{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26101748", "kind": "science-record", "revision": 8, "content_hash": "sha256:7dba64685ac5362499c1312553d9cc68dd3b04111a3c1e9f8001e05417ccbd98", "created_at": "2026-11-01T15:40:09Z", "updated_at": "2026-11-01T22:42:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene expression profiles of Bapx1 expressing FACS sorted cells from wildtype and Bapx1-EGFP null mouse embryos.", "doi": "10.1016/j.gdata.2015.05.031", "pmid": "26101748", "authors": ["Sumantra Chatterjee", "V Sivakamasundari", "Petra Kraus", "Sook Peng Yap", "Vibhor Kumar", "Shyam Prabhakar", "Thomas Lufkin"], "journal": "Genomics data", "year": 2015, "abstract": "The data described in this article refers to Chatterjee et al. (2015) \"In vivo genome-wide analysis of multiple tissues identifies gene regulatory networks, novel functions and downstream regulatory genes for Bapx1 and its co-regulation with Sox9 in the mammalian vertebral column\" (GEO GSE35649) [1]. Transcriptional profiling combined with genome wide binding data is a powerful tool to elucidate the molecular mechanism behind vertebrate organogenesis. It also helps to uncover multiple roles of a single gene in different organs. In the above mentioned report we reveal the function of the homeobox gene Bapx1 during the embryogenesis of five distinct organs (vertebral column, spleen, gut, forelimb and hindlimb) at a relevant developmental stage (E12.5), microarray analysis of isolated wildtype and mutant cells in is compared in conjunction with ChIP-Seq analysis. We also analyzed the development of the vertebral column by comparing microarray and ChIP-Seq data for Bapx1 with similarly generated data sets for Sox9 to generate a gene regulatory network controlling various facets of the organogenesis.", "claims": [{"id": "claim-method", "statement": "ANOVA with nominal alpha value set to 0.05 was then used to determine the probe sets significantly different between the different genotypes compared.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26101748", "locator": "sections[7] \"Gene expression microarrays and analyses\" paragraph 2", "quote": "ANOVA with nominal alpha value set to 0.05 was then used to determine the probe sets significantly different between the different genotypes compared."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Deposited data can be found here: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE35649.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26101748", "locator": "sections[2] \"Direct link to deposited data\" paragraph 2", "quote": "Deposited data can be found here: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE35649."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "“In the above mentioned report we reveal the function of the homeobox gene Bapx1 during the embryogenesis of five distinct organs (vertebral column, spleen, gut, forelimb and hindlimb) at a relevant developmental stage (E12.5), microarray analysis of isolated wildtype and mutant cells in is compared in conjunction with ChIP-Seq analysis.”", "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:26101748"], "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:GSE35649"], "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:GSE35649"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26101748", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2015.05.031", "sha256": "sha256:ebec702c3b91b7a42a0f2baa6cb6927bfc66858cf6ab53e1cfeeb96b4e6afd47", "bytes": 15836, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2015.05.031", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4474491", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE35649", "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=GSE35649", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE35649", "version": null, "note": "Deposited data can be found here: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE35649.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Deposited data can be found here: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE35649.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM872912", "GSM872913", "GSM872914", "GSM872915", "GSM872916", "GSM872917", "GSM872918", "GSM872919"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "6887", "taxon": "Mus musculus", "title": "Gene Expression profiles of Bapx1 sorted cells from forelimbs (FL) of wildtype (WT) and Bapx1 null (HOMO) E12.5 mouse embryos", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE35877", "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=GSE35877", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE35877", "version": null, "note": "Deposited data can be found here: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE35649.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Deposited data can be found here: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE35649.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM872912", "GSM872913", "GSM872914", "GSM872915", "GSM872916", "GSM872917", "GSM872918", "GSM872919", "GSM872920", "GSM872921", "GSM872922", "GSM872923", "GSM872924", "GSM872925", "GSM872926", "GSM872927", "GSM872956", "GSM872957", "GSM872958", "GSM872959", "GSM872960", "GSM872961", "GSM872962", "GSM872963", "GSM872997", "GSM872998", "GSM872999", "GSM873000", "GSM873001", "GSM873002", "GSM873003", "GSM873004", "GSM873005", "GSM873006", "GSM873007", "GSM873008", "GSM873009", "GSM873010", "GSM873011", "GSM873012", "GSM877197", "GSM877198", "GSM877199", "GSM877200", "GSM877201", "GSM877202", "GSM877203", "GSM877204", "GSM898364", "GSM898365", "GSM898366", "GSM898367", "GSM898368", "GSM898369"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "6887;9250;6568", "taxon": "Mus musculus", "title": "Genome wide binding and expression profiling defines a Bapx1-Sox9 axis in vertebral column, Gut, Spleen and limbs in developing mouse embryo.", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:26101748:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c078239e0b4fa0b891e5e99395453e317a57b3d20a3ce447e0ce0b350b21e3bb", "bytes": 900, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#t0005", "version": null, "note": "Signaling pathways affected by Bapx1 in the vertebral column.", "structure": {"pmcid": "PMC4474491", "section_index": 8, "section_title": "Functional annotation of genes controlled by Bapx1 and Sox9", "row_count": 23, "column_count": 2}, "table": {"label": "Table 1", "caption": "Signaling pathways affected by Bapx1 in the vertebral column.", "rows": [["Bapx1 in Vertebral column", ""], ["Pathways", "-log (p-value)"], ["Wnt/β-catenin Signaling", "1.26"], ["Inhibition of Matrix Metalloproteases", "1.41"], ["VEGF Signaling", "1.45"], [""], ["Bapx1 in Spleen", ""], ["Pathways", "-log (p-value)"], ["FGF Signaling", "1.82"], ["ERK/MAPK Signaling", "2.06"], ["Epithelial Adherens Junction Signaling", "4.2"], ["", ""], ["Bapx1 in Gut", ""], ["Pathways", "-log (p-value)"], ["ERK/MAPK Signaling", "1.61"], ["Regulation of the Epithelial-Mesenchymal Transition Pathway", "1.66"], ["VEGF Signaling", "1.79"], [""], ["Sox9 in Vertebral column", ""], ["Pathways", "-log (p-value)"], ["Differentiation of chondrocytes", "5.46"], ["Apoptosis", "13.41"], ["Proliferation of cells", "27.42"]], "row_count": 23, "column_count": 2, "numeric_cells": 12, "header_rows": 1, "locator": "section[8]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE35649 not downloaded", "asset:data:geo:GSE35649 licence not read", "asset:data:geo:GSE35877 not downloaded", "asset:data:geo:GSE35877 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "ANOVA with nominal alpha value set to 0.05 was then used to determine the probe sets significantly different between the different genotypes compared."}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE35649", "GSE35877"], "resolved_accessions": ["GSE35649", "GSE35877"], "statements": ["Deposited data can be found here: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE35649."], "basis": "The paper names GSE35649, GSE35877 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:26101748", "data:geo:GSE35649", "asset:table:pmid:26101748:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE35649"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:03Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 37323, "completion_tokens": 3790, "cached_tokens": 5904}}, "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:26101748", "type": "paper", "label": "pmid:26101748"}, {"id": "source:pmid:26101748", "type": "manuscript", "label": "PMID 26101748 full text"}, {"id": "data:geo:GSE35649", "type": "dataset", "label": "GEO GSE35649"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26101748", "type": "paper", "label": "pmid:26101748"}, {"id": "source:pmid:26101748", "type": "manuscript", "label": "PMID 26101748 full text"}, {"id": "data:geo:GSE35649", "type": "dataset", "label": "GEO GSE35649"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26101748", "type": "extraction", "used": ["source:pmid:26101748"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE35649", "type": "accession_resolution", "used": ["data:geo:GSE35649"], "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:26101748", "parent_hash": "sha256:9ae608da20167bef4f1bc0b5737f04b700f7dee76c7abb7fb603998b5eb8936d", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE35649 licence not read", "asset:data:geo:GSE35649 not downloaded", "asset:data:geo:GSE35877 licence not read", "asset:data:geo:GSE35877 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Gene expression profiles of Bapx1 expressing FACS sorted cells from wildtype and Bapx1-EGFP nu", "embryos for dissociation into single cells. FACS allows for the separation of EGFP positive a"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"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": ["rted cells from wildtype and Bapx1-EGFP null mouse embryos.", "article refers to Chatterjee et al. (2015) \"In vivo genome-wide analysis of multiple tissues ide", "d here pertains to Chatterjee et al. (2015) “In vivo genome-wide analysis of multiple tissues ide", "column.” [1]. We have used stable transgenic mouse lines expressing EGFP under the endogenous p"], "order_basis": "paper_text_order:52", "id": "assay:2"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": [") at a relevant developmental stage (E12.5), microarray analysis of isolated wildtype and mutant cel", "lopment of the vertebral column by comparing microarray and ChIP-Seq data for Bapx1 with similarly g"], "order_basis": "paper_text_order:828", "id": "assay:3"}, {"role": "data_generation", "definition_id": "chip_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ant cells in is compared in conjunction with ChIP-Seq analysis. We also analyzed the development o", "vertebral column by comparing microarray and ChIP-Seq data for Bapx1 with similarly generated data"], "order_basis": "paper_text_order:921", "id": "assay:4"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["ANOVA with nominal alpha value set to 0.05 was then used to determine the probe sets significantly different between the different genotypes compared."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:47:11+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}}}