{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36621808", "kind": "science-record", "revision": 4, "content_hash": "sha256:3a73ec66926d59a9bab509dc24a3185b28dd17b1f2585bc45fca178f7ac28b57", "created_at": "2026-11-01T19:01:10Z", "updated_at": "2026-11-01T22:51:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Characterization of the gene signature correlated with favorable response to chemoradiotherapy in rectal cancer: A hypothesis-generating study.", "doi": "10.1002/cam4.5586", "pmid": "36621808", "authors": ["Seung Hyuck Jeon", "Eui Kyu Chie"], "journal": "Cancer medicine", "year": 2023, "abstract": "PURPOSE: This study aimed to define the gene signature associated with response to neoadjuvant chemoradiotherapy (nCRT), or chemoradiosensitivity (CRS) signature, in rectal cancer, and investigate the correlation between the CRS signature and characteristics of tumor.\nMATERIALS AND METHODS: Three public microarray datasets of pre-nCRT rectal cancer were used to discover and validate the CRS signature, and the pathway analysis of the CRS signature was performed. Patients in The Cancer Genome Atlas (TCGA) dataset were stratified according to the CRS signature enrichment score, and mutational profile and proportions of infiltrated immune cells were compared.\nRESULTS: In the discovery dataset (GSE53781), 95 genes were upregulated in complete responders compared to non-complete responders and defined as the CRS signature. Pathways regarding DNA replication and repair processes as well as inflammatory response were enriched in the CRS signature. In the validation datasets (GSE35452 and GSE45404), patients with favorable response to nCRT exhibited higher enrichment score of the CRS. In TCGA-READ cohort, patients with high CRS signature harbored KRAS mutation in lower frequency than those with low CRS signature. In addition, proportions of proinflammatory immune cells were higher, but proportion of immunosuppressive M2 macrophages was lower in patients with high CRS signature than those with low CRS signature.\nCONCLUSIONS: The current integrative bioinformatic analysis suggests the CRS signature and showed that the CRS signature is associated with dissimilar mutational profile and increased immune response. The discovered CRS signature and related characteristics may serve as candidate of stratification factor in upcoming studies for rectal cancer.", "claims": [{"id": "claim-method", "statement": "Based on the normalized expression, the empirical Bayes method was used to perform differential expression analysis in an R package limma.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36621808", "locator": "sections[4] \"Definition and characterization of gene signature\" paragraph 2", "quote": "Based on the normalized expression, the empirical Bayes method was used to perform differential expression analysis in an R package limma."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36621808", "locator": "sections[17] \"DATA AVAILABILITY STATEMENT\" paragraph 2", "quote": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In TCGA-READ, the high-CRS group had less frequent KRAS mutation, greater activated NK-cell and dendritic-cell infiltration, and less M2 macrophage infiltration than the low-CRS group.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36621808", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "In TCGA‐READ cohort, patients with high CRS signature harbored KRAS mutation in lower frequency than those with low CRS signature."}, {"asset": "source:pmid:36621808", "locator": "sections[10] \"Association between the CRS signature and mutation profiles of cancer\" paragraph 5", "quote": "Among the analyzed genes, KRAS mutation was less frequent in patients with high CRS signature (23.8% vs. 48.8%, p = 0.030) than those with low CRS signature."}, {"asset": "source:pmid:36621808", "locator": "sections[11] \"Association between the CRS signature and immune cell infiltration into cancer\" paragraph 2", "quote": "Activated NK cells were significantly more frequent in tumor with high CRS signature compared to low CRS signature (2.80% vs. 1.48%, p = 0.038; Figure 3A)."}, {"asset": "source:pmid:36621808", "locator": "sections[11] \"Association between the CRS signature and immune cell infiltration into cancer\" paragraph 2", "quote": "Activated dendritic cells were also significantly more abundant in tumor with high CRS signature than low CRS signature (1.20% vs. 0.40%, p = 0.011; Figure 3C)."}, {"asset": "source:pmid:36621808", "locator": "sections[11] \"Association between the CRS signature and immune cell infiltration into cancer\" paragraph 2", "quote": "On contrary, the proportion of immunosuppressive M2 macrophages was significantly lower in tumor with high CRS signature than low CRS signature (17.91% vs. 22.38%, p = 0.026; Figure 3D)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "In TCGA-READ, the high-CRS group had less frequent KRAS mutation, greater activated NK-cell and dendritic-cell infiltration, and less M2 macrophage infiltration than the low-CRS group.", "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:36621808"], "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:GSE35452"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "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:GSE35452"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36621808", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/cam4.5586", "sha256": "sha256:897a6fd314454ee76fd58c0297229d89577a7246ec7ca8997137da8732eaa35f", "bytes": 23986, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/cam4.5586", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10134325", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE35452", "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=GSE35452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE35452", "version": null, "note": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM868548", "GSM868549", "GSM868550", "GSM868551", "GSM868552", "GSM868553", "GSM868554", "GSM868555", "GSM868556", "GSM868557", "GSM868558", "GSM868559", "GSM868560", "GSM868561", "GSM868562", "GSM868563", "GSM868564", "GSM868565", "GSM868566", "GSM868567", "GSM868568", "GSM868569", "GSM868570", "GSM868571", "GSM868572", "GSM868573", "GSM868574", "GSM868575", "GSM868576", "GSM868577", "GSM868578", "GSM868579", "GSM868580", "GSM868581", "GSM868582", "GSM868583", "GSM868584", "GSM868585", "GSM868586", "GSM868587", "GSM868588", "GSM868589", "GSM868590", "GSM868591", "GSM868592", "GSM868593"], "sample_count": 46, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Prediction of sensitivity of rectal cancer cells in response to preoperative chemoradiotherapy by DNA microarray analysis of gene expression profiles.", "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:GSE45404", "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=GSE45404", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE45404", "version": null, "note": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1103623", "GSM1103624", "GSM1103625", "GSM1103626", "GSM1103627", "GSM1103628", "GSM1103629", "GSM1103630", "GSM1103631", "GSM1103632", "GSM1103633", "GSM1103634", "GSM1103635", "GSM1103636", "GSM1103637", "GSM1103638", "GSM1103639", "GSM1103640", "GSM1103641", "GSM1103642", "GSM1103643", "GSM1103644", "GSM1103645", "GSM1103646", "GSM1103647", "GSM1103648", "GSM1103649", "GSM1103650", "GSM1103651", "GSM1103652", "GSM1103653", "GSM1103654", "GSM1103655", "GSM1103656", "GSM1103657", "GSM1103658", "GSM1103659", "GSM1103660", "GSM1103661", "GSM1103662", "GSM1103663", "GSM1103664", "GSM1103670", "GSM1103671", "GSM1103672", "GSM1103673", "GSM1103674", "GSM1103675", "GSM1103676", "GSM1103677", "GSM1103678", "GSM1103679", "GSM1103680", "GSM1103681", "GSM1103682", "GSM1103683", "GSM1103684", "GSM1103685", "GSM1103686", "GSM1103687", "GSM1103688", "GSM1103689", "GSM1103690", "GSM1103691", "GSM1103692", "GSM1103693", "GSM1103694", "GSM1103695", "GSM1103696", "GSM1103697", "GSM1103698", "GSM1103699", "GSM1103700", "GSM1103701", "GSM1103702", "GSM1103703", "GSM1103704", "GSM1103705", "GSM1103706", "GSM1103707"], "sample_count": 80, "group_sizes": null, "group_sizes_basis": null, "platform": "4133;570", "taxon": "Homo sapiens", "title": "Integrative computational biology and molecular determinants of rectal cancer resistance to chemoradiotherapies", "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:GSE53781", "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=GSE53781", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53781", "version": null, "note": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1300638", "GSM1300639", "GSM1300640", "GSM1300641", "GSM1300642", "GSM1300643", "GSM1300644", "GSM1300645", "GSM1300646", "GSM1300647", "GSM1300648", "GSM1300649", "GSM1300650", "GSM1300651", "GSM1300652", "GSM1300653", "GSM1300654", "GSM1300655", "GSM1300656", "GSM1300657", "GSM1300658", "GSM1300659", "GSM1300660", "GSM1300661", "GSM1300662", "GSM1300663"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "18134", "taxon": "Homo sapiens", "title": "Microarray profiling of rectal tumor samples", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE35452 not downloaded", "asset:data:geo:GSE35452 licence not read", "asset:data:geo:GSE45404 not downloaded", "asset:data:geo:GSE45404 licence not read", "asset:data:geo:GSE53781 not downloaded", "asset:data:geo:GSE53781 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Based on the normalized expression, the empirical Bayes method was used to perform differential expression analysis in an R package limma."}}, {"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": 0.8, "band": "high", "quote": "limma"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor", "method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": ["GSE53781", "GSE35452", "GSE45404"], "resolved_accessions": ["GSE53781", "GSE35452", "GSE45404"], "statements": ["The data that support the findings of this study are openly accessible through the Gene Expression Omnibus (GEO) database."], "basis": "The paper names GSE53781, GSE35452, GSE45404 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:36621808", "data:geo:GSE35452"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE35452"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:23:01Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7013, "completion_tokens": 2460, "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:36621808", "type": "paper", "label": "pmid:36621808"}, {"id": "source:pmid:36621808", "type": "manuscript", "label": "PMID 36621808 full text"}, {"id": "data:geo:GSE35452", "type": "dataset", "label": "GEO GSE35452"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36621808", "type": "paper", "label": "pmid:36621808"}, {"id": "source:pmid:36621808", "type": "manuscript", "label": "PMID 36621808 full text"}, {"id": "data:geo:GSE35452", "type": "dataset", "label": "GEO GSE35452"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36621808", "type": "extraction", "used": ["source:pmid:36621808"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE35452", "type": "accession_resolution", "used": ["data:geo:GSE35452"], "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:36621808", "parent_hash": "sha256:ab61c239de28023cda6c629d5116aca84d8f19dc45e5bbca505322d472470725", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE35452 licence not read", "asset:data:geo:GSE35452 not downloaded", "asset:data:geo:GSE45404 licence not read", "asset:data:geo:GSE45404 not downloaded", "asset:data:geo:GSE53781 licence not read", "asset:data:geo:GSE53781 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "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": ["f tumor. MATERIALS AND METHODS: Three public microarray datasets of pre-nCRT rectal cancer were used"], "order_basis": "paper_text_order:404", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Based on the normalized expression, the empirical Bayes method was used to perform differential expression analysis in an R package limma."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T00:38:22+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}}}