{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30602391", "kind": "science-record", "revision": 7, "content_hash": "sha256:c0af26a573f0a8b3109b6691b4b2d24414422206d0927ded2ac3edcefa4f4cbb", "created_at": "2026-11-01T15:40:40Z", "updated_at": "2026-11-01T22:00:13Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of potential miRNA-mRNA regulatory network contributing to pathogenesis of HBV-related HCC.", "doi": "10.1186/s12967-018-1761-7", "pmid": "30602391", "authors": ["Weiyang Lou", "Jingxing Liu", "Bisha Ding", "Danni Chen", "Liang Xu", "Jun Ding", "Donghai Jiang", "Lin Zhou", "Shusen Zheng", "Weimin Fan"], "journal": "Journal of translational medicine", "year": 2019, "abstract": "BACKGROUND: Hepatitis B virus (HBV) is one of the major risk factors of hepatocellular carcinoma (HCC). Increasing evidence indicates that microRNA (miRNA)-mRNA axis is involved in HCC. However, a comprehensive miRNA-mRNA regulatory network in HBV-related HCC is still absent. This study aims to identify potential miRNA-mRNA regulatory pathways contributing to pathogenesis of HBV-related HCC.\nMETHODS: Microarray GSE69580 was downloaded from Gene Expression Omnibus (GEO) database. GEO2R and 'R-limma' were used to conduct differential expression analysis. The common miRNAs appeared in the two analytic sets were screened as potential differentially expressed miRNAs (DE-miRNAs). The prognostic roles of screened DE-miRNAs in HCC were further evaluated using Kaplan-Meier plotter database. Target genes of DE-miRNAs were predicted by miRNet. Then, protein-protein interaction (PPI) networks were established for these targets via the STRING database, after which hub genes in the networks were identified by Cytoscape. Functional annotation and pathway enrichment analyses for the target genes were performed through DAVID database. Three enriched pathways related to HBV-related HCC were selected for further analysis and potential target genes commonly appeared in all three pathways were screened. Cytoscape was employed to construct miRNA-hub gene network. The expression and correlation of potential miRNAs and targets were further detected in clinical HBV-related HCC samples by qRT-PCR.\nRESULTS: 7 upregulated and 9 downregulated DE-miRNAs were accessed. 5 of 7 upregulated DE-miRNAs and 5 of 7 downregulated DE-miRNAs indicated significant prognostic roles in HCC. 2312 and 1175 target genes were predicted for the upregulated and downregulated DE-miRNAs, respectively. TP53 was identified as the hub gene in the PPI networks. Pathway enrichment analysis suggested that these predicted targets were linked to hepatitis B, pathways in cancer, microRNAs in cancer and viral carcinogenesis. Further analysis of these pathways screened 20 and 16 target genes for upregulated and downregulated DE-miRNAs, respectively. By detecting the expression of 36 target genes, six candidate target genes were identified. Finally, a potential miRNA-mRNA regulatory network was established based on the results of qRT-PCR and expression correlation analysis.\nCONCLUSIONS: In the study, potential miRNA-mRNA regulatory pathways were identified, exploring the underlying pathogenesis and effective therapy strategy of HBV-related HCC.", "claims": [{"id": "claim-method", "statement": "The differences between two groups were estimated by a two-tailed Student’s t-test. Spearman correlation coefficients were calculated to evaluate the correlations.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30602391", "locator": "sections[15] \"Statistical analysis\" paragraph 2", "quote": "The differences between two groups were estimated by a two-tailed Student’s t-test. Spearman correlation coefficients were calculated to evaluate the correlations."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data were deposited in the Gene Expression Omnibus (GEO) database (Accession number: GSE69580). Besides, please contact author for data and materials requests.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30602391", "locator": "sections[27] \"ack\" paragraph 1", "quote": "The microarray data were deposited in the Gene Expression Omnibus (GEO) database (Accession number: GSE69580). Besides, please contact author for data and materials requests."}], "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:30602391"], "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:GSE69580"], "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:GSE69580"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30602391", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-018-1761-7", "sha256": "sha256:7050d06d3b48c343268ea82ffb73649fa50ff302a813bfc85ea62974c30273cb", "bytes": 36186, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-018-1761-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6317219", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE69580", "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=GSE69580", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE69580", "version": null, "note": "The microarray data were deposited in the Gene Expression Omnibus (GEO) database (Accession number: GSE69580). Besides, please contact author for data and materials requests.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data were deposited in the Gene Expression Omnibus (GEO) database (Accession number: GSE69580). Besides, please contact author for data and materials requests.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1704144", "GSM1704145", "GSM1704146", "GSM1704147", "GSM1704148", "GSM1704149", "GSM1704150", "GSM1704151", "GSM1704152", "GSM1704153"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "10850", "taxon": "Homo sapiens", "title": "Differential miRNA expression profiles betweenHBV-related  HCC tumor versus non-tumor liver tissue", "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:30602391:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c28ee8977141d8333ab1c5afd9d43280c68c7a2a379824a21f1d4dbdbc30fe80", "bytes": 724, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab1", "version": null, "note": "Common (GEO2R and R-limma) differentially expressed miRNAs (DE-miRNAs) between HBV-related HCC tumor versus non-tumor liver tissue", "structure": {"pmcid": "PMC6317219", "section_index": 17, "section_title": "Candidate DE-miRNAs Identification and survival analysis", "row_count": 8, "column_count": 5}, "table": {"label": "Table 1", "caption": "Common (GEO2R and R-limma) differentially expressed miRNAs (DE-miRNAs) between HBV-related HCC tumor versus non-tumor liver tissue", "rows": [["Upregulated DE-miRNA", "log2FC", "t", "B", "P value"], ["hsa-miR-25-3p", "1.86", "5.2", "− 0.0946", "7.03E−04"], ["hsa-miR-501-3p", "7.01", "19.1", "8.4883", "3.14E−08"], ["hsa-miR-93-5p", "1.84", "3.66", "− 2.2376", "5.84E−03"], ["hsa-miR-532-5p", "5.83", "3.46", "− 2.5537", "7.99E−03"], ["hsa-miR-106b-5p", "2.68", "5.37", "0.1219", "5.67E−04"], ["hsa-miR-21-5p", "3.89", "6.85", "1.8157", "1.03E−04"], ["hsa-miR-151-3p", "3.38", "5.38", "0.14", "5.57E−04"]], "row_count": 8, "column_count": 5, "numeric_cells": 35, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:30602391:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ae8cab3578fb81993d2e03b22dbdc51cbec796cb45014ebf7ac77b6d3c5feb25", "bytes": 552, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab2", "version": null, "note": "The target number of the upregulated and downregulated DE-miRNAs", "structure": {"pmcid": "PMC6317219", "section_index": 18, "section_title": "Target prediction and analysis of candidate DE-miRNAs", "row_count": 7, "column_count": 4}, "table": {"label": "Table 2", "caption": "The target number of the upregulated and downregulated DE-miRNAs", "rows": [["Upregulated DE-miRNA", "Number", "Downregulated DE-miRNA", "Number"], ["hsa-miR-93-5p", "1220", "hsa-let-7c-5p", "516"], ["hsa-miR-106b-5p", "1091", "hsa-miR-125b-5p", "432"], ["hsa-miR-21-5p", "612", "hsa-miR-99a-5p", "133"], ["hsa-miR-25-3p", "518", "hsa-miR-139-5p", "105"], ["hsa-miR-501-3p", "69", "hsa-miR-486-5p", "67"], ["Total", "2312", "Total", "1175"]], "row_count": 7, "column_count": 4, "numeric_cells": 22, "header_rows": 1, "locator": "section[18]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:30602391:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:68b67019fb9ff170c25de4b67fc5d8ba2a528713b523a9e95b9358c5954fd275", "bytes": 583, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[2]#Tab3", "version": null, "note": "Hub genes identified in the PPI networks", "structure": {"pmcid": "PMC6317219", "section_index": 18, "section_title": "Target prediction and analysis of candidate DE-miRNAs", "row_count": 12, "column_count": 4}, "table": {"label": "Table 3", "caption": "Hub genes identified in the PPI networks", "rows": [["Upregulated DE-miRNAs", "Downregulated DE-miRNAs"], ["Gene symbol", "Degree", "Gene symbol", "Degree"], ["TP53", "336", "TP53", "248"], ["UBC", "274", "UBA52", "193"], ["RPS27A", "255", "MYC", "177"], ["GAPDH", "249", "AKT1", "165"], ["MYC", "223", "UBB", "163"], ["PHLPP2", "215", "EGFR", "149"], ["HSP90AA1", "209", "JUN", "144"], ["TOP2A", "205", "HSP90AA1", "140"], ["MAPK1", "203", "PIK3CA", "134"], ["JUN", "193", "ACLY", "119"]], "row_count": 12, "column_count": 4, "numeric_cells": 26, "header_rows": 2, "locator": "section[18]/table-wrap[2]#Tab3"}}], "gaps": ["asset:data:geo:GSE69580 not downloaded", "asset:data:geo:GSE69580 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The differences between two groups were estimated by a two-tailed Student’s t-test. Spearman correlation coefficients were calculated to evaluate the correlations."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "plots were created, and hazard ratio (HR), 95% confidence in", "p_value": "erval (CI) and log rank P-value were displayed on the w", "confidence_interval": "hazard ratio (HR), 95% confidence interval (CI) and log rank P-val"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log rank"}}, {"id": "method-4", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "limma"}}, {"id": "method-5", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-6", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["spearman_rho"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: spearman."}, "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": ["GSE69580"], "resolved_accessions": ["GSE69580"], "statements": ["The microarray data were deposited in the Gene Expression Omnibus (GEO) database (Accession number: GSE69580). Besides, please contact author for data and materials requests."], "basis": "The paper names GSE69580 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["spearman_rho"], "assets": ["source:pmid:30602391", "data:geo:GSE69580", "asset:table:pmid:30602391:1", "asset:table:pmid:30602391:2", "asset:table:pmid:30602391:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE69580"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:19Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29241, "completion_tokens": 2260, "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:30602391", "type": "paper", "label": "pmid:30602391"}, {"id": "source:pmid:30602391", "type": "manuscript", "label": "PMID 30602391 full text"}, {"id": "data:geo:GSE69580", "type": "dataset", "label": "GEO GSE69580"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30602391", "type": "paper", "label": "pmid:30602391"}, {"id": "source:pmid:30602391", "type": "manuscript", "label": "PMID 30602391 full text"}, {"id": "data:geo:GSE69580", "type": "dataset", "label": "GEO GSE69580"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30602391", "type": "extraction", "used": ["source:pmid:30602391"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE69580", "type": "accession_resolution", "used": ["data:geo:GSE69580"], "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:30602391", "parent_hash": "sha256:e43df454e902ce2bd06c706dff808ce837cc073a9c9732f03ada03aae10771ba", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE69580 licence not read", "asset:data:geo:GSE69580 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": 0.99, "evidence": ["to pathogenesis of HBV-related HCC. METHODS: Microarray GSE69580 was downloaded from Gene Expression", "Oncomine database, which is an online cancer microarray database. P-value < 1E−4, fold change > 2 an"], "order_basis": "paper_text_order:466", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["e Academy of Sciences (Shanghai, China). The cell line was maintained in Dulbecco’s modified Eagle’s medium (DMEM;"], "order_basis": "paper_text_order:5257", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["spearman_rho"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The differences between two groups were estimated by a two-tailed Student’s t-test. Spearman correlation coefficients were calculated to evaluate the correlations."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:38:50+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}}}