{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33979320", "kind": "science-record", "revision": 7, "content_hash": "sha256:6b78e9c825f731012e2d09c4ba50d1de37cb8a0a4313c83b88f348c2a36debaa", "created_at": "2026-11-01T15:41:35Z", "updated_at": "2026-11-01T22:03:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Decreased HLF Expression Predicts Poor Survival in Lung Adenocarcinoma.", "doi": "10.12659/MSM.929333", "pmid": "33979320", "authors": ["Zaiyan Wang", "Xiaoning Li", "Hao Chen", "Li Han", "Xiaobin Ji", "Qiubo Wang", "Li Wei", "Yafang Miao", "Jing Wang", "Jianfeng Mao", "Zeming Zhang"], "journal": "Medical science monitor : international medical journal of experimental and clinical research", "year": 2021, "abstract": "BACKGROUND Lung adenocarcinoma (LUAD) is a type of non-small cell carcinoma. Its pathogenesis is being explored and there is no cure for the disease. MATERIAL AND METHODS The Gene Expression Omnibus (GEO) was searched to obtain data on expression of messenger RNA. GEO2R, an interactive web tool, was used to calculate the differentially expressed genes (DEGs) in LUAD. All the DEGs from different datasets were imported into VENNY 2.1 (https://bioinfogp.cnb.csic.es/tools/venny/index.html) to identify the intersection of the DEGs. An online analysis tool, the Database for Annotation, Visualization, and Integrated Discovery (DAVID), was used to help understand the biological meaning of DEG enrichment in LUAD. Cytoscape 3.7.2 was used to perform centrality analysis and visualize hub genes and related networks. Furthermore, the prognostic value of the hub genes was evaluated with the Kaplan-Meier plotter survival analysis tool. RESULTS The GEO database was used to obtain RNA sequencing information for LUAD and normal tissue from the GSE118370, GSE136043, and GSE140797 datasets. A total of 376 DEGs were identified from GSE118370, 248 were identified from GSE136403, and 718 DEGs were identified from GSE140797. The 10 genes with the highest degrees of expression - the hub genes - were CAV1, TEK, SLIT2, RHOJ, DGSX, HLF, MEIS1, PTPRD, FOXF1, and ADRB2. In addition, Kaplan-Meier survival evaluation showed that CAV1, TEK, SLIT2, HLF, MEIS1, PTPRD, FOXF1, and ADRB2 were associated with favorable outcomes for LUAD. CONCLUSIONS CAV1, TEK, SLIT2, HLF, MEIS1, PTPRD, FOXF1, and ADRB2 are hub genes in the DEG interaction network for LUAD and are involved in the development of and prognosis for the disease. The mechanisms underlying these genes should be the subject of further studies.", "claims": [{"id": "claim-method", "statement": "GEO2R is online software used to analyze data from GEO.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33979320", "locator": "sections[4] \"Identification of Differentially Expressed Genes\" paragraph 2", "quote": "GEO2R is online software used to analyze data from GEO."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33979320"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33979320", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12659/MSM.929333", "sha256": "sha256:1c4fe0890af853e97bba90c43386a42f06f49ecd84be0cddf7f94ad9a8be0ec3", "bytes": 28136, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12659/MSM.929333", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8127640", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33979320:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d15e78cc6e3fb46be276633f8a80122f2a66f45d44420cc16af5aa9c97595562", "bytes": 334, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t1-medscimonit-27-e929333", "version": null, "note": "Information about the 3 datasets obtained from GEO.", "structure": {"pmcid": "PMC8127640", "section_index": 11, "section_title": "Identification of DEGs", "row_count": 4, "column_count": 4}, "table": {"label": "Table 1", "caption": "Information about the 3 datasets obtained from GEO.", "rows": [["ID", "LUAD", "Normal", "Total"], ["GSE118370", "6", "6", "12"], ["GSE136043", "5", "5", "10"], ["GSE140797", "7", "7", "14"]], "row_count": 4, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t1-medscimonit-27-e929333"}}, {"id": "asset:table:pmid:33979320:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:eea68f7f570e8bb905a9edbf816f85b6989773224458e0c3c8025d7d2c71f8ef", "bytes": 2806, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#t2-medscimonit-27-e929333", "version": null, "note": "Functional and pathway enrichment analysis of the DEGs.", "structure": {"pmcid": "PMC8127640", "section_index": 12, "section_title": "Gene Ontology and Kyoto Encyclopedia of Genes and Genomes Enrichment Analysis of DEGs", "row_count": 17, "column_count": 5}, "table": {"label": "Table 2", "caption": "Functional and pathway enrichment analysis of the DEGs.", "rows": [["Term", "Name", "Count", "P value", "Genes"], ["Biological processes"], ["GO: 0007155", "Cell adhesion", "17", "9.7E-6", "TNXB, PODXL, FERMT1, SEMA5A, KIAA1462, WISP2, CD36, LAMA3, COL6A6, ITGA8, CD24, PDZD2, MFAP4, EMP2, AOC3, RS1, MYH10"], ["GO: 0001763", "Morphogenesis of a branching structure", "4", "4.8E-5", "TCF21, COL13A1, FOXF1, NOTCH4"], ["GO: 0001525", "Angiogenesis", "10", "3.2E-4", "TAL1, CAV1, EMCN, HLF, TEK, TBX4, ROBO4, RASIP1, TMEM100, MEIS1"], ["Molecular functions"], ["GO: 0005515", "Protein binding", "94", "1.1E-2", "RHOJ, STEAP3, NDST1, ELF3, TNNC1, EIF5, FERMT2, SPINK1, PTPN21, ASPA, DGSX, HHIP, TMEM100, SLC1A1, GOLM1, AHNAK, COL10A1, GHR, LIMK1, TOX3, SLIT2, NEBL, SH2D3C, EYA4, SDC1, ADRB2, CD36, PTRF, SGCG, PLEKHH2, CFL2, CLIC5, SIX1, RYR2, JAM2, MFAP4, EMP2, AOC3, CAV2, TSHZ3, CAV1, HMGB3, ALDH18A1, ADAMTSL3, ABLIM3, PEAK1, BEX1, MME, AFAP1L1, MEIS1, TIMP3, STARD13, TAL1, GPM6A, HOXA5, DISP1, MYZAP, TEK, P2RY1, ETV1, MSI2, VMP1, CD24, FGD5, MYOC, ICA1, PTPRD, ERG, ADARB1, TNXB, HLF, TBX2, COL13A1, PODXL, SMAD6, MAL, DACH1, CDC25C, AGER, SHANK3, CCDC68, LIN7A, TMPRSS4, DOCK4, CDKN1C, UACA, NOTCH4, DEPTOR, SYNM, SH3D19, GRK5, ARAP3, AGR2, MYH10"], ["GO: 0008289", "Lipid binding", "6", "1.2E-2", "APOL3, CD36, STARD9, STARD8, MAL, STARD13"], ["GO: 0001077", "Transcriptional activator activity, RNA polymerase II core promoter proximal region sequence-specific binding", "7", "1.9E-2", "TCF21, ELF3, HLF, HOXA5, SIX1, ETV1, MEIS1"], ["Cellular component"], ["GO: 0005887", "Integral component of plasma membrane", "29", "7.7E-5", "STEAP3, CAV2, CAV1, MME, CD52, SLC19A3, PTGIR, DGSX, TEK, P2RY1, SLC39A8, HHIP, SLC1A1, GOLM1, GHR, PTPRD, PODXL, MAL, AGER, CLEC1A, ADRB2, SDC1, CD36, SSTR1, P2RY14, NOTCH4, ST14, ABCC3, JAM2"], ["GO: 0045121", "Membrane raft", "10", "1.2E-4", "CAV2, CAV1, CD36, PTRF, PODXL, TEK, MAL, CD24, EMP2, AHNAK"], ["GO: 0005886", "Plasma membrane", "59", "1.9E-4", "RHOJ, EIF5, DUOX1, PTGIR, DGSX, KCNQ3, TMEM100, SCN7A, DPP6, SLC1A1, AHNAK, GHR, SLIT2, ADRB2, SDC1, CD36, SGCG, STXBP6, PLEKHH2, SSTR1, CLIC6, ST14, RYR2, JAM2, EMP2, AOC3, CAV2, EMCN, CAV1, CLDN18, PEAK1, MME, SLC19A3, GNG11, AFAP1L1, SEMA5A, STK32A, GPM6A, P2RY1, TEK, SLC39A8, VMP1, PTPRD, COL13A1, PODXL, AGER, SHANK3, GJB2, DOCK4, LIN7A, P2RY14, ITGA8, NOTCH4, ABCC3, NLN, SH3D19, GRK5, ARAP3, MYH10"], ["KEGG pathway"], ["hsa04512", "ECM-receptor interaction", "6", "2.5E-3", "SDC1, LAMA3, CD36, TNXB, COL6A6, ITGA8"], ["Hsa04974", "Protein digestion and absorption", "5", "1.5E-2", "COL6A6, COL13A1, MME, SLC1A1, COL10A1"], ["hsa04360", "Axon guidance", "5", "4.9E-2", "SEMA5A, LIMK1, CFL2, ABLIM3, SLIT2"]], "row_count": 17, "column_count": 5, "numeric_cells": 47, "header_rows": 1, "locator": "section[12]/table-wrap[1]#t2-medscimonit-27-e929333"}}, {"id": "asset:table:pmid:33979320:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3f37cd4c1107135fa344a7c04bd95c08eec8c3a2dd54a2d71043bee0f56d1522", "bytes": 674, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#t3-medscimonit-27-e929333", "version": null, "note": "Information for the top 10 genes with high degrees of expression.", "structure": {"pmcid": "PMC8127640", "section_index": 13, "section_title": "PPI Network Construction and Module Analysis", "row_count": 11, "column_count": 3}, "table": {"label": "Table 3", "caption": "Information for the top 10 genes with high degrees of expression.", "rows": [["Gene symbol", "Gene name", "Degree of expression"], ["CAV1", "Caveolin 1", "42"], ["TEK", "TEK receptor tyrosine kinase", "34"], ["SLIT2", "Slit guidance ligand 2", "31"], ["RHOJ", "Ras homolog family member J", "30"], ["DGSX", "Glypican 3", "27"], ["FOXF1", "Forkhead box F1", "25"], ["HLF", "HIF-1-alpha-like factor", "25"], ["MEIS1", "Meis homeobox 1", "25"], ["PTPRD", "Protein tyrosine phosphatase receptor Type D", "25"], ["ADRB2", "Adrenoceptor beta 2", "24"]], "row_count": 11, "column_count": 3, "numeric_cells": 16, "header_rows": 1, "locator": "section[13]/table-wrap[1]#t3-medscimonit-27-e929333"}}, {"id": "asset:table:pmid:33979320:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7be438cfaac5bb881fc7d28f69e6faac09ff96e3fc9ec9268b5f3d764f9f4fb4", "bytes": 486, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#t4-medscimonit-27-e929333", "version": null, "note": "Hub genes in the Kaplan-Meier plotter database and corresponding probes.", "structure": {"pmcid": "PMC8127640", "section_index": 14, "section_title": "Kaplan-Meier Survival Analysis of hub Genes", "row_count": 11, "column_count": 2}, "table": {"label": "Table 4", "caption": "Hub genes in the Kaplan-Meier plotter database and corresponding probes.", "rows": [["Gene symbol", "Probe ID"], ["CAV1", "212097_at"], ["TEK", "206702_at"], ["SLIT2", "228850_s_at"], ["RHOJ", "235131_at"], ["DGSX", "209220_at"], ["HLF", "204754_at"], ["MEIS1", "204069_at"], ["PTPRD", "214043_at"], ["FOXF1", "205935_at"], ["ADRB2", "206170_at"]], "row_count": 11, "column_count": 2, "numeric_cells": 10, "header_rows": 1, "locator": "section[14]/table-wrap[1]#t4-medscimonit-27-e929333"}}], "gaps": []}, "analysis": {"state": "partial", "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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "Pathway Enrichment"}}, {"id": "method-3", "family": "network_analysis", "specific": "centrality", "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": "centrality"}}, {"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": "GEO2R is online software used to analyze data from GEO."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": [], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:33979320", "asset:table:pmid:33979320:1", "asset:table:pmid:33979320:2", "asset:table:pmid:33979320:3", "asset:table:pmid:33979320:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:33:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 24222, "completion_tokens": 1946, "cached_tokens": 8320}}, "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:33979320", "type": "paper", "label": "pmid:33979320"}, {"id": "source:pmid:33979320", "type": "manuscript", "label": "PMID 33979320 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33979320", "type": "paper", "label": "pmid:33979320"}, {"id": "source:pmid:33979320", "type": "manuscript", "label": "PMID 33979320 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33979320", "type": "extraction", "used": ["source:pmid:33979320"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33979320", "parent_hash": "sha256:9bdf273490c89f3789c70ad7de0e17ed9164e946f6ff7f9235f22ec0f46dc50e", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["RESULTS The GEO database was used to obtain RNA sequencing information for LUAD and normal tissue from"], "order_basis": "paper_text_order:1007", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["lly significant difference. Cell Culture and Transfection The LUAD cell line A549 was purchased from t", "culture all the cells at 37°C in 5% CO2. For transfection, the negative control small interfering RNA", "arma Biotechnology Co., Ltd. A549 cells were transfected with 100 nM NC siRNA or HLA siRNA using Lipo", "the negative control small interfering RNA (siRNA) and HLF siRNA were designed by Suzhou GeneP"], "order_basis": "paper_text_order:3046", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Culture and Transfection The LUAD cell line A549 was purchased from the Shanghai Cell Bank. D", "by Suzhou GenePharma Biotechnology Co., Ltd. A549 cells were transfected with 100 nM NC siRNA", "lementary Figure 1Inhibition of HLF promotes A549 cell proliferation. (A) qRT-PCR results of t", "(B) qRT-PCR results of the HLF expression in A549 cells after siRNA-NC and siRNA-HLF treatment"], "order_basis": "paper_text_order:3079", "id": "assay:3"}, {"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": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T01:18:43+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}}}