{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35498426", "kind": "science-record", "revision": 4, "content_hash": "sha256:0235ebf492f5064ba31830c69a25a7ba045bad334446b41b82b1249cca10530c", "created_at": "2026-11-01T18:14:23Z", "updated_at": "2026-11-01T22:06:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification and Validation of a Prognostic Prediction Model in Diffuse Large B-Cell Lymphoma.", "doi": "10.3389/fendo.2022.846357", "pmid": "35498426", "authors": ["Jiaqin Yan", "Wei Yuan", "Junhui Zhang", "Ling Li", "Lei Zhang", "Xudong Zhang", "Mingzhi Zhang"], "journal": "Frontiers in endocrinology", "year": 2022, "abstract": "Background: Diffuse large B-cell lymphoma (DLBCL) is a heterogeneous group with varied pathophysiological, genetic, and clinical features, accounting for approximately one-third of all lymphoma cases worldwide. Notwithstanding that unprecedented scientific progress has been achieved over the years, the survival of DLBCL patients remains low, emphasizing the need to develop novel prognostic biomarkers for early risk stratification and treatment optimization.\nMethod: In this study, we screened genes related to the overall survival (OS) of DLBCL patients in datasets GSE117556, GSE10846, and GSE31312 using univariate Cox analysis. Survival-related genes among the three datasets were screened according to the criteria: hazard ratio (HR) >1 or <1 and p-value <0.01. Least Absolute Shrinkage and Selection Operator (LASSO) and multivariate Cox regression analysis were used to optimize and establish the final gene risk prediction model. The TCGA-NCICCR datasets and our clinical cohort were used to validate the performance of the prediction model. CIBERSORT and ssGSEA algorithms were used to estimate immune scores in the high- and low-risk groups.\nResults: We constructed an eight-gene prognostic signature that could reliably predict the clinical outcome in training, testing, and validation cohorts. Our prognostic signature also performed distinguished areas under the ROC curve in each dataset, respectively. After stratification based on clinical characteristics such as cell-of-origin (COO), age, eastern cooperative oncology group (ECOG) performance status, international prognostic index (IPI), stage, and MYC/BCL2 expression, the difference in OS between the high- and low-risk groups was statistically significant. Next, univariate and multivariate analyses revealed that the risk score model had a significant prediction value. Finally, a nomogram was established to visualize the prediction model. Of note, we found that the low-risk group was enriched with immune cells.\nConclusion: In summary, we identified an eight-gene prognostic prediction model that can effectively predict survival outcomes of patients with DLBCL and built a nomogram to visualize the perdition model. We also explored immune alterations between high- and low-risk groups.", "claims": [{"id": "claim-method", "statement": "Multivariate Cox regression analysis showed that the risk score model was an independent prognostic factor for poor prognosis (p < 0.0001, HR = 1.380) ( Figure 6B ).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35498426", "locator": "sections[14] \"Validation of the Performance of Our Prediction Model\" paragraph 2", "quote": "Multivariate Cox regression analysis showed that the risk score model was an independent prognostic factor for poor prognosis (p < 0.0001, HR = 1.380) ( Figure 6B )."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35498426", "locator": "sections[17] \"Data Availability Statement\" paragraph 2", "quote": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Compared with other indicators, the risk score was superior for predicting the patient prognosis (AUC = 0.820) ( Figure 6C ).", "kind": "quantitative", "target": {"value": 0.82, "unit": "auc", "tolerance": null, "source": "Compared with other indicators, the risk score was superior for predicting the patient prognosis (AUC = 0.820) ( Figure 6C )."}, "evidence": [{"asset": "source:pmid:35498426", "locator": "sections[14] \"Validation of the Performance of Our Prediction Model\" paragraph 2", "quote": "Compared with other indicators, the risk score was superior for predicting the patient prognosis (AUC = 0.820) ( Figure 6C )."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Compared with other indicators, the risk score was superior for predicting the patient prognosis (AUC = 0.820) ( Figure 6C ).", "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:35498426"], "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:GSE10846"], "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:GSE10846"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35498426", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fendo.2022.846357", "sha256": "sha256:3b31ee18d843f75559121a20a76fe17df6a35479727ae3cb62785d3f9e9de0b5", "bytes": 31157, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fendo.2022.846357", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9048048", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10846", "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=GSE10846", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10846", "version": null, "note": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM274895", "GSM274896", "GSM274897", "GSM274898", "GSM274899", "GSM274900", "GSM274901", "GSM274902", "GSM274903", "GSM274904", "GSM274905", "GSM274906", "GSM274907", "GSM274908", "GSM274909", "GSM274910", "GSM274911", "GSM274912", "GSM274913", "GSM274914", "GSM274915", "GSM274916", "GSM274917", "GSM274918", "GSM274919", "GSM274920", "GSM274921", "GSM274922", "GSM274923", "GSM274924", "GSM274925", "GSM274926", "GSM274927", "GSM274928", "GSM274929", "GSM274930", "GSM274931", "GSM274932", "GSM274933", "GSM274934", "GSM274935", "GSM274936", "GSM274937", "GSM274938", "GSM274939", "GSM274940", "GSM274941", "GSM274942", "GSM274943", "GSM274944", "GSM274945", "GSM274946", "GSM274947", "GSM274948", "GSM274949", "GSM274950", "GSM274951", "GSM274952", "GSM274953", "GSM274954", "GSM274955", "GSM274956", "GSM274957", "GSM274958", "GSM274959", "GSM274960", "GSM274961", "GSM274962", "GSM274963", "GSM274964", "GSM274965", "GSM274966", "GSM274967", "GSM274968", "GSM274969", "GSM274970", "GSM274971", "GSM274972", "GSM274973", "GSM274974", "GSM274975", "GSM274976", "GSM274977", "GSM274978", "GSM274979", "GSM274980", "GSM274981", "GSM274982", "GSM274983", "GSM274984", "GSM274985", "GSM274986", "GSM274987", "GSM274988", "GSM274989", "GSM274990", "GSM274991", "GSM274992", "GSM274993", "GSM274994", "GSM274995", "GSM274996", "GSM274997", "GSM274998", "GSM274999", "GSM275000", "GSM275001", "GSM275002", "GSM275003", "GSM275004", "GSM275005", "GSM275006", "GSM275007", "GSM275008", "GSM275009", "GSM275010", "GSM275011", "GSM275012", "GSM275013", "GSM275014", "GSM275015", "GSM275016", "GSM275017", "GSM275018", "GSM275019", "GSM275020", "GSM275021", "GSM275022", "GSM275023", "GSM275024", "GSM275025", "GSM275026", "GSM275027", "GSM275028", "GSM275029", "GSM275030", "GSM275031", "GSM275032", "GSM275033", "GSM275034", "GSM275035", "GSM275036", "GSM275037", "GSM275038", "GSM275039", "GSM275040", "GSM275041", "GSM275042", "GSM275043", "GSM275044", "GSM275045", "GSM275046", "GSM275047", "GSM275048", "GSM275049", "GSM275050", "GSM275051", "GSM275052", "GSM275053", "GSM275054", "GSM275055", "GSM275056", "GSM275057", "GSM275058", "GSM275059", "GSM275060", "GSM275061", "GSM275062", "GSM275063", "GSM275064", "GSM275065", "GSM275066", "GSM275067", "GSM275068", "GSM275069", "GSM275070", "GSM275071", "GSM275072", "GSM275073", "GSM275074", "GSM275075", "GSM275076", "GSM275077", "GSM275078", "GSM275079", "GSM275080", "GSM275081", "GSM275082", "GSM275083", "GSM275084", "GSM275085", "GSM275086", "GSM275087", "GSM275088", "GSM275089", "GSM275090", "GSM275091", "GSM275092", "GSM275093", "GSM275094", "GSM275095", "GSM275096", "GSM275097", "GSM275098", "GSM275099", "GSM275100", "GSM275101", "GSM275102", "GSM275103", "GSM275104", "GSM275105", "GSM275106", "GSM275107", "GSM275108", "GSM275109", "GSM275110", "GSM275111", "GSM275112", "GSM275113", "GSM275114", "GSM275115", "GSM275116", "GSM275117", "GSM275118", "GSM275119", "GSM275120", "GSM275121", "GSM275122", "GSM275123", "GSM275124", "GSM275125", "GSM275126", "GSM275127", "GSM275128", "GSM275129", "GSM275130", "GSM275131", "GSM275132", "GSM275133", "GSM275134", "GSM275135", "GSM275136", "GSM275137", "GSM275138", "GSM275139", "GSM275140", "GSM275141", "GSM275142", "GSM275143", "GSM275144", "GSM275145", "GSM275146", "GSM275147", "GSM275148", "GSM275149", "GSM275150", "GSM275151", "GSM275152", "GSM275153", "GSM275154", "GSM275155", "GSM275156", "GSM275157", "GSM275158", "GSM275159", "GSM275160", "GSM275161", "GSM275162", "GSM275163", "GSM275164", "GSM275165", "GSM275166", "GSM275167", "GSM275168", "GSM275169", "GSM275170", "GSM275171", "GSM275172", "GSM275173", "GSM275174", "GSM275175", "GSM275176", "GSM275177", "GSM275178", "GSM275179", "GSM275180", "GSM275181", "GSM275182", "GSM275183", "GSM275184", "GSM275185", "GSM275186", "GSM275187", "GSM275188", "GSM275189", "GSM275190", "GSM275191", "GSM275192", "GSM275193", "GSM275194", "GSM275195", "GSM275196", "GSM275197", "GSM275198", "GSM275199", "GSM275200", "GSM275201", "GSM275202", "GSM275203", "GSM275204", "GSM275205", "GSM275206", "GSM275207", "GSM275208", "GSM275209", "GSM275210", "GSM275211", "GSM275212", "GSM275213", "GSM275214", "GSM275215", "GSM275216", "GSM275217", "GSM275218", "GSM275219", "GSM275220", "GSM275221", "GSM275222", "GSM275223", "GSM275224", "GSM275225", "GSM275226", "GSM275227", "GSM275228", "GSM275229", "GSM275230", "GSM275231", "GSM275232", "GSM275233", "GSM275234", "GSM275235", "GSM275236", "GSM275237", "GSM275238", "GSM275239", "GSM275240", "GSM275241", "GSM275242", "GSM275243", "GSM275244", "GSM275245", "GSM275246", "GSM275247", "GSM275248", "GSM275249", "GSM275250", "GSM275251", "GSM275252", "GSM275253", "GSM275254", "GSM275255", "GSM275256", "GSM275257", "GSM275258", "GSM275259", "GSM275260", "GSM275261", "GSM275262", "GSM275263", "GSM275264", "GSM275265", "GSM275266", "GSM275267", "GSM275268", "GSM275269", "GSM275270", "GSM275271", "GSM275272", "GSM275273", "GSM275274", "GSM275275", "GSM275276", "GSM275277", "GSM275278", "GSM275279", "GSM275280", "GSM275281", "GSM275282", "GSM275283", "GSM275284", "GSM275285", "GSM275286", "GSM275287", "GSM275288", "GSM275289", "GSM275290", "GSM275291", "GSM275292", "GSM275293", "GSM275294", "GSM275295", "GSM275296", "GSM275297", "GSM275298", "GSM275299", "GSM275300", "GSM275301", "GSM275302", "GSM275303", "GSM275304", "GSM275305", "GSM275306", "GSM275307", "GSM275308", "GSM361239", "GSM361240", "GSM361241", "GSM361242", "GSM361243", "GSM361244"], "sample_count": 420, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Prediction of survival in diffuse large B cell lymphoma treated with chemotherapy plus Rituximab", "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:GSE117556", "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=GSE117556", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE117556", "version": null, "note": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3302930", "GSM3302931", "GSM3302932", "GSM3302933", "GSM3302934", "GSM3302935", "GSM3302936", "GSM3302937", "GSM3302938", "GSM3302939", "GSM3302940", "GSM3302941", "GSM3302942", "GSM3302943", "GSM3302944", "GSM3302945", "GSM3302946", "GSM3302947", "GSM3302948", "GSM3302949", "GSM3302950", "GSM3302951", "GSM3302952", "GSM3302953", "GSM3302954", "GSM3302955", "GSM3302956", "GSM3302957", "GSM3302958", "GSM3302959", "GSM3302960", "GSM3302961", "GSM3302962", "GSM3302963", "GSM3302964", "GSM3302965", "GSM3302966", "GSM3302967", "GSM3302968", "GSM3302969", "GSM3302970", "GSM3302971", "GSM3302972", "GSM3302973", "GSM3302974", "GSM3302975", "GSM3302976", "GSM3302977", "GSM3302978", "GSM3302979", "GSM3302980", "GSM3302981", "GSM3302982", "GSM3302983", "GSM3302984", "GSM3302985", "GSM3302986", "GSM3302987", "GSM3302988", "GSM3302989", "GSM3302990", "GSM3302991", "GSM3302992", "GSM3302993", "GSM3302994", "GSM3302995", "GSM3302996", "GSM3302997", "GSM3302998", "GSM3302999", "GSM3303000", "GSM3303001", "GSM3303002", "GSM3303003", "GSM3303004", "GSM3303005", "GSM3303006", "GSM3303007", "GSM3303008", "GSM3303009", "GSM3303010", "GSM3303011", "GSM3303012", "GSM3303013", "GSM3303014", "GSM3303015", "GSM3303016", "GSM3303017", "GSM3303018", "GSM3303019", "GSM3303020", "GSM3303021", "GSM3303022", "GSM3303023", "GSM3303024", "GSM3303025", "GSM3303026", "GSM3303027", "GSM3303028", "GSM3303029", "GSM3303030", "GSM3303031", "GSM3303032", "GSM3303033", "GSM3303034", "GSM3303035", "GSM3303036", "GSM3303037", "GSM3303038", "GSM3303039", "GSM3303040", "GSM3303041", "GSM3303042", "GSM3303043", "GSM3303044", "GSM3303045", "GSM3303046", "GSM3303047", "GSM3303048", "GSM3303049", "GSM3303050", "GSM3303051", "GSM3303052", "GSM3303053", "GSM3303054", "GSM3303055", "GSM3303056", "GSM3303057", "GSM3303058", "GSM3303059", "GSM3303060", "GSM3303061", "GSM3303062", "GSM3303063", "GSM3303064", "GSM3303065", "GSM3303066", "GSM3303067", "GSM3303068", "GSM3303069", "GSM3303070", "GSM3303071", "GSM3303072", "GSM3303073", "GSM3303074", "GSM3303075", "GSM3303076", "GSM3303077", "GSM3303078", "GSM3303079", "GSM3303080", "GSM3303081", "GSM3303082", "GSM3303083", "GSM3303084", "GSM3303085", "GSM3303086", "GSM3303087", "GSM3303088", "GSM3303089", "GSM3303090", "GSM3303091", "GSM3303092", "GSM3303093", "GSM3303094", "GSM3303095", "GSM3303096", "GSM3303097", "GSM3303098", "GSM3303099", "GSM3303100", "GSM3303101", "GSM3303102", "GSM3303103", "GSM3303104", "GSM3303105", "GSM3303106", "GSM3303107", "GSM3303108", "GSM3303109", "GSM3303110", "GSM3303111", "GSM3303112", "GSM3303113", "GSM3303114", "GSM3303115", "GSM3303116", "GSM3303117", "GSM3303118", "GSM3303119", "GSM3303120", "GSM3303121", "GSM3303122", "GSM3303123", "GSM3303124", "GSM3303125", "GSM3303126", "GSM3303127", "GSM3303128", "GSM3303129", "GSM3303130", "GSM3303131", "GSM3303132", "GSM3303133", "GSM3303134", "GSM3303135", "GSM3303136", "GSM3303137", "GSM3303138", "GSM3303139", "GSM3303140", "GSM3303141", "GSM3303142", "GSM3303143", "GSM3303144", "GSM3303145", "GSM3303146", "GSM3303147", "GSM3303148", "GSM3303149", "GSM3303150", "GSM3303151", "GSM3303152", "GSM3303153", "GSM3303154", "GSM3303155", "GSM3303156", "GSM3303157", "GSM3303158", "GSM3303159", "GSM3303160", "GSM3303161", "GSM3303162", "GSM3303163", "GSM3303164", "GSM3303165", "GSM3303166", "GSM3303167", "GSM3303168", "GSM3303169", "GSM3303170", "GSM3303171", "GSM3303172", "GSM3303173", "GSM3303174", "GSM3303175", "GSM3303176", "GSM3303177", "GSM3303178", "GSM3303179", "GSM3303180", "GSM3303181", "GSM3303182", "GSM3303183", "GSM3303184", "GSM3303185", "GSM3303186", "GSM3303187", "GSM3303188", "GSM3303189", "GSM3303190", "GSM3303191", "GSM3303192", "GSM3303193", "GSM3303194", "GSM3303195", "GSM3303196", "GSM3303197", "GSM3303198", "GSM3303199", "GSM3303200", "GSM3303201", "GSM3303202", "GSM3303203", "GSM3303204", "GSM3303205", "GSM3303206", "GSM3303207", "GSM3303208", "GSM3303209", "GSM3303210", "GSM3303211", "GSM3303212", "GSM3303213", "GSM3303214", "GSM3303215", "GSM3303216", "GSM3303217", "GSM3303218", "GSM3303219", "GSM3303220", "GSM3303221", "GSM3303222", "GSM3303223", "GSM3303224", "GSM3303225", "GSM3303226", "GSM3303227", "GSM3303228", "GSM3303229", "GSM3303230", "GSM3303231", "GSM3303232", "GSM3303233", "GSM3303234", "GSM3303235", "GSM3303236", "GSM3303237", "GSM3303238", "GSM3303239", "GSM3303240", "GSM3303241", "GSM3303242", "GSM3303243", "GSM3303244", "GSM3303245", "GSM3303246", "GSM3303247", "GSM3303248", "GSM3303249", "GSM3303250", "GSM3303251", "GSM3303252", "GSM3303253", "GSM3303254", "GSM3303255", "GSM3303256", "GSM3303257", "GSM3303258", "GSM3303259", "GSM3303260", "GSM3303261", "GSM3303262", "GSM3303263", "GSM3303264", "GSM3303265", "GSM3303266", "GSM3303267", "GSM3303268", "GSM3303269", "GSM3303270", "GSM3303271", "GSM3303272", "GSM3303273", "GSM3303274", "GSM3303275", "GSM3303276", "GSM3303277", "GSM3303278", "GSM3303279", "GSM3303280", "GSM3303281", "GSM3303282", "GSM3303283", "GSM3303284", "GSM3303285", "GSM3303286", "GSM3303287", "GSM3303288", "GSM3303289", "GSM3303290", "GSM3303291", "GSM3303292", "GSM3303293", "GSM3303294", "GSM3303295", "GSM3303296", "GSM3303297", "GSM3303298", "GSM3303299", "GSM3303300", "GSM3303301", "GSM3303302", "GSM3303303", "GSM3303304", "GSM3303305", "GSM3303306", "GSM3303307", "GSM3303308", "GSM3303309", "GSM3303310", "GSM3303311", "GSM3303312", "GSM3303313", "GSM3303314", "GSM3303315", "GSM3303316", "GSM3303317", "GSM3303318", "GSM3303319", "GSM3303320", "GSM3303321", "GSM3303322", "GSM3303323", "GSM3303324", "GSM3303325", "GSM3303326", "GSM3303327", "GSM3303328", "GSM3303329", "GSM3303330", "GSM3303331", "GSM3303332", "GSM3303333", "GSM3303334", "GSM3303335", "GSM3303336", "GSM3303337", "GSM3303338", "GSM3303339", "GSM3303340", "GSM3303341", "GSM3303342", "GSM3303343", "GSM3303344", "GSM3303345", "GSM3303346", "GSM3303347", "GSM3303348", "GSM3303349", "GSM3303350", "GSM3303351", "GSM3303352", "GSM3303353", "GSM3303354", "GSM3303355", "GSM3303356", "GSM3303357", "GSM3303358", "GSM3303359", "GSM3303360", "GSM3303361", "GSM3303362", "GSM3303363", "GSM3303364", "GSM3303365", "GSM3303366", "GSM3303367", "GSM3303368", "GSM3303369", "GSM3303370", "GSM3303371", "GSM3303372", "GSM3303373", "GSM3303374", "GSM3303375", "GSM3303376", "GSM3303377", "GSM3303378", "GSM3303379", "GSM3303380", "GSM3303381", "GSM3303382", "GSM3303383", "GSM3303384", "GSM3303385", "GSM3303386", "GSM3303387", "GSM3303388", "GSM3303389", "GSM3303390", "GSM3303391", "GSM3303392", "GSM3303393", "GSM3303394", "GSM3303395", "GSM3303396", "GSM3303397", "GSM3303398", "GSM3303399", "GSM3303400", "GSM3303401", "GSM3303402", "GSM3303403", "GSM3303404", "GSM3303405", "GSM3303406", "GSM3303407", "GSM3303408", "GSM3303409", "GSM3303410", "GSM3303411", "GSM3303412", "GSM3303413", "GSM3303414", "GSM3303415", "GSM3303416", "GSM3303417", "GSM3303418", "GSM3303419", "GSM3303420", "GSM3303421", "GSM3303422", "GSM3303423", "GSM3303424", "GSM3303425", "GSM3303426", "GSM3303427", "GSM3303428", "GSM3303429", "GSM3303430", "GSM3303431", "GSM3303432", "GSM3303433", "GSM3303434", "GSM3303435", "GSM3303436", "GSM3303437", "GSM3303438", "GSM3303439", "GSM3303440", "GSM3303441", "GSM3303442", "GSM3303443", "GSM3303444", "GSM3303445", "GSM3303446", "GSM3303447", "GSM3303448", "GSM3303449", "GSM3303450", "GSM3303451", "GSM3303452", "GSM3303453", "GSM3303454", "GSM3303455", "GSM3303456", "GSM3303457", "GSM3303458", "GSM3303459", "GSM3303460", "GSM3303461", "GSM3303462", "GSM3303463", "GSM3303464", "GSM3303465", "GSM3303466", "GSM3303467", "GSM3303468", "GSM3303469", "GSM3303470", "GSM3303471", "GSM3303472", "GSM3303473", "GSM3303474", "GSM3303475", "GSM3303476", "GSM3303477", "GSM3303478", "GSM3303479", "GSM3303480", "GSM3303481", "GSM3303482", "GSM3303483", "GSM3303484", "GSM3303485", "GSM3303486", "GSM3303487", "GSM3303488", "GSM3303489", "GSM3303490", "GSM3303491", "GSM3303492", "GSM3303493", "GSM3303494", "GSM3303495", "GSM3303496", "GSM3303497", "GSM3303498", "GSM3303499", "GSM3303500", "GSM3303501", "GSM3303502", "GSM3303503", "GSM3303504", "GSM3303505", "GSM3303506", "GSM3303507", "GSM3303508", "GSM3303509", "GSM3303510", "GSM3303511", "GSM3303512", "GSM3303513", "GSM3303514", "GSM3303515", "GSM3303516", "GSM3303517", "GSM3303518", "GSM3303519", "GSM3303520", "GSM3303521", "GSM3303522", "GSM3303523", "GSM3303524", "GSM3303525", "GSM3303526", "GSM3303527", "GSM3303528", "GSM3303529", "GSM3303530", "GSM3303531", "GSM3303532", "GSM3303533", "GSM3303534", "GSM3303535", "GSM3303536", "GSM3303537", "GSM3303538", "GSM3303539", "GSM3303540", "GSM3303541", "GSM3303542", "GSM3303543", "GSM3303544", "GSM3303545", "GSM3303546", "GSM3303547", "GSM3303548", "GSM3303549", "GSM3303550", "GSM3303551", "GSM3303552", "GSM3303553", "GSM3303554", "GSM3303555", "GSM3303556", "GSM3303557", "GSM3303558", "GSM3303559", "GSM3303560", "GSM3303561", "GSM3303562", "GSM3303563", "GSM3303564", "GSM3303565", "GSM3303566", "GSM3303567", "GSM3303568", "GSM3303569", "GSM3303570", "GSM3303571", "GSM3303572", "GSM3303573", "GSM3303574", "GSM3303575", "GSM3303576", "GSM3303577", "GSM3303578", "GSM3303579", "GSM3303580", "GSM3303581", "GSM3303582", "GSM3303583", "GSM3303584", "GSM3303585", "GSM3303586", "GSM3303587", "GSM3303588", "GSM3303589", "GSM3303590", "GSM3303591", "GSM3303592", "GSM3303593", "GSM3303594", "GSM3303595", "GSM3303596", "GSM3303597", "GSM3303598", "GSM3303599", "GSM3303600", "GSM3303601", "GSM3303602", "GSM3303603", "GSM3303604", "GSM3303605", "GSM3303606", "GSM3303607", "GSM3303608", "GSM3303609", "GSM3303610", "GSM3303611", "GSM3303612", "GSM3303613", "GSM3303614", "GSM3303615", "GSM3303616", "GSM3303617", "GSM3303618", "GSM3303619", "GSM3303620", "GSM3303621", "GSM3303622", "GSM3303623", "GSM3303624", "GSM3303625", "GSM3303626", "GSM3303627", "GSM3303628", "GSM3303629", "GSM3303630", "GSM3303631", "GSM3303632", "GSM3303633", "GSM3303634", "GSM3303635", "GSM3303636", "GSM3303637", "GSM3303638", "GSM3303639", "GSM3303640", "GSM3303641", "GSM3303642", "GSM3303643", "GSM3303644", "GSM3303645", "GSM3303646", "GSM3303647", "GSM3303648", "GSM3303649", "GSM3303650", "GSM3303651", "GSM3303652", "GSM3303653", "GSM3303654", "GSM3303655", "GSM3303656", "GSM3303657", "GSM3303658", "GSM3303659", "GSM3303660", "GSM3303661", "GSM3303662", "GSM3303663", "GSM3303664", "GSM3303665", "GSM3303666", "GSM3303667", "GSM3303668", "GSM3303669", "GSM3303670", "GSM3303671", "GSM3303672", "GSM3303673", "GSM3303674", "GSM3303675", "GSM3303676", "GSM3303677", "GSM3303678", "GSM3303679", "GSM3303680", "GSM3303681", "GSM3303682", "GSM3303683", "GSM3303684", "GSM3303685", "GSM3303686", "GSM3303687", "GSM3303688", "GSM3303689", "GSM3303690", "GSM3303691", "GSM3303692", "GSM3303693", "GSM3303694", "GSM3303695", "GSM3303696", "GSM3303697", "GSM3303698", "GSM3303699", "GSM3303700", "GSM3303701", "GSM3303702", "GSM3303703", "GSM3303704", "GSM3303705", "GSM3303706", "GSM3303707", "GSM3303708", "GSM3303709", "GSM3303710", "GSM3303711", "GSM3303712", "GSM3303713", "GSM3303714", "GSM3303715", "GSM3303716", "GSM3303717", "GSM3303718", "GSM3303719", "GSM3303720", "GSM3303721", "GSM3303722", "GSM3303723", "GSM3303724", "GSM3303725", "GSM3303726", "GSM3303727", "GSM3303728", "GSM3303729", "GSM3303730", "GSM3303731", "GSM3303732", "GSM3303733", "GSM3303734", "GSM3303735", "GSM3303736", "GSM3303737", "GSM3303738", "GSM3303739", "GSM3303740", "GSM3303741", "GSM3303742", "GSM3303743", "GSM3303744", "GSM3303745", "GSM3303756", "GSM3303757", "GSM3303758", "GSM3303759", "GSM3303760", "GSM3303761", "GSM3303762", "GSM3303763", "GSM3303764", "GSM3303765", "GSM3303766", "GSM3303767", "GSM3303768", "GSM3303769", "GSM3303770", "GSM3303771", "GSM3303772", "GSM3303773", "GSM3303774", "GSM3303775", "GSM3303776", "GSM3303777", "GSM3303778", "GSM3303779", "GSM3303780", "GSM3303781", "GSM3303782", "GSM3303783", "GSM3303784", "GSM3303785", "GSM3303786", "GSM3303787", "GSM3303788", "GSM3303789", "GSM3303790", "GSM3303791", "GSM3303792", "GSM3303793", "GSM3303794", "GSM3303795", "GSM3303796", "GSM3303797", "GSM3303798", "GSM3303799", "GSM3303800", "GSM3303801", "GSM3303802", "GSM3303803", "GSM3303804", "GSM3303805", "GSM3303806", "GSM3303807", "GSM3303808", "GSM3303809", "GSM3303810", "GSM3303811", "GSM3303812", "GSM3303813", "GSM3303814", "GSM3303815", "GSM3303816", "GSM3303817", "GSM3303818", "GSM3303819", "GSM3303820", "GSM3303821", "GSM3303822", "GSM3303823", "GSM3303824", "GSM3303825", "GSM3303826", "GSM3303827", "GSM3303828", "GSM3303829", "GSM3303830", "GSM3303831", "GSM3303832", "GSM3303833", "GSM3303834", "GSM3303835", "GSM3303836", "GSM3303837", "GSM3303838", "GSM3303839", "GSM3303840", "GSM3303841", "GSM3303842", "GSM3303843", "GSM3303844", "GSM3303845", "GSM3303846", "GSM3303847", "GSM3303848", "GSM3303849", "GSM3303850", "GSM3303851", "GSM3303852", "GSM3303853", "GSM3303854", "GSM3303855", "GSM3303856", "GSM3303857", "GSM3303858", "GSM3303859", "GSM3303860", "GSM3303861", "GSM3303862", "GSM3303863", "GSM3303864", "GSM3303865", "GSM3303866", "GSM3303867"], "sample_count": 928, "group_sizes": null, "group_sizes_basis": null, "platform": "14951", "taxon": "Homo sapiens", "title": "Molecular definition of high grade B cell lymphoma: a centroblast-like group with potential for more effective therapy", "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:GSE31312", "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=GSE31312", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31312", "version": null, "note": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM775979", "GSM775980", "GSM775981", "GSM775982", "GSM775983", "GSM775984", "GSM775985", "GSM775986", "GSM775987", "GSM775988", "GSM775989", "GSM775990", "GSM775991", "GSM775992", "GSM775993", "GSM775994", "GSM775995", "GSM775996", "GSM775997", "GSM775998", "GSM775999", "GSM776000", "GSM776001", "GSM776002", "GSM776003", "GSM776004", "GSM776005", "GSM776006", "GSM776007", "GSM776008", "GSM776009", "GSM776010", "GSM776011", "GSM776012", "GSM776013", "GSM776014", "GSM776015", "GSM776016", "GSM776017", "GSM776018", "GSM776019", "GSM776020", "GSM776021", "GSM776022", "GSM776023", "GSM776024", "GSM776025", "GSM776026", "GSM776027", "GSM776028", "GSM776029", "GSM776030", "GSM776031", "GSM776032", "GSM776033", "GSM776034", "GSM776035", "GSM776036", "GSM776037", "GSM776038", "GSM776039", "GSM776040", "GSM776041", "GSM776042", "GSM776043", "GSM776044", "GSM776045", "GSM776046", "GSM776047", "GSM776048", "GSM776049", "GSM776050", "GSM776051", "GSM776052", "GSM776053", "GSM776054", "GSM776055", "GSM776056", "GSM776057", "GSM776058", "GSM776059", "GSM776060", "GSM776061", "GSM776062", "GSM776063", "GSM776064", "GSM776065", "GSM776066", "GSM776067", "GSM776068", "GSM776069", "GSM776070", "GSM776071", "GSM776072", "GSM776073", "GSM776074", "GSM776075", "GSM776076", "GSM776077", "GSM776078", "GSM776079", "GSM776080", "GSM776081", "GSM776082", "GSM776083", "GSM776084", "GSM776085", "GSM776086", "GSM776087", "GSM776088", "GSM776089", "GSM776090", "GSM776091", "GSM776092", "GSM776093", "GSM776094", "GSM776095", "GSM776096", "GSM776097", "GSM776098", "GSM776099", "GSM776100", "GSM776101", "GSM776102", "GSM776103", "GSM776104", "GSM776105", "GSM776106", "GSM776107", "GSM776108", "GSM776109", "GSM776110", "GSM776111", "GSM776112", "GSM776113", "GSM776114", "GSM776115", "GSM776116", "GSM776117", "GSM776118", "GSM776119", "GSM776120", "GSM776121", "GSM776122", "GSM776123", "GSM776124", "GSM776125", "GSM776126", "GSM776127", "GSM776128", "GSM776129", "GSM776130", "GSM776131", "GSM776132", "GSM776133", "GSM776134", "GSM776135", "GSM776136", "GSM776137", "GSM776138", "GSM776139", "GSM776140", "GSM776141", "GSM776142", "GSM776143", "GSM776144", "GSM776145", "GSM776146", "GSM776147", "GSM776148", "GSM776149", "GSM776150", "GSM776151", "GSM776152", "GSM776153", "GSM776154", "GSM776155", "GSM776156", "GSM776157", "GSM776158", "GSM776159", "GSM776160", "GSM776161", "GSM776162", "GSM776163", "GSM776164", "GSM776165", "GSM776166", "GSM776167", "GSM776168", "GSM776169", "GSM776170", "GSM776171", "GSM776172", "GSM776173", "GSM776174", "GSM776175", "GSM776176", "GSM776177", "GSM776178", "GSM776179", "GSM776180", "GSM776181", "GSM776182", "GSM776183", "GSM776184", "GSM776185", "GSM776186", "GSM776187", "GSM776188", "GSM776189", "GSM776190", "GSM776191", "GSM776192", "GSM776193", "GSM776194", "GSM776195", "GSM776196", "GSM776197", "GSM776198", "GSM776199", "GSM776200", "GSM776201", "GSM776202", "GSM776203", "GSM776204", "GSM776205", "GSM776206", "GSM776207", "GSM776208", "GSM776209", "GSM776210", "GSM776211", "GSM776212", "GSM776213", "GSM776214", "GSM776215", "GSM776216", "GSM776217", "GSM776218", "GSM776219", "GSM776220", "GSM776221", "GSM776222", "GSM776223", "GSM776224", "GSM776225", "GSM776226", "GSM776227", "GSM776228", "GSM776229", "GSM776230", "GSM776231", "GSM776232", "GSM776233", "GSM776234", "GSM776235", "GSM776236", "GSM776237", "GSM776238", "GSM776239", "GSM776240", "GSM776241", "GSM776242", "GSM776243", "GSM776244", "GSM776245", "GSM776246", "GSM776247", "GSM776248", "GSM776249", "GSM776250", "GSM776251", "GSM776252", "GSM776253", "GSM776254", "GSM776255", "GSM776256", "GSM776257", "GSM776258", "GSM776259", "GSM776260", "GSM776261", "GSM776262", "GSM776263", "GSM776264", "GSM776265", "GSM776266", "GSM776267", "GSM776268", "GSM776269", "GSM776270", "GSM776271", "GSM776272", "GSM776273", "GSM776274", "GSM776275", "GSM776276", "GSM776277", "GSM776278", "GSM776279", "GSM776280", "GSM776281", "GSM776282", "GSM776283", "GSM776284", "GSM776285", "GSM776286", "GSM776287", "GSM776288", "GSM776289", "GSM776290", "GSM776291", "GSM776292", "GSM776293", "GSM776294", "GSM776295", "GSM776296", "GSM776297", "GSM776298", "GSM776299", "GSM776300", "GSM776301", "GSM776302", "GSM776303", "GSM776304", "GSM776305", "GSM776306", "GSM776307", "GSM776308", "GSM776309", "GSM776310", "GSM776311", "GSM776312", "GSM776313", "GSM776314", "GSM776315", "GSM776316", "GSM776317", "GSM776318", "GSM776319", "GSM776320", "GSM776321", "GSM776322", "GSM776323", "GSM776324", "GSM776325", "GSM776326", "GSM776327", "GSM776328", "GSM776329", "GSM776330", "GSM776331", "GSM776332", "GSM776333", "GSM776334", "GSM776335", "GSM776336", "GSM776337", "GSM776338", "GSM776339", "GSM776340", "GSM776341", "GSM776342", "GSM776343", "GSM776344", "GSM776345", "GSM776346", "GSM776347", "GSM776348", "GSM776349", "GSM776350", "GSM776351", "GSM776352", "GSM776353", "GSM776354", "GSM776355", "GSM776356", "GSM776357", "GSM776358", "GSM776359", "GSM776360", "GSM776361", "GSM776362", "GSM776363", "GSM776364", "GSM776365", "GSM776366", "GSM776367", "GSM776368", "GSM776369", "GSM776370", "GSM776371", "GSM776372", "GSM776373", "GSM776374", "GSM776375", "GSM776376", "GSM776377", "GSM776378", "GSM776379", "GSM776380", "GSM776381", "GSM776382", "GSM776383", "GSM776384", "GSM776385", "GSM776386", "GSM776387", "GSM776388", "GSM776389", "GSM776390", "GSM776391", "GSM776392", "GSM776393", "GSM776394", "GSM776395", "GSM776396", "GSM776397", "GSM776398", "GSM776399", "GSM776400", "GSM776401", "GSM776402", "GSM776403", "GSM776404", "GSM776405", "GSM776406", "GSM776407", "GSM776408", "GSM776409", "GSM776410", "GSM776411", "GSM776412", "GSM776413", "GSM776414", "GSM776415", "GSM776416", "GSM776417", "GSM776418", "GSM776419", "GSM776420", "GSM776421", "GSM776422", "GSM776423", "GSM776424", "GSM776425", "GSM776426", "GSM776427", "GSM776428", "GSM776429", "GSM776430", "GSM776431", "GSM776432", "GSM776433", "GSM776434", "GSM776435", "GSM776436", "GSM776437", "GSM776438", "GSM776439", "GSM776440", "GSM776441", "GSM776442", "GSM776443", "GSM776444", "GSM776445", "GSM776446", "GSM776447", "GSM776448", "GSM776449", "GSM776450", "GSM776451", "GSM776452", "GSM776453", "GSM776454", "GSM776455", "GSM776456", "GSM776457", "GSM776458", "GSM776459", "GSM776460", "GSM776461", "GSM776462", "GSM776463", "GSM776464", "GSM776465", "GSM776466", "GSM776467", "GSM776468", "GSM776469", "GSM776470", "GSM776471", "GSM776472", "GSM776473", "GSM776474", "GSM776475", "GSM776476"], "sample_count": 498, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Development and application of a new immunophenotypic algorithm for molecular subtype classification of Diffuse Large B-Cell Lymphoma (DLBCL): Report from an International DLBCL Rituximab-CHOP Consortium Program Study", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE10846 not downloaded", "asset:data:geo:GSE10846 licence not read", "asset:data:geo:GSE117556 not downloaded", "asset:data:geo:GSE117556 licence not read", "asset:data:geo:GSE31312 not downloaded", "asset:data:geo:GSE31312 licence not read"]}, "analysis": {"state": "complete", "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": 1.0, "band": "verbatim", "quote": "Multivariate Cox regression analysis showed that the risk score model was an independent prognostic factor for poor prognosis (p < 0.0001, HR = 1.380) ( Figure 6B )."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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-4", "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": "GO enrichment"}}, {"id": "method-5", "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": 0.7, "band": "medium", "quote": "ROC curve"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "classification_metrics", "expected_value": 0.82, "unit": "auc", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": []}, "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": ["GSE117556", "GSE10846", "GSE31312"], "resolved_accessions": ["GSE117556", "GSE10846", "GSE31312"], "statements": ["The datasets GSE117556, GSE10846 and GSE31312 for this study can be found in the GEO (https://www.ncbi.nlm.nih.gov/geo).The datasets NCICCR for this study can be found at TCGA (https://portal.gdc.cancer.gov/repository)."], "basis": "The paper names GSE117556, GSE10846, GSE31312 in 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:35498426", "data:geo:GSE10846"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10846"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:44:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8781, "completion_tokens": 2084, "cached_tokens": 256}}, "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:35498426", "type": "paper", "label": "pmid:35498426"}, {"id": "source:pmid:35498426", "type": "manuscript", "label": "PMID 35498426 full text"}, {"id": "data:geo:GSE10846", "type": "dataset", "label": "GEO GSE10846"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35498426", "type": "paper", "label": "pmid:35498426"}, {"id": "source:pmid:35498426", "type": "manuscript", "label": "PMID 35498426 full text"}, {"id": "data:geo:GSE10846", "type": "dataset", "label": "GEO GSE10846"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35498426", "type": "extraction", "used": ["source:pmid:35498426"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10846", "type": "accession_resolution", "used": ["data:geo:GSE10846"], "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:35498426", "parent_hash": "sha256:d89c425d40674f976fb4fbce12acc58f610667a9fcb1a9849230ea4127fe4816", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE10846 licence not read", "asset:data:geo:GSE10846 not downloaded", "asset:data:geo:GSE117556 licence not read", "asset:data:geo:GSE117556 not downloaded", "asset:data:geo:GSE31312 licence not read", "asset:data:geo:GSE31312 not downloaded", "execution.not_run", "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": 1.0, "evidence": ["Multivariate Cox regression analysis showed that the risk score model was an independent prognostic factor for poor prognosis (p < 0.0001, HR = 1.380) ( Figure 6B )."], "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":"2026-11-04T02:53:57+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}}}