{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40860944", "kind": "science-record", "revision": 4, "content_hash": "sha256:f31224a869df0893dfcbd7cdcecd068940c38e7f9b68dc924857c0e85cc1f8a3", "created_at": "2026-11-01T20:30:58Z", "updated_at": "2026-11-01T22:57:06Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Machine Learning-Based Identification and Experimental Validation of Hub Ferroptosis-Related Cuproptosis Genes in Lupus Nephritis.", "doi": "10.2147/JIR.S526572", "pmid": "40860944", "authors": ["Su Zhang", "Weitao Hu", "Yifang Zhang", "Chunyan Huang", "Ziqiong He", "Jing Xu", "Shihong Lin", "Baoya Yang", "Xiaoqing Chen"], "journal": "Journal of inflammation research", "year": 2025, "abstract": "Background: The role of ferroptosis and cuproptosis in lupus nephritis (LN) is unclear. The aim of this study was to explore the expression and effects of ferroptosis-related cuproptosis genes (FRCGs) in LN using bioinformatics and experimental validation.\nMethods: The LN-related datasets GSE112943 and GSE32591 were downloaded from the GEO database. We collected 834 ferroptosis-related genes and 1046 cuproptosis-related genes. Weighted gene co-expression network analysis (WGCNA) and machine learning algorithms identified hub FRCGs in the LN. We then analyzed the relationship of hub FRCGs with immune infiltration and clinical traits. Finally, we validated the expression of the hub FRCGs in vivo and in vitro.\nResults: A total of 31 differentially expressed FRCGs (DE-FRCGs) in the LN were screened, which were mainly involved in the response to metal ions and oxidative stress. And they were engaged in autophagy-animal signaling pathway. Machine learning identified two hub FRCGs (JUN and ZFP36). Public datasets, clinical samples, in vivo and in vitro experiments confirmed that hub FRCGs expression was reduced in the LN group compared to control group. Immune infiltration analysis displayed that monocytes and macrophages were the major infiltrating cells in LN kidneys. In LN, hub genes were negatively correlated with macrophages and monocytes.\nConclusion: This study elucidates the contribution of ferroptosis-related cuproptosis genes to the onset and progression of LN. JUN and ZFP36 were potentially effective biomarkers of LN and may be potential targets for LN therapy in the future.", "claims": [{"id": "claim-method", "statement": "The training cohort was then screened for differentially expressed genes (DEGs) with the “limma” package of R.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40860944", "locator": "sections[3] \"Acquisition of Datasets and Screening of Differentially Expressed Genes\" paragraph 2", "quote": "The training cohort was then screened for differentially expressed genes (DEGs) with the “limma” package of R."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated and/or analysed during the current study are available in the [GEO] repository, [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112943].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40860944", "locator": "sections[41] \"Data Availability Statement\" paragraph 2", "quote": "The datasets generated and/or analysed during the current study are available in the [GEO] repository, [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112943]."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In GSE112943, limma screening identified 12,520 DEGs, and their intersection with WGCNA modules, ferroptosis-related genes, and cuproptosis-related genes yielded 31 DE-FRCGs.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40860944", "locator": "sections[29] \"Identification of DEGs\" paragraph 2", "quote": "A total of 12520 DEGs (Supplementary material) were screened in the LN and NC groups, including 7151 up-regulated genes and 5369 down-regulated genes (Figure 2C and D)."}, {"asset": "source:pmid:40860944", "locator": "sections[31] \"Acquisition and Functional Enrichment Analysis of DE-FRCGs\" paragraph 2", "quote": "The DEGs, WGCNAs, FRGs and CRGs were taken to intersect to obtain the 31 DE-FRCGs in the LN (Figure 3A)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "In GSE112943, limma screening identified 12,520 DEGs, and their intersection with WGCNA modules, ferroptosis-related genes, and cuproptosis-related genes yielded 31 DE-FRCGs.", "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:40860944"], "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:GSE112943"], "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:GSE112943"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40860944", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/JIR.S526572", "sha256": "sha256:0828bd79866e49d902db513ef61e4724e49f4e5a440172381f354cd78ed87098", "bytes": 42438, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/JIR.S526572", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12372846", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE112943", "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=GSE112943", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE112943", "version": null, "note": "The datasets generated and/or analysed during the current study are available in the [GEO] repository, [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112943].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analysed during the current study are available in the [GEO] repository, [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112943].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3091745", "GSM3091746", "GSM3091747", "GSM3091748", "GSM3091749", "GSM3091750", "GSM3091751", "GSM3091752", "GSM3091753", "GSM3091754", "GSM3091755", "GSM3091756", "GSM3091757", "GSM3091758", "GSM3091759", "GSM3091760", "GSM3091765", "GSM3091766", "GSM3091767", "GSM3091768", "GSM3091769", "GSM3091770", "GSM3091771", "GSM3091772", "GSM3091773", "GSM3091774", "GSM3091775", "GSM3091776", "GSM3091777", "GSM3091778", "GSM3091779", "GSM3091780", "GSM3091781", "GSM3091782", "GSM3091783", "GSM3091784", "GSM3091785", "GSM3091786", "GSM3091787", "GSM3091788", "GSM3091789", "GSM3091790", "GSM3091791", "GSM3091792", "GSM3091793", "GSM3091794", "GSM3091795"], "sample_count": 47, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression of cutaneous lupus skin samples and lupus nephritis kidney samples", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE32591", "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=GSE32591", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32591", "version": null, "note": "The datasets generated and/or analysed during the current study are available in the [GEO] repository, [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112943].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and/or analysed during the current study are available in the [GEO] repository, [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112943].", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM807842", "GSM807843", "GSM807844", "GSM807845", "GSM807846", "GSM807847", "GSM807848", "GSM807849", "GSM807850", "GSM807851", "GSM807852", "GSM807853", "GSM807854", "GSM807855", "GSM807856", "GSM807857", "GSM807858", "GSM807859", "GSM807860", "GSM807861", "GSM807862", "GSM807863", "GSM807864", "GSM807865", "GSM807866", "GSM807867", "GSM807868", "GSM807869", "GSM807870", "GSM807871", "GSM807872", "GSM807873", "GSM807874", "GSM807875", "GSM807876", "GSM807877", "GSM807878", "GSM807879", "GSM807880", "GSM807881", "GSM807882", "GSM807883", "GSM807884", "GSM807885", "GSM807886", "GSM807887", "GSM807888", "GSM807889", "GSM807890", "GSM807891", "GSM807892", "GSM807893", "GSM807894", "GSM807895", "GSM807896", "GSM807897", "GSM807898", "GSM807899", "GSM807900", "GSM807901", "GSM807902", "GSM807903", "GSM807904", "GSM807905", "GSM807906", "GSM807907", "GSM807908", "GSM807909", "GSM807910", "GSM807911", "GSM807912", "GSM807913", "GSM807914", "GSM807915", "GSM807916", "GSM807917", "GSM807918", "GSM807919", "GSM807920", "GSM807921", "GSM807922", "GSM807923", "GSM807924", "GSM807925", "GSM807926", "GSM807927", "GSM807928", "GSM807929", "GSM807930", "GSM807931", "GSM807932", "GSM807933", "GSM807934"], "sample_count": 93, "group_sizes": null, "group_sizes_basis": null, "platform": "14663", "taxon": "Homo sapiens", "title": "Expression data from human with lupus nephritis (LN)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE112943 not downloaded", "asset:data:geo:GSE112943 licence not read", "asset:data:geo:GSE32591 not downloaded", "asset:data:geo:GSE32591 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The training cohort was then screened for differentially expressed genes (DEGs) with the “limma” package of R."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "Protein-Protein Interaction"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE112943", "GSE32591"], "resolved_accessions": ["GSE112943", "GSE32591"], "statements": ["The datasets generated and/or analysed during the current study are available in the [GEO] repository, [https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE112943]."], "basis": "The paper names GSE112943, GSE32591 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:40860944", "data:geo:GSE112943"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE112943"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:00:34Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12489, "completion_tokens": 2197, "cached_tokens": 128}}, "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:40860944", "type": "paper", "label": "pmid:40860944"}, {"id": "source:pmid:40860944", "type": "manuscript", "label": "PMID 40860944 full text"}, {"id": "data:geo:GSE112943", "type": "dataset", "label": "GEO GSE112943"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40860944", "type": "paper", "label": "pmid:40860944"}, {"id": "source:pmid:40860944", "type": "manuscript", "label": "PMID 40860944 full text"}, {"id": "data:geo:GSE112943", "type": "dataset", "label": "GEO GSE112943"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40860944", "type": "extraction", "used": ["source:pmid:40860944"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE112943", "type": "accession_resolution", "used": ["data:geo:GSE112943"], "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:40860944", "parent_hash": "sha256:e8545c404db83e4c402714a4e7193606438ae21c7f0072b68446474890abc6c6", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE112943 licence not read", "asset:data:geo:GSE112943 not downloaded", "asset:data:geo:GSE32591 licence not read", "asset:data:geo:GSE32591 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["we validated the expression of the hub FRCGs in vivo and in vitro. Results: A total of 31 differe", "d ZFP36). Public datasets, clinical samples, in vivo and in vitro experiments confirmed that hub", "in several studies as a commonly used lupus mouse model,29 and female C57BL/6 mice of the same week", "easured weekly from 16 weeks of age, and the mice were killed at 20 weeks of age after modeling. Sp"], "order_basis": "paper_text_order:781", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["b genes was high (Figure 5C). The results of RT-qPCR of PBMC and IHC staining of paraffin section", "enes was high (Figure 5C). The results of RT-qPCR of PBMC and IHC staining of paraffin section"], "order_basis": "paper_text_order:7077", "id": "assay:2"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["gure 5C). The results of RT-qPCR of PBMC and IHC staining of paraffin sections of kidney tiss"], "order_basis": "paper_text_order:7097", "id": "assay:3"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The training cohort was then screened for differentially expressed genes (DEGs) with the “limma” package of R."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:24:41+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}}}