""], ["Forward", "GAACGGGAAGCTCACTGG"], ["Reverse", "GCCTGCTTCACCACCTTCT"]], "row_count": 37, "column_count": 2, "numeric_cells": 4, "header_rows": 1, "locator": "section[18]/table-wrap[1]#tbl4"}}, {"id": "asset:table:pmid:33161156:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e7f76e03c6c5d72d5114efb6e1ae0d529984a3d219be096cd726a470fdbb9e64", "bytes": 609, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#tbl1", "version": null, "note": "siRNA Information", "structure": {"pmcid": "PMC7859172", "section_index": 21, "section_title": "Quantitative Real-Time PCR", "row_count": 13, "column_count": 2}, "table": {"label": "Table 1", "caption": "siRNA Information", "rows": [["Target gene", "Sequence"], ["CXCR2-#1", "GCTACTTGGTCAAATTCAT"], ["CXCR2-#2", "GCTATACATGGCTTGATCAGC"], ["MEF2A-#1", "GCTCAACGTTAACAGATTC"], ["MEF2A-#2", "GAAACCAGATCTTCGAGTT"], ["CEBPB-#1", "GCCCTGAGTAATCGCTTAA"], ["CEBPB-#2", "GTGGCCAACTTCTACTACG"], ["YY1-#1", "CGACGACTACATTGAACAA"], ["YY1-#2", "CCTGAAATCTCACATCTTA"], ["VDR-#1", "GTCAGTTACAGCATCCAAA"], ["VDR-#2", "CCCACCATAAGACCTACGA"], ["TP53-#1", "GAGAAUAUUUCACCCUUAA"], ["TP53-#2", "UGGUUCACUGAAGACCCAGUU"]], "row_count": 13, "column_count": 2, "numeric_cells": 12, "header_rows": 1, "locator": "section[21]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:33161156:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:eca17485163c28879ecf562497c44f9f3f40ad50e2777282cec48c069addd5c6", "bytes": 1493, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#tbl2", "version": null, "note": "Antibody Information", "structure": {"pmcid": "PMC7859172", "section_index": 22, "section_title": "IHC Analysis", "row_count": 31, "column_count": 3}, "table": {"label": "Table 2", "caption": "Antibody Information", "rows": [["Antibody", "Final dilution", "Manufacturer and cat no"], ["p53", "Western blot (WB) 1:4000, IHC 1:1500", "Abcam ab1101, CA"], ["p-p53(Ser15)", "WB 1:500", "Abcam ab1431"], ["p-p53(Ser392)", "WB 1:500", "CST 9281, Danvers, MA"], ["p21", "WB 1:1000, IHC 1:100", "CST 2947"], ["p21", "IHC 1:100", "Abclone A2691, Wuhan, China"], ["Anti–H pylori", "IHC 1:200", "ZSGB-BIO ZA-0127, Beijing, China"], ["CagA", "WB 1:500", "GeneTex GTX42382, CA"], ["BrdU", "Immunofluorescence (IF) 1:250", "Abcam ab6326"], ["CXCR2", "WB 1:500", "Abcam ab65968"], ["CXCR2", "IHC 1:100", "Abcam ab14935"], ["Cxcl1", "IHC 1:100", "Santa Cruz sc-365870, CA"], ["β-tubulin", "WB 1:1000", "CST 2128"], ["γH2AX", "IHC 1:100", "Abcam ab26350"], ["GAPDH", "WB 1:2000", "JETWAY SF-PA005, Guangzhou, China"], ["IKK", "WB 1:1000", "CST 8943"], ["pIKK", "WB 1:1000", "CST 2697"], ["IKBα", "WB 1:1000", "CST 4814"], ["pIKBα (Ser32)", "WB 1:1000", "CST 2859"], ["RELA", "WB 1:1000", "CST 8242"], ["p-RELA (Ser536)", "WB 1:500", "CST 3037"], ["NFKB1", "WB 1:1000", "CST 13586"], ["STAT1", "WB 1:1000", "CST 1499"], ["pSTAT1(Tyr701)", "WB 1:500", "CST 7649"], ["MEF2A", "WB 1:2000", "Abcam ab76063"], ["CEBPB", "WB 1:1000", "Abcam ab32358"], ["YY1", "WB 1:1000", "Abcam ab109228"], ["VDR", "WB 1:1000", "Abcam ab109234"], ["Erk", "WB 1:1000", "CST 46953"], ["pErk (Thr202/Tyr204)", "WB 1:2000", "CST 4370"], ["Cyclin D1", "WB 1:1000", "CST 2978"]], "row_count": 31, "column_count": 3, "numeric_cells": 69, "header_rows": 1, "locator": "section[22]/table-wrap[1]#tbl2"}}, {"id": "asset:table:pmid:33161156:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5e5fe297ee3c708fbeca40376780a71265556b29f0c29bfeedf8b4d34b0993c5", "bytes": 642, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[27]/table-wrap[1]#tbl3", "version": null, "note": "Primers Used in ChIP", "structure": {"pmcid": "PMC7859172", "section_index": 27, "section_title": "ChIP", "row_count": 16, "column_count": 2}, "table": {"label": "Table 3", "caption": "Primers Used in ChIP", "rows": [["Gene", "Primer sequence"], ["ChIP-NFKB1-RE1", ""], ["Forward", "CATCAATGCTGCGTTCCT"], ["Reverse", "TCTGGTATTGTGAAGGGTC"], ["ChIP-NFKB1-RE2", ""], ["Forward", "CTCTAAGACCCTTCACAATAC"], ["Reverse", "GAATACCCTGTGGAACAAA"], ["ChIP-NFKB1-RE3", ""], ["Forward", "TCCAGAAGCCATCAGACA"], ["Reverse", "GGGAGGTATTCCCACAGA"], ["ChIP-TP53-RE1", ""], ["Forward", "CGTGCGAGTTCAGACAAG"], ["Reverse", "TGGAGGAGCCTACCAGTC"], ["ChIP-TP53-RE2", ""], ["Forward", "CTAAGACCCTTCACAATACC"], ["Reverse", "AATACCCTGTGGAACAAA"]], "row_count": 16, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[27]/table-wrap[1]#tbl3"}}], "gaps": ["asset:data:geo:GSE3556 not downloaded", "asset:data:geo:GSE3556 licence not read", "asset:data:geo:GSE47797 not downloaded", "asset:data:geo:GSE47797 licence not read", "asset:data:geo:GSE65458 not downloaded", "asset:data:geo:GSE65458 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Gene set enrichment analysis (GSEA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Data were analyzed using GSEA."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Gene set enrichment analysis (GSEA)), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE47797", "GSE3556", "GSE65458"], "resolved_accessions": ["GSE47797", "GSE3556", "GSE65458"], "statements": ["GSEA of senescence-associated pathways in H pylori infection using GSE47797 (human samples with H pylori–associated gastritis) and GSE3556 (AGS cell line infected with wild-type H pylori G27, which is CagA positive) from the GEO data set."], "basis": "The paper names GSE47797, GSE3556, GSE65458 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:33161156", "data:geo:GSE3556", "asset:table:pmid:33161156:1", "asset:table:pmid:33161156:2", "asset:table:pmid:33161156:3", "asset:table:pmid:33161156:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE3556"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:00Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 63233, "completion_tokens": 1375, "cached_tokens": 791}}, "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:33161156", "type": "paper", "label": "pmid:33161156"}, {"id": "source:pmid:33161156", "type": "manuscript", "label": "PMID 33161156 full text"}, {"id": "data:geo:GSE3556", "type": "dataset", "label": "GEO GSE3556"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33161156", "type": "paper", "label": "pmid:33161156"}, {"id": "source:pmid:33161156", "type": "manuscript", "label": "PMID 33161156 full text"}, {"id": "data:geo:GSE3556", "type": "dataset", "label": "GEO GSE3556"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33161156", "type": "extraction", "used": ["source:pmid:33161156"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE3556", "type": "accession_resolution", "used": ["data:geo:GSE3556"], "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:33161156", "parent_hash": "sha256:296a50f6fe0960696711fe1978f571101f162d84a40b58427e8c8153d2493d72", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE3556 licence not read", "asset:data:geo:GSE3556 not downloaded", "asset:data:geo:GSE47797 licence not read", "asset:data:geo:GSE47797 not downloaded", "asset:data:geo:GSE65458 licence not read", "asset:data:geo:GSE65458 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["the underlying mechanism. METHODS: C57BL/6J mice were infected with H pylori for biological and me", "inhibition of CXCR2 in an H pylori-infected mouse model attenuated mucosal senescence and atrophy, a", "ylori for biological and mechanistic studies in vivo. Gastric precancerous lesions from patients", "tric epithelial cell senescence in vitro and in vivo in a manner that depended on C-X-C motif che"], "order_basis": "paper_text_order:312", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["iated beta-galactosidase, Sudan Black B, and immunohistochemical staining to analyze senescent cells, signali"], "order_basis": "paper_text_order:547", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["was given to the control group. H pylori was cultured in Brucella Agar (Hopebio, Shandong, China) wit"], "order_basis": "paper_text_order:7717", "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":"2026-11-04T02:51:20+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}}}