{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41191207", "kind": "science-record", "revision": 3, "content_hash": "sha256:752a8cad2893837631ef269438d8f52e99f10e07b8d33080a42dd0ed1dabc2e3", "created_at": "2026-11-01T20:31:13Z", "updated_at": "2026-11-01T22:14:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of lactylation-related biomarkers in HNSC by integrating machine learning and Spatial transcriptomics analysis.", "doi": "10.1007/s12672-025-03849-6", "pmid": "41191207", "authors": ["Pu-Yu Wang", "Yi-Ping Zheng", "Yu-Lin Zhao"], "journal": "Discover oncology", "year": 2025, "abstract": "OBJECTIVE: Head and neck squamous cell carcinoma (HNSC) is a common malignant tumor with a 5-year survival rate of less than 60% and lactylation modification plays a key role in its occurrence and progression. This study aims to identify key lactylation-related genes (LRGs) in HNSC and their prognostic impact by combining machine learning methods and spatial transcriptomics analysis.\nMETHODS: High-throughput gene expression data of HNSC were obtained from the TCGA database. The \"Limma\" R package was used to screen differentially expressed genes (DEGs), and their biological significance was investigated through GO and KEGG functional enrichment analyses. Subsequently, weighted gene co-expression network analysis (WGCNA) was employed to identify disease trait-associated modules. We used 12 machine learning methods to screen for key genes and validated them in the GSE6631 dataset. Survival curves were plotted to evaluate the prognostic ability of key genes. Transcriptional regulation analysis via the \"RcisTarget\" package identified transcription factors associated with motifs exceeding NES 3.5. Single-cell and spatial transcriptomic analysis was performed, which involved dimensionality reduction, clustering via UMAP, cell type annotation and the plotting of spatial expression distribution maps of key genes. Finally, for immune infiltration analysis, the CIBERSORT algorithm was used to calculate the proportions of 22 types of immune cells, and then the correlations between key genes and immune-related genes were analyzed.\nRESULTS: Our study identified three key LRGs (MSN, KIF2C, and RFC4), which exhibited strong diagnostic performance, with AUC values of 0.986 for KIF2C, 0.964 for RFC4, and 0.89 for MSN in the TCGA-HNSC cohort. These findings were validated in the GSE6631 dataset. Western blotting showed a significant upregulation of the expression of these genes in the HNSC group, which was consistent with the RT-qPCR results. Survival analysis showed that the high expression of key genes was closely associated with a poorer overall survival (p < 0.05). Spatial transcriptomics analysis revealed that KIF2C, RFC4, and MSN were preferentially expressed in tumor core regions, indicating their involvement in the malignant microenvironment. Additionally, we discovered that 10 types of immune cell infiltrations were significantly changed in HNSC and well correlated with key genes.\nCONCLUSION: MSN, KIF2C and RFC4 may serve as potential biomarkers for diagnosing and predicting the prognosis of HNSC, providing new insights into targeted therapy.", "claims": [{"id": "claim-method", "statement": "Kaplan-Meier method was used to plot survival curves to visualize differences in overall survival between the two groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41191207", "locator": "sections[6] \"Survival analysis\" paragraph 2", "quote": "Kaplan-Meier method was used to plot survival curves to visualize differences in overall survival between the two groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analyzed in this study are available in the following open access repositories: TCGA, (https://portal.gdc.cancer.gov/). GEO (https://www.ncbi.nlm.nih.gov/geo/). The data that support the findings of this study are available from the corresponding author, upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41191207", "locator": "sections[27] \"notes\" paragraph 1", "quote": "The datasets analyzed in this study are available in the following open access repositories: TCGA, (https://portal.gdc.cancer.gov/). GEO (https://www.ncbi.nlm.nih.gov/geo/). The data that support the findings of this study are available from the corresponding author, upon reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Our study identified three key LRGs (MSN, KIF2C, and RFC4), which exhibited strong diagnostic performance, with AUC values of 0.986 for KIF2C, 0.964 for RFC4, and 0.89 for MSN in the TCGA-HNSC cohort.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41191207", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Our study identified three key LRGs (MSN, KIF2C, and RFC4), which exhibited strong diagnostic performance, with AUC values of 0.986 for KIF2C, 0.964 for RFC4, and 0.89 for MSN in the TCGA-HNSC cohort."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Our study identified three key LRGs (MSN, KIF2C, and RFC4), which exhibited strong diagnostic performance, with AUC values of 0.986 for KIF2C, 0.964 for RFC4, and 0.89 for MSN in the TCGA-HNSC cohort.", "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:41191207"], "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:GSE6631"], "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:GSE6631"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41191207", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-03849-6", "sha256": "sha256:3d9dc495af82a76ba8f84265199340f18bcb4f5efbdd030f52e382a5eaa185a0", "bytes": 35497, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-03849-6", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12589766", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE6631", "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=GSE6631", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6631", "version": null, "note": "The datasets analyzed in this study are available in the following open access repositories: TCGA, (https://portal.gdc.cancer.gov/). GEO (https://www.ncbi.nlm.nih.gov/geo/). The data that support the findings of this study are available from the corresponding author, upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed in this study are available in the following open access repositories: TCGA, (https://portal.gdc.cancer.gov/). GEO (https://www.ncbi.nlm.nih.gov/geo/). The data that support the findings of this study are available from the corresponding author, upon reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM153813", "GSM153814", "GSM153815", "GSM153816", "GSM153817", "GSM153818", "GSM153819", "GSM153820", "GSM153821", "GSM153822", "GSM153823", "GSM153824", "GSM153825", "GSM153826", "GSM153827", "GSM153828", "GSM153829", "GSM153830", "GSM153831", "GSM153832", "GSM153833", "GSM153834", "GSM153835", "GSM153836", "GSM153837", "GSM153838", "GSM153839", "GSM153840", "GSM153841", "GSM153842", "GSM153843", "GSM153844", "GSM153845", "GSM153846", "GSM153847", "GSM153848", "GSM153849", "GSM153850", "GSM153851", "GSM153852", "GSM153853", "GSM153854", "GSM153855", "GSM153856"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "8300", "taxon": "Homo sapiens", "title": "Expression data from head and neck squamous cell carcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE6631 not downloaded", "asset:data:geo:GSE6631 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Kaplan-Meier method was used to plot survival curves to visualize differences in overall survival between the two groups."}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "Limma"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE6631", "GSE252265-GSM7998252"], "resolved_accessions": ["GSE6631"], "statements": ["The datasets analyzed in this study are available in the following open access repositories: TCGA, (https://portal.gdc.cancer.gov/). GEO (https://www.ncbi.nlm.nih.gov/geo/). The data that support the findings of this study are available from the corresponding author, upon reasonable request."], "basis": "The paper names GSE6631 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:41191207", "data:geo:GSE6631"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE6631"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:04:54Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9778, "completion_tokens": 1746, "cached_tokens": 256}}, "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:41191207", "type": "paper", "label": "pmid:41191207"}, {"id": "source:pmid:41191207", "type": "manuscript", "label": "PMID 41191207 full text"}, {"id": "data:geo:GSE6631", "type": "dataset", "label": "GEO GSE6631"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41191207", "type": "paper", "label": "pmid:41191207"}, {"id": "source:pmid:41191207", "type": "manuscript", "label": "PMID 41191207 full text"}, {"id": "data:geo:GSE6631", "type": "dataset", "label": "GEO GSE6631"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41191207", "type": "extraction", "used": ["source:pmid:41191207"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE6631", "type": "accession_resolution", "used": ["data:geo:GSE6631"], "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:41191207", "parent_hash": "sha256:0fcd23ebcecc36349694b4dbce7db256cd64f824dd614b392147111a5c476d16", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE6631 licence not read", "asset:data:geo:GSE6631 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["dings were validated in the GSE6631 dataset. Western blotting showed a significant upregulation of the exp", "Rs in HNSC, we further performed qRT-PCR and Western blotting. qRT-PCR results showed that the mRNA expres", "ignificantly high in HNSC group (Fig. 8A–C). Western blotting results showed that the protein levels of MS", "n levels of three key genes were detected by Western blotting. E Detection of lactylation modification in"], "order_basis": "paper_text_order:1890", "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": ["he HNSC group, which was consistent with the RT-qPCR results. Survival analysis showed that the h", "HNSC group, which was consistent with the RT-qPCR results. Survival analysis showed that the h"], "order_basis": "paper_text_order:2023", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Kaplan-Meier method was used to plot survival curves to visualize differences in overall survival between the two groups."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:44:28+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}}}