{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32571304", "kind": "science-record", "revision": 7, "content_hash": "sha256:eb5bf16ca9b573f8ebe39156c805cc2d151b3a503eaeee69b8a7c3dac5e492ff", "created_at": "2026-11-01T15:41:04Z", "updated_at": "2026-11-01T22:01:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Construction and analysis of a lncRNA-miRNA-mRNA network based on competitive endogenous RNA reveal functional lncRNAs in oral cancer.", "doi": "10.1186/s12920-020-00741-w", "pmid": "32571304", "authors": ["Junhao Yin", "Xiaoli Zeng", "Zexin Ai", "Miao Yu", "Yang'ou Wu", "Shengjiao Li"], "journal": "BMC medical genomics", "year": 2020, "abstract": "BACKGROUND: A growing evidence suggests that long non-coding RNAs (lncRNAs) can function as a microRNA (miRNA) sponge in various diseases including oral cancer. However, the pathophysiological function of lncRNAs remains unclear.\nMETHODS: Based on the competitive endogenous RNA (ceRNA) theory, we constructed a lncRNA-miRNA-mRNA network in oral cancer with the human expression profiles GSE74530 from the Gene Expression Omnibus (GEO) database. We used topological analysis to determine the hub lncRNAs in the regulatory ceRNA network. Then, function enrichment analysis was performed using the clusterProfiler R package. Clinical information was downloaded from The Cancer Genome Atlas (TCGA) database and survival analysis was performed with Kaplan-Meier analysis.\nRESULTS: A total of 238 potential co-dysregulated competing triples were obtained in the lncRNA-associated ceRNA network in oral cancer, which consisted of 10 lncRNA nodes, 41 miRNA nodes and 122 mRNA nodes. Additionally, we found lncRNA HCG22 exhibiting superior potential as a diagnostic and prognostic marker of oral cancer.\nCONCLUSIONS: Our findings provide novel insights to understand the ceRNA regulation in oral cancer and identify a novel lncRNA as a potential molecular biomarker.", "claims": [{"id": "claim-method", "statement": "Survival analysis was estimated based on Kaplan-Meier curve analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32571304", "locator": "sections[21] \"Survival analysis\" paragraph 2", "quote": "Survival analysis was estimated based on Kaplan-Meier curve analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets supporting the conclusions of this article were retrieved from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/) with the accession number GSE74530 and the series matrix files were available at (ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE74nnn/GSE74530/matrix/). The raw data for data quality assessment was available at (https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE74530&format=file). The full data table of microarray platform GPL570 was available at (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL570). The human comprehensive gene annotation we used to identify lncRNAs was available at (ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_34/gencode.v34.annotation.gtf.gz). The case IDs and direct web links of all oral cancer samples obtained from the TCGA data portal (http://portal.gdc.cancer.gov/; dbGaP Study Accession: phs000178) by Bioconductor package TCGAbiolinks were shown in Additional file 2. Data banks/repositories corresponding to all datasets analyzed in this study were listed in Additional file 1.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32571304", "locator": "sections[30] \"Availability of data and materials\" paragraph 2", "quote": "The datasets supporting the conclusions of this article were retrieved from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/) with the accession number GSE74530 and the series matrix files were available at (ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE74nnn/GSE74530/matrix/). The raw data for data quality assessment was available at (https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE74530&format=file). The full data table of microarray platform GPL570 was available at (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL570). The human comprehensive gene annotation we used to identify lncRNAs was available at (ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_34/gencode.v34.annotation.gtf.gz). The case IDs and direct web links of all oral cancer samples obtained from the TCGA data portal (http://portal.gdc.cancer.gov/; dbGaP Study Accession: phs000178) by Bioconductor package TCGAbiolinks were shown in Additional file 2. Data banks/repositories corresponding to all datasets analyzed in this study were listed in Additional file 1."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:32571304"], "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:GSE74530"], "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:GSE74530"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32571304", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12920-020-00741-w", "sha256": "sha256:c1aa0e0df2a16357c0997658996807ac2d3d0d83fd491317c9494c07326dcdf8", "bytes": 50014, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12920-020-00741-w", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7310129", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE74530", "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=GSE74530", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE74530", "version": null, "note": "The datasets supporting the conclusions of this article were retrieved from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/) with the accession number GSE74530 and the series matrix files were available at (ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE74nnn/GSE74530/matrix/). The raw data for data quality assessment was available at (https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE74530&format=file). The full data table of microarray platform GPL570 was available at (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL570). The human comprehensive gene annotation we used to identify lncRNAs was available at (ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_34/gencode.v34.annotation.gtf.gz). The case IDs and direct web links of all oral cancer samples obtained from the TCGA data portal (http://portal.gdc.cancer.gov/; dbGaP Study Accession: phs000178) by Bioconductor package TCGAbiolinks were shown in Additional file 2. Data banks/repositories corresponding to all datasets analyzed in this study were listed in Additional file 1.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusions of this article were retrieved from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/) with the accession number GSE74530 and the series matrix files were available at (ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE74nnn/GSE74530/matrix/). The raw data for data quality assessment was available at (https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE74530&format=file). The full data table of microarray platform GPL570 was available at (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL570). The human comprehensive gene annotation we used to identify lncRNAs was available at (ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_34/gencode.v34.annotation.gtf.gz). The case IDs and direct web links of all oral cancer samples obtained from the TCGA data portal (http://portal.gdc.cancer.gov/; dbGaP Study Accession: phs000178) by Bioconductor package TCGAbiolinks were shown in Additional file 2. Data banks/repositories corresponding to all datasets analyzed in this study were listed in Additional file 1.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1922229", "GSM1922230", "GSM1922231", "GSM1922232", "GSM1922233", "GSM1922234", "GSM1922235", "GSM1922236", "GSM1922237", "GSM1922238", "GSM1922239", "GSM1922240"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from tumors and adjacent normal tissue from clinical oral cancer patients", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32571304:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:40d9d8b668ff36ea6ccf6b2c4b108026f5e335892e9a591704b174b7c0974cb4", "bytes": 1089, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab1", "version": null, "note": "The effect characteristic of miRNAs in oral squamous cell carcinoma (OSCC)", "structure": {"pmcid": "PMC7310129", "section_index": 15, "section_title": "Construction of the ceRNA network in oral cancer", "row_count": 9, "column_count": 4}, "table": {"label": "Table 1", "caption": "The effect characteristic of miRNAs in oral squamous cell carcinoma (OSCC)", "rows": [["miRNA", "Targets", "Effect characteristic", "Reference"], ["hsa-miR-139-5p", "AKT", "Inhibits oral cancer cell proliferation and induces cell apoptosis", "[36]"], ["hsa-miR-17-5p", "Casp-2/−7/− 8, Bcl-2 and DIALO", "Inhibits hypoxia-induced apoptosis", "[37]"], ["hsa-miR-107", "p53", "p53 upregulates miR-107 in normal condition", "[38]"], ["hsa-miR-375", "Sp1 and cyclin D1", "Inhibits cell growth and its expression is correlatedwith prognosis of TSCC", "[39]"], ["hsa-miR-455-5p", "UBE2B", "Binds SMAD3-specific promoter regions, leads toUBE2B downregulation, and contributes to oralcancer tumorigenesis", "[40]"], ["hsa-miR-137", "CDK6", "Arrests cell cycle at the G1-S checkpoint", "[41]"], ["hsa-miR-140-5p", "ADAM10", "Inhibits the invasion and migration of TSCC cells", "[42]"], ["hsa-miR-125b-5p", "BAK1", "Boosts the level of BAK1 that is controlling the apoptotic pathway", "[38]"]], "row_count": 9, "column_count": 4, "numeric_cells": 20, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:32571304:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:99c796f50dc9032d601783f344ce64454288db82be2685927c7053ae95962841", "bytes": 1656, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab2", "version": null, "note": "The list of differentially expressed genes (node degree > 5)", "structure": {"pmcid": "PMC7310129", "section_index": 17, "section_title": "Topological analysis of the ceRNA network", "row_count": 43, "column_count": 4}, "table": {"label": "Table 2", "caption": "The list of differentially expressed genes (node degree > 5)", "rows": [["Number", "Degree", "Name", "Type"], ["1", "27", "hsa-miR-17-5p", "miRNA"], ["2", "24", "HCP5", "lncRNA"], ["3", "21", "AGAP11", "lncRNA"], ["4", "19", "hsa-miR-24-3p", "miRNA"], ["5", "18", "hsa-miR-27a-3p", "miRNA"], ["6", "17", "hsa-miR-1297", "miRNA"], ["7", "17", "hsa-miR-23b-3p", "miRNA"], ["8", "16", "hsa-miR-140-5p", "miRNA"], ["9", "16", "hsa-miR-129-5p", "miRNA"], ["10", "15", "CRNDE", "lncRNA"], ["11", "15", "hsa-miR-22-3p", "miRNA"], ["12", "15", "hsa-miR-20b-5p", "miRNA"], ["13", "14", "HCG22", "lncRNA"], ["14", "13", "EPB41L4A-AS1", "lncRNA"], ["15", "13", "hsa-miR-507", "miRNA"], ["16", "13", "hsa-miR-107", "miRNA"], ["17", "13", "hsa-miR-216b-5p", "miRNA"], ["18", "12", "SOX21-AS1", "lncRNA"], ["19", "12", "hsa-miR-3619-5p", "miRNA"], ["20", "11", "UCA1", "lncRNA"], ["21", "11", "hsa-miR-761", "miRNA"], ["22", "9", "hsa-miR-490-3p", "miRNA"], ["23", "9", "hsa-miR-125b-5p", "miRNA"], ["24", "9", "hsa-miR-1244", "miRNA"], ["25", "9", "hsa-miR-139-5p", "miRNA"], ["26", "7", "YOD1", "mRNA"], ["27", "7", "LINC00491", "lncRNA"], ["28", "7", "hsa-miR-125a-5p", "miRNA"], ["29", "7", "hsa-miR-425-5p", "miRNA"], ["30", "7", "hsa-miR-363-3p", "miRNA"], ["31", "7", "hsa-miR-876-3p", "miRNA"], ["32", "7", "hsa-miR-455-5p", "miRNA"], ["33", "7", "hsa-miR-217", "miRNA"], ["34", "6", "NEK6", "mRNA"], ["35", "6", "MFHAS1", "mRNA"], ["36", "6", "RORA", "mRNA"], ["37", "6", "hsa-miR-33a-3p", "miRNA"], ["38", "6", "LINC00515", "lncRNA"], ["39", "6", "AC073321", "lncRNA"], ["40", "6", "hsa-miR-146b-5p", "miRNA"], ["41", "6", "hsa-miR-508-3p", "miRNA"], ["42", "6", "hsa-miR-135a-5p", "miRNA"]], "row_count": 43, "column_count": 4, "numeric_cells": 119, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:32571304:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e24c307d145e90db611c43eaa08dc790d1219e1f52bf5197f8cd25aca7ecb210", "bytes": 791, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#Tab3", "version": null, "note": "List of the 15 genes with the top betweenness centrality", "structure": {"pmcid": "PMC7310129", "section_index": 17, "section_title": "Topological analysis of the ceRNA network", "row_count": 16, "column_count": 4}, "table": {"label": "Table 3", "caption": "List of the 15 genes with the top betweenness centrality", "rows": [["Number", "Type", "name", "Betweenness Centrality"], ["1", "lncRNA", "HCP5", "0.26"], ["2", "lncRNA", "AGAP11", "0.16"], ["3", "miRNA", "hsa-miR-17-5p", "0.14"], ["4", "miRNA", "hsa-miR-24-3p", "0.13"], ["5", "miRNA", "hsa-miR-27a-3p", "0.10"], ["6", "miRNA", "hsa-miR-1297", "0.10"], ["7", "miRNA", "hsa-miR-22-3p", "0.09"], ["8", "lncRNA", "CRNDE", "0.09"], ["9", "miRNA", "hsa-miR-140-5p", "0.09"], ["10", "miRNA", "hsa-miR-129-5p", "0.08"], ["11", "lncRNA", "HCG22", "0.08"], ["12", "miRNA", "hsa-miR-216b-5p", "0.07"], ["13", "miRNA", "hsa-miR-507", "0.07"], ["14", "miRNA", "hsa-miR-23b-3p", "0.06"], ["15", "miRNA", "hsa-miR-107", "0.06"]], "row_count": 16, "column_count": 4, "numeric_cells": 43, "header_rows": 1, "locator": "section[17]/table-wrap[2]#Tab3"}}], "gaps": ["asset:data:geo:GSE74530 not downloaded", "asset:data:geo:GSE74530 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": "Survival analysis was estimated based on Kaplan-Meier curve analysis."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "centrality"}}], "targets": [], "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": ["GSE74530"], "resolved_accessions": ["GSE74530"], "statements": ["The datasets supporting the conclusions of this article were retrieved from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/) with the accession number GSE74530 and the series matrix files were available at (ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE74nnn/GSE74530/matrix/). The raw data for data quality assessment was available at (https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE74530&format=file). The full data table of microarray platform GPL570 was available at (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL570). The human comprehensive gene annotation we used to identify lncRNAs was available at (ftp://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_34/gencode.v34.annotation.gtf.gz). The case IDs and direct web links of all oral cancer samples obtained from the TCGA data portal (http://portal.gdc.cancer.gov/; dbGaP Study Accession: phs000178) by Bioconductor package TCGAbiolinks were shown in Additional file 2. Data banks/repositories corresponding to all datasets analyzed in this study were listed in Additional file 1."], "basis": "The paper names GSE74530 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:32571304", "data:geo:GSE74530", "asset:table:pmid:32571304:1", "asset:table:pmid:32571304:2", "asset:table:pmid:32571304:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE74530"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:36Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 41093, "completion_tokens": 1816, "cached_tokens": 784}}, "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:32571304", "type": "paper", "label": "pmid:32571304"}, {"id": "source:pmid:32571304", "type": "manuscript", "label": "PMID 32571304 full text"}, {"id": "data:geo:GSE74530", "type": "dataset", "label": "GEO GSE74530"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32571304", "type": "paper", "label": "pmid:32571304"}, {"id": "source:pmid:32571304", "type": "manuscript", "label": "PMID 32571304 full text"}, {"id": "data:geo:GSE74530", "type": "dataset", "label": "GEO GSE74530"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32571304", "type": "extraction", "used": ["source:pmid:32571304"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE74530", "type": "accession_resolution", "used": ["data:geo:GSE74530"], "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:32571304", "parent_hash": "sha256:176d203b642bea10eefb743a8e0670bec73280523ac3cb6ba39ed2de0f7b1f59", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE74530 licence not read", "asset:data:geo:GSE74530 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["SE74530&format=file). The full data table of microarray platform GPL570 was available at (https://ww"], "order_basis": "paper_text_order:2764", "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": ["Survival analysis was estimated based on Kaplan-Meier curve analysis."], "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":"2026-11-04T01:25:13+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}}}