{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30909944", "kind": "science-record", "revision": 4, "content_hash": "sha256:f35c6b04c6b4960be836930e1767689b6b46804ce00512027542305ad70eb5b1", "created_at": "2026-11-01T15:40:43Z", "updated_at": "2026-11-01T21:22:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Deciphering the mechanism of Indirubin and its derivatives in the inhibition of Imatinib resistance using a \"drug target prediction-gene microarray analysis-protein network construction\" strategy.", "doi": "10.1186/s12906-019-2471-2", "pmid": "30909944", "authors": ["Huayao Li", "Lijuan Liu", "Jing Zhuang", "Cun Liu", "Chao Zhou", "Jing Yang", "Chundi Gao", "Gongxi Liu", "Changgang Sun"], "journal": "BMC complementary and alternative medicine", "year": 2019, "abstract": "BACKGROUND: The introduction of imatinib revolutionized the treatment of chronic myeloid leukaemia (CML), substantially extending patient survival. However, imatinib resistance is currently a clinical problem for CML. It is very importantto find a strategy to inhibit imatinib resistance.\nMETHODS: (1) We Identified indirubin and its derivatives and predicted its putative targets; (2) We downloaded data of the gene chip GSE2810 from the Gene Expression Omnibus (GEO) database and performed GEO2R analysis to obtain differentially expressed genes (DEGs); and (3) we constructed a P-P network of putative targets and DEGs to explore the mechanisms of action and to verify the results of molecular docking.\nRESULT: We Identified a total of 42 small-molecule compounds, of which 15 affected 11 putative targets, indicating the potential to inhibit imatinib resistance; the results of molecular docking verified these results. Six biomarkers of imatinib resistance were characterised by analysing DEGs.\nCONCLUSION: The 15 small molecule compounds inhibited imatinib resistance through the cytokine-cytokine receptor signalling pathway, the JAK-stat pathway, and the NF-KB signalling pathway. Indirubin and its derivatives may be new drugsthat can combat imatinib resistance.", "claims": [{"id": "claim-method", "statement": "The analysis was carried out by using GEO2R, an online analysis tool for the GEO database, based on R language.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30909944", "locator": "sections[6] \"Identify imatinib resistance related genes\" paragraph 2", "quote": "The analysis was carried out by using GEO2R, an online analysis tool for the GEO database, based on R language."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analysed during this study are included in this published article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30909944", "locator": "sections[20] \"Availability of data and materials\" paragraph 2", "quote": "All data generated or analysed during this study are included in this published article."}], "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:30909944"], "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:GSE2810"], "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:GSE2810"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30909944", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12906-019-2471-2", "sha256": "sha256:fb178c11d1e57517f8278c10d27a5c5448f2e31fcd0429278308fbe575ebdfbb", "bytes": 42791, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12906-019-2471-2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6434895", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE2810", "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=GSE2810", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE2810", "version": null, "note": "All data generated or analysed during this study are included in this published article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analysed during this study are included in this published article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM60884", "GSM60885", "GSM60886", "GSM60887", "GSM60888", "GSM60889", "GSM60890", "GSM60891", "GSM60892", "GSM83839"], "sample_count": 10, "group_sizes": null, "group_sizes_basis": null, "platform": "2531", "taxon": "Homo sapiens", "title": "Comparative analysis of BCR-ABL tyrosine kinase inhibitors in BCR-ABL positive K562 cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30909944:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4362a9188575adbd28b4d11881b12109584e34fe000ce2f7a8b9f807fd73f83c", "bytes": 199, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab1", "version": null, "note": "Indirubin and 41 derivatives and putative targets", "structure": {"pmcid": "PMC6434895", "section_index": 12, "section_title": "Indirubin and 41 derivatives and putative targets", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Indirubin and 41 derivatives and putative targets", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:30909944:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:26b6ff025bf15547a0ac823ecc8b67981670dfea9154183085749192ec7cc693", "bytes": 1375, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab2", "version": null, "note": "The top 10 significantly up-regulated DEGs and down-regulated DEGs", "structure": {"pmcid": "PMC6434895", "section_index": 13, "section_title": "Imatinib resistance related genes", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "The top 10 significantly up-regulated DEGs and down-regulated DEGs", "rows": [["Group", "Genesymbol", "Gene Description", "Fold Change"], ["Upregulated genes", "CCL13", "C-C motif chemokine 13", "9.39035"], ["MAPK11", "Mitogen-activated protein kinase 11", "7.52975"], ["PDCD4", "Programmed cell death protein 4", "7.43475"], ["BCL2", "Bcl2-associated agonist of cell death", "7.22081"], ["CCL27", "C-C motif chemokine 27", "6.79919"], ["TCEB3B", "transcription elongation factor B subunit 3B", "6.65061"], ["ANAPC10", "anaphase promoting complex subunit 10", "6.21695"], ["IL1R1", "interleukin 1 receptor type 1", "6.14025"], ["TCF4", "transcription factor 4", "5.79877"], ["TFAP2A", "transcription factor AP-2 alpha", "5.65156"], ["Downregulated genes", "MLH1", "MutL homolog 1", "−10.7446"], ["BCL10", "B-cell CLL/lymphoma 10", "−8.27759"], ["MAP3K4", "mitogen-activated protein kinase kinase kinase 4", "−8.1475"], ["CDK9", "cyclin dependent kinase 9", "−6.66841"], ["APOB", "apolipoprotein B", "−6.5818"], ["PDGFC", "platelet derived growth factor C", "−6.62762"], ["IL10RA", "interleukin 10 receptor subunit alpha", "−5.64569"], ["IL12A", "interleukin 12A", "−5.49548"], ["CDC14A", "cell division cycle 14A", "−5.20635"], ["ALOX5", "arachidonate 5-lipoxygenase", "−5.20383"]], "row_count": 21, "column_count": 4, "numeric_cells": 45, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:30909944:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7e4c9c6f39dfb4bd2843cca56a3de4a9d3933b88feea3ce42617e4d76c517d49", "bytes": 4004, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#Tab3", "version": null, "note": "The 62 major targets information of P-P network", "structure": {"pmcid": "PMC6434895", "section_index": 13, "section_title": "Imatinib resistance related genes", "row_count": 63, "column_count": 4}, "table": {"label": "Table 3", "caption": "The 62 major targets information of P-P network", "rows": [["ID", "Major target", "Uniprot ID", "Gene name"], ["MT1", "Interleukin-6", "P05231", "IL6"], ["MT2", "Epidermal growth factor receptor", "P00533", "EGFR"], ["MT3", "Transcription factor AP-1", "P05412", "JUN"], ["MT4", "Apoptosis regulator Bcl-2", "P10415", "BCL2"], ["MT5", "Heat shock protein HSP 90-alpha", "P07900", "HSP90AA1"], ["MT6", "Serine-protein kinase ATM", "Q13315", "ATM"], ["MT7", "Tyrosine-protein kinase JAK2", "O60674", "JAK2"], ["MT8", "Phosphatidylinositol 4,5-bisphosphate 3-kinase catalytic subunit delta isoform", "O00329", "PIK3CD"], ["MT9", "Receptor tyrosine-protein kinase erbB-2", "P04626", "ERBB2"], ["MT10", "Baculoviral IAP repeat-containing protein 5", "O15392", "BIRC5"], ["MT11", "Interleukin-1 beta", "P01584", "IL1B"], ["MT12", "Receptor-type tyrosine-protein phosphatase C", "P08575", "PTPRC"], ["MT13", "Mitogen-activated protein kinase 11", "Q15759", "MAPK11"], ["MT14", "Interleukin-10", "P22301", "IL10"], ["MT15", "C-X-C chemokine receptor type 4", "P61073", "CXCR4"], ["MT16", "Amyloid-beta A4 protein", "P05067", "APP"], ["MT17", "Inhibitor of nuclear factor kappa-B kinase subunit alpha", "O15111", "CHUK"], ["MT18", "POU domain, class 5, transcription factor 1", "Q01860", "POU5F1"], ["MT19", "Cyclin-dependent-like kinase 5", "Q00535", "CDK5"], ["MT20", "ATP-binding cassette sub-family G member 2", "Q9UNQ0", "ABCG2"], ["MT21", "Cation-independent mannose-6-phosphate receptor", "P11717", "IGF2R"], ["MT22", "Cyclin-dependent kinase inhibitor 1B", "P46527", "CDKN1B"], ["MT23", "ALK tyrosine kinase receptor", "Q9UM73", "ALK"], ["MT24", "E3 ubiquitin-protein ligase CBL", "P22681", "CBL"], ["MT25", "Substance-P receptor", "P25103", "TACR1"], ["MT26", "Wilms tumor protein", "P19544", "WT1"], ["MT27", "ETS-related transcription factor Elf-3", "P78545", "ELF3"], ["MT28", "G1/S-specific cyclin-D2", "P30279", "CCND2"], ["MT29", "Amine oxidase [flavin-containing] A", "P21397", "MAOA"], ["MT30", "Metalloproteinase inhibitor 1", "P20414", "TIMP1"], ["MT31", "Kinesin-like protein KIF11", "P52732", "KIF11"], ["MT32", "Cell division cycle protein 16 homolog", "Q13042", "CDC16"], ["MT33", "Nitric oxide synthase, brain", "P29475", "NOS1"], ["MT34", "DNA (cytosine-5)-methyltransferase 3B", "Q9UBC3", "DNMT3B"], ["MT35", "1-phosphatidylinositol 4,5-bisphosphate phosphodiesterase gamma-1", "P19174", "PLCG1"], ["MT36", "POU domain class 2-associating factor 1", "Q16633", "POU2AF1"], ["MT37", "E3 ubiquitin-protein ligase XIAP", "P98170", "XIAP"], ["MT38", "Anaphase-promoting complex subunit 10", "Q9UM13", "ANAPC10"], ["MT39", "Runt-related transcription factor 1", "Q01196", "RUNX1"], ["MT40", "WD repeat and FYVE domain-containing protein 2", "Q96P53", "WDFY2"], ["MT41", "M-phase inducer phosphatase 1", "P30304", "CDC25A"], ["MT42", "D(2) dopamine receptor", "P14416", "DRD2"], ["MT43", "CASP8 and FADD-like apoptosis regulator", "O15519", "CASP8"], ["MT44", "Cyclin-dependent kinase 3", "Q00526", "CDK3"], ["MT45", "Tyrosine-protein phosphatase non-receptor type 2", "P17706", "PTPN2"], ["MT46", "DNA mismatch repair protein Mlh1", "P40692", "MLH1"], ["MT47", "Wee1-like protein kinase", "P30291", "WEE1"], ["MT48", "Neural cell adhesion molecule 1", "P30291", "NCAM1"], ["MT49", "Caspase-9", "P55211", "CASP9"], ["MT50", "Toll-like receptor 3", "O15455", "TLR3"], ["MT51", "C-X-C motif chemokine 2", "P19875", "CXCL2"], ["MT52", "5-hydroxytryptamine receptor 1A", "P08908", "HTR1A"], ["MT53", "Mothers against decapentaplegic homolog 7", "O15105", "SMAD7"], ["MT54", "Transcription factor 4", "P15884", "TCF4"], ["MT55", "Tyrosine-protein kinase JAK3", "P52333", "JAK3"], ["MT56", "Interleukin-2 receptor subunit alpha", "P01589", "IL2RA"], ["MT57", "Non-receptor tyrosine-protein kinase TYK2", "P29597", "TYK2"], ["MT58", "Dual specificity protein phosphatase CDC14A", "Q9UNH5", "CDC14A"], ["MT59", "Cyclin-dependent kinase 9", "P50750", "CDK9"], ["MT60", "Presenilin-1", "P49768", "PSEN1"], ["MT61", "Apolipoprotein B-100", "P04114", "APOB"], ["MT62", "C-X-C motif chemokine 13", "O43927", "CXCL13"]], "row_count": 63, "column_count": 4, "numeric_cells": 164, "header_rows": 1, "locator": "section[13]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:30909944:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3bb7b385177bef1e700347d977334fbb1a11553572d6b4c68d91a667c474fc92", "bytes": 380, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[3]#Tab4", "version": null, "note": "The docking results of molecule compounds and their putative targets. ‘4 + EGFR’ represents the molecular docking of the indirubin derivative numbered 4 with EGFR, and Score represents the score Identified by molecular docking", "structure": {"pmcid": "PMC6434895", "section_index": 13, "section_title": "Imatinib resistance related genes", "row_count": 0, "column_count": 0}, "table": {"label": "Table 4", "caption": "The docking results of molecule compounds and their putative targets. ‘4 + EGFR’ represents the molecular docking of the indirubin derivative numbered 4 with EGFR, and Score represents the score Identified by molecular docking", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[13]/table-wrap[3]#Tab4"}}], "gaps": ["asset:data:geo:GSE2810 not downloaded", "asset:data:geo:GSE2810 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "GEO2R analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The analysis was carried out by using GEO2R, an online analysis tool for the GEO database, based on R language."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (GEO2R analysis), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE2810"], "resolved_accessions": ["GSE2810"], "statements": ["All data generated or analysed during this study are included in this published article."], "basis": "The paper names GSE2810 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": [], "assets": ["source:pmid:30909944", "data:geo:GSE2810", "asset:table:pmid:30909944:1", "asset:table:pmid:30909944:2", "asset:table:pmid:30909944:3", "asset:table:pmid:30909944:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE2810"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32888, "completion_tokens": 1007, "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:30909944", "type": "paper", "label": "pmid:30909944"}, {"id": "source:pmid:30909944", "type": "manuscript", "label": "PMID 30909944 full text"}, {"id": "data:geo:GSE2810", "type": "dataset", "label": "GEO GSE2810"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30909944", "type": "paper", "label": "pmid:30909944"}, {"id": "source:pmid:30909944", "type": "manuscript", "label": "PMID 30909944 full text"}, {"id": "data:geo:GSE2810", "type": "dataset", "label": "GEO GSE2810"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30909944", "type": "extraction", "used": ["source:pmid:30909944"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE2810", "type": "accession_resolution", "used": ["data:geo:GSE2810"], "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:30909944", "parent_hash": "sha256:28b9f0b40c961b3af92db2ecc93b857bf575f9e190945accfe315534db593e88", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE2810 licence not read", "asset:data:geo:GSE2810 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["istance using a \"drug target prediction-gene microarray analysis-protein network construction\" strat"], "order_basis": "paper_text_order:92", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:16:03+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}}}