{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38613800", "kind": "science-record", "revision": 3, "content_hash": "sha256:69488f050179e86bc023791a5efffd5b1dfadf080565e7422defa3e0609b5ccb", "created_at": "2026-11-01T19:20:35Z", "updated_at": "2026-11-01T22:11:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PROS1 is a crucial gene in the macrophage efferocytosis of diabetic foot ulcers: a concerted analytical approach through the prisms of computer analysis.", "doi": "10.18632/aging.205732", "pmid": "38613800", "authors": ["Hongshuo Shi", "Zhicheng Zhang", "Xin Yuan", "Guobin Liu", "Weijing Fan", "Wenbo Wang"], "journal": "Aging", "year": 2024, "abstract": "BACKGROUND: Diabetic foot ulcers (DFUs) pose a serious long-term threat because of elevated mortality and disability risks. Research on its biomarkers is still, however, very limited. In this paper, we have effectively identified biomarkers linked with macrophage excretion in diabetic foot ulcers through the application of bioinformatics and machine learning methodologies. These findings were subsequently validated using external datasets and animal experiments. Such discoveries are anticipated to offer novel insights and approaches for the early diagnosis and treatment of DFU.\nMETHODS: In this work, we used the Gene Expression Omnibus (GEO) database's datasets GSE68183 and GSE80178 as the training dataset to build a gene model using machine learning methods. After that, we used the training and validation sets to validate the model (GSE134431). On the model genes, we performed enrichment analysis using both gene set variant analysis (GSVA) and gene set enrichment analysis (GSEA). Additionally, the model genes were subjected to immunological association and immune function analyses.\nRESULTS: In this study, PROS1 was identified as a potential key target associated with macrophage efflux in DFU by machine learning and bioinformatics approaches. Subsequently, the key biomarker status of PROS1 in DFU was also confirmed by external datasets. In addition, PROS1 also plays a key role in macrophage exudation in DFU. This gene may be associated with macrophage M1, CD4 memory T cells, naïve B cells, and macrophage M2, and affects IL-17, Rap1, hedgehog, and JAK-STAT signaling pathways.\nCONCLUSIONS: PROS1 was identified and validated as a biomarker for DFU. This finding has the potential to provide a target for macrophage clearance of DFU.", "claims": [{"id": "claim-method", "statement": "We performed a Spearman correlation analysis with the aim of exploring in depth the association between diagnostic biomarkers and infiltrating immune cells.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38613800", "locator": "sections[9] \"Correlation analysis between diagnostic biomarkers and immune cells\" paragraph 2", "quote": "We performed a Spearman correlation analysis with the aim of exploring in depth the association between diagnostic biomarkers and infiltrating immune cells."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38613800", "locator": "sections[10] \"Data availability\" paragraph 2", "quote": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com."}], "state": "complete"}, {"id": "claim-target-result", "statement": "PROS1 was identified and validated as a biomarker for DFU.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38613800", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "PROS1 was identified and validated as a biomarker for DFU."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "PROS1 was identified and validated as a biomarker for DFU.", "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:38613800"], "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:GSE134431"], "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:GSE134431"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38613800", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.205732", "sha256": "sha256:dfb86bc6d9c5df2d1b1d6b74445fddf26e795d5c0153dc53b2da47869c807901", "bytes": 30945, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.205732", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11087110", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE134431", "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=GSE134431", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE134431", "version": null, "note": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3946485", "GSM3946486", "GSM3946487", "GSM3946488", "GSM3946489", "GSM3946490", "GSM3946491", "GSM3946492", "GSM3946493", "GSM3946494", "GSM3946495", "GSM3946496", "GSM3946497", "GSM3946498", "GSM3946499", "GSM3946500", "GSM3946501", "GSM3946502", "GSM3946503", "GSM3946504", "GSM3946505"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Deregulated immune signature orchestrated by FOXM1 impairs human diabetic wound healing", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE68183", "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=GSE68183", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68183", "version": null, "note": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1665311", "GSM1665312", "GSM1665313", "GSM1665314", "GSM1665315", "GSM1665316"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "16686", "taxon": "Homo sapiens", "title": "Comparative genomic, microRNA, and tissue analyses reveal subtle differences between non-diabetic and diabetic foot skin [gene expression]", "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:GSE80178", "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=GSE80178", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE80178", "version": null, "note": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2114231", "GSM2114232", "GSM2114233", "GSM2114234", "GSM2114235", "GSM2114236", "GSM2114237", "GSM2114238", "GSM2114239", "GSM2114240", "GSM2114241", "GSM2114242"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "16686", "taxon": "Homo sapiens", "title": "Genomic Profiling of Diabetic Foot Ulcers Identifies miR-15b-5p as a Major Regulator that Leads to Suboptimal Inflammatory Response and Diminished DNA Repair Mechanisms", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE134431 not downloaded", "asset:data:geo:GSE134431 licence not read", "asset:data:geo:GSE68183 not downloaded", "asset:data:geo:GSE68183 licence not read", "asset:data:geo:GSE80178 not downloaded", "asset:data:geo:GSE80178 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": "We performed a Spearman correlation analysis with the aim of exploring in depth the association between diagnostic biomarkers and infiltrating immune cells."}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-3", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Random Forest"}}, {"id": "method-4", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Support Vector Machine"}}, {"id": "method-5", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Gradient Boosting"}}, {"id": "method-6", "family": "machine_learning", "specific": "decision_tree", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "decision tree"}}, {"id": "method-7", "family": "model_calibration", "specific": "decision_curve", "label": "Model calibration / clinical utility", "dsl_operations": ["calibration_bins", "net_benefit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictions_and_outcomes"], "evidence": {"score": 0.8, "band": "high", "quote": "decision curve analysis"}}], "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": ["GSE68183", "GSE80178", "GSE134431"], "resolved_accessions": ["GSE68183", "GSE80178", "GSE134431"], "statements": ["All data generated have been incorporated into the published manuscript. The gene expression datasets produced during this investigation are accessible in the NCBI Gene Expression Omnibus (GEO) database under the accession numbers: GSE68183, GSE80178, and GSE134431. For additional information, please reach out to the authors at Hongshuo Shi’s email address: jf17510413109@163.com."], "basis": "The paper names GSE68183, GSE80178, GSE134431 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:38613800", "data:geo:GSE134431"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE134431"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:15:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8377, "completion_tokens": 1691, "cached_tokens": 264}}, "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:38613800", "type": "paper", "label": "pmid:38613800"}, {"id": "source:pmid:38613800", "type": "manuscript", "label": "PMID 38613800 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38613800", "type": "paper", "label": "pmid:38613800"}, {"id": "source:pmid:38613800", "type": "manuscript", "label": "PMID 38613800 full text"}, {"id": "data:geo:GSE134431", "type": "dataset", "label": "GEO GSE134431"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38613800", "type": "extraction", "used": ["source:pmid:38613800"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE134431", "type": "accession_resolution", "used": ["data:geo:GSE134431"], "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:38613800", "parent_hash": "sha256:11b1eda468db6c46fed04aacddd6b478b2d7228a40f86c314a89cc6cec5f8310", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE134431 licence not read", "asset:data:geo:GSE134431 not downloaded", "asset:data:geo:GSE68183 licence not read", "asset:data:geo:GSE68183 not downloaded", "asset:data:geo:GSE80178 licence not read", "asset:data:geo:GSE80178 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": ["We performed a Spearman correlation analysis with the aim of exploring in depth the association between diagnostic biomarkers and infiltrating immune cells."], "order_basis": "analysis_only", "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":"2026-11-04T01:42:54+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}}}