{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38111587", "kind": "science-record", "revision": 3, "content_hash": "sha256:c43832d16459fa232b8d7077a23b6b2a7c17092cdf0bb394e0bd0d81f7a6cfb9", "created_at": "2026-11-01T19:20:02Z", "updated_at": "2026-11-01T22:53:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Single-cell and bulk RNA sequencing analysis of B cell marker genes in TNBC TME landscape and immunotherapy.", "doi": "10.3389/fimmu.2023.1245514", "pmid": "38111587", "authors": ["Fangrui Zhao", "Chen Zhao", "Tangpeng Xu", "Yanfang Lan", "Huiqing Lin", "Xiaofei Wu", "Xiangpan Li"], "journal": "Frontiers in immunology", "year": 2023, "abstract": "Objective: This study amied to investigate the prognostic characteristics of triple negative breast cancer (TNBC) patients by analyzing B cell marker genes based on single-cell and bulk RNA sequencing.\nMethods: Utilizing single-cell sequencing data from TNBC patients, we examined tumor-associated B cell marker genes. Transcriptomic data from The Cancer Genome Atlas (TCGA) database were used as the foundation for predictive modeling. Independent validation set was conducted using the GSE58812 dataset. Immune cell infiltration into the tumor was assessed through various, including XCELL, TIMER, QUANTISEQ, CIBERSORT, CIBERSORT-ABS, and ssGSEA. The TIDE score was utilized to predict immunotherapy outcomes. Additional investigations were conducted on the immune checkpoint blockade gene, tumor mutational load, and the GSEA enrichment analysis.\nResults: Our analysis encompassed 22,106 cells and 20,556 genes in cancerous tissue samples from four TNBC patients, resulting in the identification of 116 B cell marker genes. A B cell marker gene score (BCMG score) involving nine B cell marker genes (ZBP1, SEL1L3, CCND2, TNFRSF13C, HSPA6, PLPP5, CXCR4, GZMB, and CCDC50) was developed using TCGA transcriptomic data, revealing statistically significant differences in survival analysis (P<0.05). Functional analysis demonstrated that marker genes were predominantly associated with immune-related pathways. Notably, substantial differences between the higher and lower- BCMG score groups were observed in terms of immune cell infiltration, immune cell activity, tumor mutational burden, TIDE score, and the expression of immune checkpoint blockade genes.\nConclusion: This study has established a robust model based on B-cell marker genes in TNBC, which holds significant potential for predicting prognosis and response to immunotherapy in TNBC patients.", "claims": [{"id": "claim-method", "statement": "The evaluation of the 116 genes involved a univariate COX regression to identify the 10 genes associated with prognosis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38111587", "locator": "sections[14] \"Development of a predictive model for B-Cell marker gene expression\" paragraph 2", "quote": "The evaluation of the 116 genes involved a univariate COX regression to identify the 10 genes associated with prognosis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38111587", "locator": "sections[21] \"Data availability statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study developed a nine-gene B cell marker gene score that showed statistically significant prognostic differences in TNBC patients.", "kind": "quantitative", "target": {"value": 0.05, "unit": "p-value", "tolerance": null, "source": "A B cell marker gene score (BCMG score) involving nine B cell marker genes (ZBP1, SEL1L3, CCND2, TNFRSF13C, HSPA6, PLPP5, CXCR4, GZMB, and CCDC50) was developed using TCGA transcriptomic data, revealing statistically significant differences in survival analysis (P<0.05)."}, "evidence": [{"asset": "source:pmid:38111587", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "A B cell marker gene score (BCMG score) involving nine B cell marker genes (ZBP1, SEL1L3, CCND2, TNFRSF13C, HSPA6, PLPP5, CXCR4, GZMB, and CCDC50) was developed using TCGA transcriptomic data, revealing statistically significant differences in survival analysis (P<0.05)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study developed a nine-gene B cell marker gene score that showed statistically significant prognostic differences in TNBC patients.", "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:38111587"], "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:GSE58812"], "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:GSE58812"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38111587", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2023.1245514", "sha256": "sha256:ff51089732aeff9e1ee6b8aca8c23ea7260efd52cd7614834b7167796e201e13", "bytes": 44654, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2023.1245514", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10725955", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE58812", "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=GSE58812", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE58812", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1419942", "GSM1419943", "GSM1419944", "GSM1419945", "GSM1419946", "GSM1419947", "GSM1419948", "GSM1419949", "GSM1419950", "GSM1419951", "GSM1419952", "GSM1419953", "GSM1419954", "GSM1419955", "GSM1419956", "GSM1419957", "GSM1419958", "GSM1419968", "GSM1419969", "GSM1419970", "GSM1419971", "GSM1419972", "GSM1419973", "GSM1419974", "GSM1419975", "GSM1419976", "GSM1419977", "GSM1419978", "GSM1419979", "GSM1419980", "GSM1419981", "GSM1419982", "GSM1419983", "GSM1419984", "GSM1419985", "GSM1419986", "GSM1419987", "GSM1419988", "GSM1419989", "GSM1419990", "GSM1419991", "GSM1419992", "GSM1419993", "GSM1419994", "GSM1419995", "GSM1419996", "GSM1419997", "GSM1419998", "GSM1419999", "GSM1420000", "GSM1420001", "GSM1420002", "GSM1420003", "GSM1420004", "GSM1420005", "GSM1420006", "GSM1420007", "GSM1420008", "GSM1420009", "GSM1420010", "GSM1420011", "GSM1420012", "GSM1420013", "GSM1420014", "GSM1420015", "GSM1420016", "GSM1420017", "GSM1420018", "GSM1420019", "GSM1420020", "GSM1420021", "GSM1420022", "GSM1420023", "GSM1420024", "GSM1420025", "GSM1420026", "GSM1420027", "GSM1420028", "GSM1420029", "GSM1420030", "GSM1420031", "GSM1420032", "GSM1420033", "GSM1420034", "GSM1420035", "GSM1420036", "GSM1420037", "GSM1420038", "GSM1420039", "GSM1420040", "GSM1420041", "GSM1420042", "GSM1420043", "GSM1420044", "GSM1420045", "GSM1420046", "GSM1420047", "GSM1420048", "GSM1420049", "GSM1420050", "GSM1420051", "GSM1420052", "GSM1420053", "GSM1420054", "GSM1420055", "GSM1420056", "GSM1420057"], "sample_count": 107, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene-expression molecular subtyping of triple-negative breast cancer tumours: importance of immune response", "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:GSM4909281", "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=GSM4909281", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSM4909281", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Triple negative tumour Total cells from Patient 0126", "resolution_checked_at": "2026-11-01T19:09:52Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSM4909282", "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=GSM4909282", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSM4909282", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Triple negative tumour Total cells from Patient 0135", "resolution_checked_at": "2026-11-01T19:09:52Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSM4909283", "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=GSM4909283", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSM4909283", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Triple negative tumour Total cells from Patient 0106", "resolution_checked_at": "2026-11-01T19:09:52Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSM4909284", "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=GSM4909284", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSM4909284", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Triple negative tumour Total cells from Patient 0114", "resolution_checked_at": "2026-11-01T19:09:52Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE58812 not downloaded", "asset:data:geo:GSE58812 licence not read", "asset:data:geo:GSM4909281 not downloaded", "asset:data:geo:GSM4909281 licence not read", "asset:data:geo:GSM4909282 not downloaded", "asset:data:geo:GSM4909282 licence not read", "asset:data:geo:GSM4909283 not downloaded", "asset:data:geo:GSM4909283 licence not read", "asset:data:geo:GSM4909284 not downloaded", "asset:data:geo:GSM4909284 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The evaluation of the 116 genes involved a univariate COX regression to identify the 10 genes associated with prognosis."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "COX regression"}}, {"id": "method-3", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 0.05, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSM4909281", "GSM4909282", "GSM4909283", "GSM4909284", "GSE58812"], "resolved_accessions": ["GSM4909281", "GSM4909282", "GSM4909283", "GSM4909284", "GSE58812"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."], "basis": "The paper names GSM4909281, GSM4909282, GSM4909283, GSM4909284, GSE58812 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:38111587", "data:geo:GSE58812"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE58812"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:03:05Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13178, "completion_tokens": 2240, "cached_tokens": 264}}, "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:38111587", "type": "paper", "label": "pmid:38111587"}, {"id": "source:pmid:38111587", "type": "manuscript", "label": "PMID 38111587 full text"}, {"id": "data:geo:GSE58812", "type": "dataset", "label": "GEO GSE58812"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38111587", "type": "paper", "label": "pmid:38111587"}, {"id": "source:pmid:38111587", "type": "manuscript", "label": "PMID 38111587 full text"}, {"id": "data:geo:GSE58812", "type": "dataset", "label": "GEO GSE58812"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38111587", "type": "extraction", "used": ["source:pmid:38111587"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE58812", "type": "accession_resolution", "used": ["data:geo:GSE58812"], "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:38111587", "parent_hash": "sha256:23518dc54bbd5ab835c8a8be57f0d275739f941da1d6705e7487e2a4797b8155", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE58812 licence not read", "asset:data:geo:GSE58812 not downloaded", "asset:data:geo:GSM4909281 licence not read", "asset:data:geo:GSM4909281 not downloaded", "asset:data:geo:GSM4909282 licence not read", "asset:data:geo:GSM4909282 not downloaded", "asset:data:geo:GSM4909283 licence not read", "asset:data:geo:GSM4909283 not downloaded", "asset:data:geo:GSM4909284 licence not read", "asset:data:geo:GSM4909284 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Single-cell and bulk RNA sequencing analysis of B cell marker genes in TNBC TME", "l marker genes based on single-cell and bulk RNA sequencing. Methods: Utilizing single-cell sequencing d", "amined tumor-associated B cell marker genes. Transcriptomic data from The Cancer Genome Atlas (TCGA) dat", ", GZMB, and CCDC50) was developed using TCGA transcriptomic data, revealing statistically significant di"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The evaluation of the 116 genes involved a univariate COX regression to identify the 10 genes associated with prognosis."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T01:50:28+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}}}