{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34557356", "kind": "science-record", "revision": 7, "content_hash": "sha256:a80b60a8c4bae7b49187a2573c47ec40f8a8b13145517b8ae9035548dbe467f8", "created_at": "2026-11-01T15:41:53Z", "updated_at": "2026-11-01T22:04:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Expression and prognosis of CDC45 in cervical cancer based on the GEO database.", "doi": "10.7717/peerj.12114", "pmid": "34557356", "authors": ["Zikang He", "Xiaojin Wang", "Zhiming Yang", "Ying Jiang", "Luhui Li", "Xingyun Wang", "Zheyao Song", "Xiuli Wang", "Jiahui Wan", "Shijun Jiang", "Naiwen Zhang", "Rongjun Cui"], "journal": "PeerJ", "year": 2021, "abstract": "Cervical cancer is one of the most common malignant tumors in women, and its morbidity and mortality are increasing year by year worldwide. Therefore, an urgent and challenging task is to identify potential biomarkers for cervical cancer. This study aims to identify the hub genes based on the GEO database and then validate their prognostic values in cervical cancer by multiple databases. By analysis, we obtained 83 co-expressed differential genes from the GEO database (GSE63514, GSE67522 and GSE39001). GO and KEGG enrichment analysis showed that these 83 co-expressed it mainly involved differential genes in DNA replication, cell division, cell cycle, etc.. The PPI network was constructed and top 10 genes with protein-protein interaction were selected. Then, we validated ten genes using some databases such as TCGA, GTEx and oncomine. Survival analysis demonstrated significant differences in CDC45, RFC4, TOP2A. Differential expression analysis showed that these genes were highly expressed in cervical cancer tissues. Furthermore, univariate and multivariate cox regression analysis indicated that CDC45 and clinical stage IV were independent prognostic factors for cervical cancer. In addition, the HPA database validated the protein expression level of CDC45 in cervical cancer. Further studies investigated the relationship between CDC45 and tumor-infiltrating immune cells via CIBERSORT. Finally, gene set enrichment analysis (GSEA) showed CDC45 related genes were mainly enriched in cell cycle, chromosome, catalytic activity acting on DNA, etc. These results suggested CDC45 may be a potential biomarker associated with the prognosis of cervical cancer.", "claims": [{"id": "claim-method", "statement": "The differentially expressed genes (DEGs) between cancer tissues and non-cancerous tissues were screened out using GEO2R (Davis & Meltzer, 2007) (http://www.ncbi.nlm.nih.gov/geo/geo2r).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34557356", "locator": "sections[3] \"Data collection and data processing\" paragraph 3", "quote": "The differentially expressed genes (DEGs) between cancer tissues and non-cancerous tissues were screened out using GEO2R (Davis & Meltzer, 2007) (http://www.ncbi.nlm.nih.gov/geo/geo2r)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34557356", "locator": "sections[35] \"Data Availability Statement\" paragraphs 1-4", "quote": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request."}], "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:34557356"], "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:GSE39001"], "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:GSE39001"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34557356", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.12114", "sha256": "sha256:effb3728dea5e8581713ea3dbe913ca308c311fcff60fd93032dad7f007b4685", "bytes": 49315, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.12114", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8420875", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE39001", "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=GSE39001", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE39001", "version": null, "note": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM953492", "GSM953493", "GSM953494", "GSM953495", "GSM953496", "GSM953497", "GSM953498", "GSM953499", "GSM953500", "GSM953501", "GSM953502", "GSM953503", "GSM953504", "GSM953505", "GSM953506", "GSM953507", "GSM953508", "GSM953509", "GSM953510", "GSM953511", "GSM953512", "GSM953513", "GSM953514", "GSM953515", "GSM953516", "GSM953517", "GSM953518", "GSM953519", "GSM953520", "GSM953521", "GSM953522", "GSM953523", "GSM953524", "GSM953525", "GSM953526", "GSM953527", "GSM953528", "GSM953529", "GSM953530", "GSM953531", "GSM953532", "GSM953533", "GSM953534", "GSM953535", "GSM953536", "GSM953537", "GSM953538", "GSM953539", "GSM953540", "GSM953541", "GSM953542", "GSM953543", "GSM953544", "GSM953545", "GSM953546", "GSM953547", "GSM953548", "GSM953549", "GSM953550", "GSM953551", "GSM953552", "GSM953553", "GSM953554", "GSM953555", "GSM953556", "GSM953557", "GSM953558", "GSM953559", "GSM953560", "GSM953561", "GSM953562", "GSM953563", "GSM953564", "GSM953565", "GSM953566", "GSM953567", "GSM953568", "GSM953569", "GSM953570"], "sample_count": 79, "group_sizes": null, "group_sizes_basis": null, "platform": "201;6244", "taxon": "Homo sapiens", "title": "Mitosis is the main pathway altered in cervical cancer and is a source of potential markers for screening and survival, and therapeutic targets.", "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:GSE52903", "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=GSE52903", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE52903", "version": null, "note": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1277835", "GSM1277836", "GSM1277837", "GSM1277838", "GSM1277839", "GSM1277840", "GSM1277841", "GSM1277842", "GSM1277843", "GSM1277844", "GSM1277845", "GSM1277846", "GSM1277847", "GSM1277848", "GSM1277849", "GSM1277850", "GSM1277851", "GSM1277852", "GSM1277853", "GSM1277854", "GSM1277855", "GSM1277856", "GSM1277857", "GSM1277858", "GSM1277859", "GSM1277860", "GSM1277861", "GSM1277862", "GSM1277863", "GSM1277864", "GSM1277865", "GSM1277866", "GSM1277867", "GSM1277868", "GSM1277869", "GSM1277870", "GSM1277871", "GSM1277872", "GSM1277873", "GSM1277874", "GSM1277875", "GSM1277876", "GSM1277877", "GSM1277878", "GSM1277879", "GSM1277880", "GSM1277881", "GSM1277882", "GSM1277883", "GSM1277884", "GSM1277885", "GSM1277886", "GSM1277887", "GSM1277888", "GSM1277889", "GSM1277890", "GSM1277891", "GSM1277892", "GSM1277893", "GSM1277894", "GSM1277895", "GSM1277896", "GSM1277897", "GSM1277898", "GSM1277899", "GSM1277900", "GSM1277901", "GSM1277902", "GSM1277903", "GSM1277904", "GSM1277905", "GSM1277906"], "sample_count": 72, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene Dosage, Mainly 3q Amplification, Deregulates a Quarter of Genes in Cervical Cancer: It Induces Glycolysis, Anaphase-dependent Proteasome Proteolysis, and Low Survival", "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:GSE63514", "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=GSE63514", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE63514", "version": null, "note": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1551311", "GSM1551312", "GSM1551313", "GSM1551314", "GSM1551315", "GSM1551316", "GSM1551317", "GSM1551318", "GSM1551319", "GSM1551320", "GSM1551321", "GSM1551322", "GSM1551323", "GSM1551324", "GSM1551325", "GSM1551326", "GSM1551327", "GSM1551328", "GSM1551329", "GSM1551330", "GSM1551331", "GSM1551332", "GSM1551333", "GSM1551334", "GSM1551335", "GSM1551336", "GSM1551337", "GSM1551338", "GSM1551339", "GSM1551340", "GSM1551341", "GSM1551342", "GSM1551343", "GSM1551344", "GSM1551345", "GSM1551346", "GSM1551347", "GSM1551348", "GSM1551349", "GSM1551350", "GSM1551351", "GSM1551352", "GSM1551353", "GSM1551354", "GSM1551355", "GSM1551356", "GSM1551357", "GSM1551358", "GSM1551359", "GSM1551360", "GSM1551361", "GSM1551362", "GSM1551363", "GSM1551364", "GSM1551365", "GSM1551366", "GSM1551367", "GSM1551368", "GSM1551369", "GSM1551370", "GSM1551371", "GSM1551372", "GSM1551373", "GSM1551374", "GSM1551375", "GSM1551376", "GSM1551377", "GSM1551378", "GSM1551379", "GSM1551380", "GSM1551381", "GSM1551382", "GSM1551383", "GSM1551384", "GSM1551385", "GSM1551386", "GSM1551387", "GSM1551388", "GSM1551389", "GSM1551390", "GSM1551391", "GSM1551392", "GSM1551393", "GSM1551394", "GSM1551395", "GSM1551396", "GSM1551397", "GSM1551398", "GSM1551399", "GSM1551400", "GSM1551401", "GSM1551402", "GSM1551403", "GSM1551404", "GSM1551405", "GSM1551406", "GSM1551407", "GSM1551408", "GSM1551409", "GSM1551410", "GSM1551411", "GSM1551412", "GSM1551413", "GSM1551414", "GSM1551415", "GSM1551416", "GSM1551417", "GSM1551418", "GSM1551419", "GSM1551420", "GSM1551421", "GSM1551422", "GSM1551423", "GSM1551424", "GSM1551425", "GSM1551426", "GSM1551427", "GSM1551428", "GSM1551429", "GSM1551430", "GSM1551431", "GSM1551432", "GSM1551433", "GSM1551434", "GSM1551435", "GSM1551436", "GSM1551437", "GSM1551438"], "sample_count": 128, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of cervical cancer progression", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE67522", "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=GSE67522", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE67522", "version": null, "note": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1648707", "GSM1648708", "GSM1648709", "GSM1648710", "GSM1648711", "GSM1648712", "GSM1648713", "GSM1648714", "GSM1648715", "GSM1648716", "GSM1648717", "GSM1648718", "GSM1648719", "GSM1648720", "GSM1648721", "GSM1648722", "GSM1648723", "GSM1648724", "GSM1648725", "GSM1648726", "GSM1648727", "GSM1648728", "GSM1648729", "GSM1648730", "GSM1648731", "GSM1648732", "GSM1648733", "GSM1648734", "GSM1648735", "GSM1648736", "GSM1648737", "GSM1648738", "GSM1648739", "GSM1648740", "GSM1648741", "GSM1648742", "GSM1648743", "GSM1648744", "GSM1648745", "GSM1648746", "GSM1648747", "GSM1648748"], "sample_count": 42, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression to identify the probably functionally relevant pathways in cervical cancer progression", "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:34557356:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a415101118e68bc9f3c2bc761b230b932133cef34e0823b1bdacfeb468189b96", "bytes": 965, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#table-1", "version": null, "note": "Association with overall survival and clinicopathologic characteristic in TCGA patients using Cox regression analysis.", "structure": {"pmcid": "PMC8420875", "section_index": 16, "section_title": "Verification and analysis of Hub genes in multiple databases", "row_count": 19, "column_count": 3}, "table": {"label": "Table 1", "caption": "Association with overall survival and clinicopathologic characteristic in TCGA patients using Cox regression analysis.", "rows": [["Clinical characteristics", "HR (95%CI)", "P-val"], ["UniCOX", "", ""], ["Age", "1.02 [1.00–1.04]", "0.134"], ["Stage I", "Ref.", ""], ["Stage II", "0.66 [0.28–1.51]", "0.318"], ["Stage III", "1.24 [0.58–2.66]", "0.582"], ["Stage IV", "6.22 [2.87–13.48]", "<0.001***"], ["Grade 1", "Ref.", ""], ["Grade 2", "1.02 [0.24–4.34]", "0.973"], ["Grade 3", "1.00 [0.23–4.30]", "0.997"], ["CDC45", "0.93 [0.88–0.98]", "0.008**"], ["RFC4", "0.99 [0.96–1.01]", "0.203"], ["TOP2A", "1.00 [0.99–1.02]", "0.598"], ["MultiCOX", "", ""], ["Stage I", "Ref.", ""], ["Stage II", "0.59 [0.25–1.37]", "0.220"], ["Stage III", "1.12 [0.52–2.42]", "0.766"], ["Stage IV", "5.54 [2.55–12.04]", "<0.001***"], ["CDC45", "0.93 [0.88–0.98]", "0.012*"]], "row_count": 19, "column_count": 3, "numeric_cells": 32, "header_rows": 1, "locator": "section[16]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:34557356:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:04a0f80ae31278006c60d6198e6e4ce2c31c2894276dc10fc41086cb380bda08", "bytes": 1378, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#table-2", "version": null, "note": "Gene sets enriched in phenotype.", "structure": {"pmcid": "PMC8420875", "section_index": 21, "section_title": "Gene sets enriched in CDC45 expression phenotype", "row_count": 25, "column_count": 4}, "table": {"label": "Table 2", "caption": "Gene sets enriched in phenotype.", "rows": [["Gene set name", "NES", "NOM p-val", "FDR Q-val"], ["KEGG", "", "", ""], ["KEGG_PURINE_METABOLISM", "−2.178", "0", "6.14E−04"], ["KEGG_CELL_CYCLE", "−2.158", "0", "3.07E−04"], ["KEGG_OOCYTE_MEIOSIS", "−2.101", "0", "5.53E−04"], ["KEGG_PYRIMIDINE_METABOLISM", "−2.075", "0.002", "0.001"], ["KEGG_DNA_REPLICATION", "−2.067", "0", "8.28E−04"], ["GO_BP", "", "", ""], ["GO_CHROMOSOME", "−2.321", "0", "5.57E−04"], ["GO_NUCLEAR_CHROMOSOME", "−2.301", "0", "2.79E−04"], ["GO_CHROMOSOMAL_REGION", "−2.184", "0", "5.57E−04"], ["GO_CATALYTIC_COMPLEX", "−2.145", "0.002", "8.18E−04"], ["GO_MICROTUBULE_CYTOSKELETON", "−2.140", "0", "6.54E−04"], ["GO_CC", "", "", ""], ["GO_CELL_CYCLE", "−2.460", "0", "0"], ["GO_CELL_CYCLE_PROCESS", "−2.409", "0", "0"], ["GO_DNA_REPLICATION", "−2.375", "0", "0"], ["GO_DNA_METABOLIC_PROCESS", "−2.372", "0", "0"], ["GO_CELLULAR_RESPONSE_TO_DNA_DAMAGE_STIMULUS", "−2.369", "0", "0"], ["GO_MF", "", "", ""], ["GO_CATALYTIC_ACTIVITY_ACTING_ON_DNA", "−2.097", "0", "0.010"], ["GO_CHROMATIN_BINDING", "−2.093", "0", "0.005"], ["GO_UBIQUITIN_LIKE_PROTEIN_BINDING", "−2.092", "0", "0.003"], ["GO_ATPASE_ACTIVITY", "−2.091", "0", "0.002"], ["GO_HYDROLASE_ACTIVITY_ACTING_ON_ACID_ANHYDRIDES", "−2.085", "0", "0.002"]], "row_count": 25, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[21]/table-wrap[1]#table-2"}}], "gaps": ["asset:data:geo:GSE39001 not downloaded", "asset:data:geo:GSE39001 licence not read", "asset:data:geo:GSE52903 not downloaded", "asset:data:geo:GSE52903 licence not read", "asset:data:geo:GSE63514 not downloaded", "asset:data:geo:GSE63514 licence not read", "asset:data:geo:GSE67522 not downloaded", "asset:data:geo:GSE67522 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "cox regression"}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-3", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-4", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The differentially expressed genes (DEGs) between cancer tissues and non-cancerous tissues were screened out using GEO2R (Davis & Meltzer, 2007) (http://www.ncbi.nlm.nih.gov/geo/geo2r)."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE63514", "GSE67522", "GSE39001", "GSE52903"], "resolved_accessions": ["GSE63514", "GSE67522", "GSE39001", "GSE52903"], "statements": ["The following information was supplied regarding data availability:\nThe data is available at NCBI GEO: GSE63514, GSE67522, GSE39001, GSE52903.\nThe R code is available upon request."], "basis": "The paper names GSE63514, GSE67522, GSE39001, GSE52903 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:34557356", "data:geo:GSE39001", "asset:table:pmid:34557356:1", "asset:table:pmid:34557356:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE39001"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:35:05Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 40501, "completion_tokens": 2337, "cached_tokens": 792}}, "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:34557356", "type": "paper", "label": "pmid:34557356"}, {"id": "source:pmid:34557356", "type": "manuscript", "label": "PMID 34557356 full text"}, {"id": "data:geo:GSE39001", "type": "dataset", "label": "GEO GSE39001"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34557356", "type": "paper", "label": "pmid:34557356"}, {"id": "source:pmid:34557356", "type": "manuscript", "label": "PMID 34557356 full text"}, {"id": "data:geo:GSE39001", "type": "dataset", "label": "GEO GSE39001"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34557356", "type": "extraction", "used": ["source:pmid:34557356"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE39001", "type": "accession_resolution", "used": ["data:geo:GSE39001"], "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:34557356", "parent_hash": "sha256:c2fbe8c638413c053ecbe497ba2c23ad7073d00e7525529f5739bef4d0bb04f8", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE39001 licence not read", "asset:data:geo:GSE39001 not downloaded", "asset:data:geo:GSE52903 licence not read", "asset:data:geo:GSE52903 not downloaded", "asset:data:geo:GSE63514 licence not read", "asset:data:geo:GSE63514 not downloaded", "asset:data:geo:GSE67522 licence not read", "asset:data:geo:GSE67522 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["cox regression"], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T00:33:02+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}}}