{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28580407", "kind": "science-record", "revision": 6, "content_hash": "sha256:40c9219340ec1696e2ef4abf2c1a5d39a9761bc5f6ff0302e400d95eb6eead71", "created_at": "2026-11-01T15:40:26Z", "updated_at": "2026-11-01T21:20:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "MC3T3 osteoblast-like cells cultured at alkaline pH: Microarray data (Affymetrix GeneChip Mouse 2.0 ST).", "doi": "10.1016/j.dib.2017.05.013", "pmid": "28580407", "authors": ["Anne-Marie Galow", "Alexander Rebl", "Dirk Koczan", "Jan Gimsa"], "journal": "Data in brief", "year": 2017, "abstract": "It is well known that pH plays a pivotal role in the control of bone remodeling. However, no comprehensive gene expression data are available for the effects of alkaline pH on osteoblasts. We cultured differentiating MC3T3-E1 osteoblast-like cells at pH 7.4, 7.8, and 8.4 for 14 days. To identify differential gene expression, microarray data were collected with Affymetrix GeneChips. The data were validated by real-time PCRs for five genes that were found to be greatly regulated in the GeneChip-experiments (DMP1, FABP4, SFRP2 and TNFRSF19) or considered relevant for the terminal function of osteoblasts (DMP1 and ATF4). All the data are available from the Gene Expression Omnibus database (GEO accession: GSE84907). Here, we provide pathway analyses of known protein coding genes that were down-regulated or up-regulated by greater than 2.0-fold. The regulation datasets obtained from comparisons of pH 7.8 and 7.4, as well as pH 8.4 and 7.4 share a high number of differentially expressed genes. When comparing pH 8.4 and 7.8, other genes mainly emerge, suggesting not only a simple amplification of the effects at pH 8.4 that were already induced at pH 7.8 but also the induction of different pathways. For a more detailed analysis, different mammalian functional gene networks were assigned to each dataset. After merging and manual optimization of the network graphs, three combined functional gene networks were obtained that reflected distinct pH-dependent cellular responses. A common feature of the networks was the central role of p38 MAP kinase. The microarray data presented here are related to the research article doi:10.1016/j.bbrep.2017.02.001 (Galow et al., 2017) [1].", "claims": [{"id": "claim-method", "statement": "Primary data analysis was carried out with the Affymetrix Expression Console 1.4.1.46 software including the Robust Multiarray Average module for normalization.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28580407", "locator": "sections[7] \"Statistical analyses of changes in global gene expression\" paragraph 2", "quote": "Primary data analysis was carried out with the Affymetrix Expression Console 1.4.1.46 software including the Robust Multiarray Average module for normalization."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Pathway analyses data are within this article; microarray data are available from the Gene Expression Omnibus database (GEO accession:GSE84907)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28580407", "locator": "sections[1] \"Specifications Table\" paragraph 2", "quote": "Pathway analyses data are within this article; microarray data are available from the Gene Expression Omnibus database (GEO accession:GSE84907)"}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper’s headline result was that p38 MAP kinase had a central role in the pH-dependent cellular responses; the statistical analysis used Robust Multi-Array Average normalization with significance defined as q<0.01 and fold changes >|2|, and the source microarray data are available through GEO accession GSE84907.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:28580407", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A common feature of the networks was the central role of p38 MAP kinase."}, {"asset": "source:pmid:28580407", "locator": "sections[7] \"Statistical analyses of changes in global gene expression\" paragraph 2", "quote": "Primary data analysis was carried out with the Affymetrix Expression Console 1.4.1.46 software including the Robust Multiarray Average module for normalization."}, {"asset": "source:pmid:28580407", "locator": "sections[7] \"Statistical analyses of changes in global gene expression\" paragraph 2", "quote": "A change was considered significant when the false discovery rate-corrected p-value/q-value thresholds met the criterion q<0.01 at fold changes >|2|, i.e. expression increments or declines larger than two."}, {"asset": "source:pmid:28580407", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All the data are available from the Gene Expression Omnibus database (GEO accession: GSE84907)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper’s headline result was that p38 MAP kinase had a central role in the pH-dependent cellular responses; the statistical analysis used Robust Multi-Array Average normalization with significance defined as q<0.01 and fold changes >|2|, and the source microarray data are available through GEO accession GSE84907.", "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:28580407"], "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:GSE84907"], "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:GSE84907"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28580407", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2017.05.013", "sha256": "sha256:117490cf62d926da359f681bd6314e571e64432844667a5c35265aa496d933a3", "bytes": 11589, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2017.05.013", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5447371", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE84907", "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=GSE84907", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE84907", "version": null, "note": "Pathway analyses data are within this article; microarray data are available from the Gene Expression Omnibus database (GEO accession:GSE84907)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Pathway analyses data are within this article; microarray data are available from the Gene Expression Omnibus database (GEO accession:GSE84907)", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2253869", "GSM2253870", "GSM2253871", "GSM2253872", "GSM2253873", "GSM2253874", "GSM2253875", "GSM2253876", "GSM2253877", "GSM2253878", "GSM2253879", "GSM2253880"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "16570", "taxon": "Mus musculus", "title": "Increased osteoblast viability at alkaline pH in vitro provides a new perspective on bone regeneration", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28580407:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:17bd382fc31e8e66142c4997eb02d62856b1d4fea7edb959e2abcbde47d6f2dd", "bytes": 901, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC5447371", "section_index": 1, "section_title": "Specifications Table", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Cell biology"], ["More specific subject area", "Bone cell biology, gene regulation"], ["Type of data", "Tables, schematic images"], ["How data was acquired", "Affymetrix GeneChip, Mouse Gene 2.0 ST Array, Robust Multi-Array Average and statistical analyses"], ["Data format", "Raw, filtered, analyzed"], ["Experimental factors", "Cells were cultured in HEPES buffered α-MEM at pH 7.4 (control) and under alkaline conditions at pH 7.8 and pH 8.4 for 14 days"], ["Experimental features", "RNA isolation, global gene expression analyses"], ["Data source location", "Rostock, Germany"], ["Data accessibility", "Pathway analyses data are within this article; microarray data are available from the Gene Expression Omnibus database (GEO accession:GSE84907)"]], "row_count": 9, "column_count": 2, "numeric_cells": 3, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:28580407:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2162606b7dae1022ed9767d516ddc56994d8e8c3c71102d78b14d309da37d782", "bytes": 1616, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#t0005", "version": null, "note": "Designations of functional networks of \"top diseases and functions\" known from mammalian (mouse, rat or human) in vivo and in vitro systems, which were extracted by the IPA software using the datasets obtained from the different pH comparisons. For each pH comparison, the table presents the three functional networks with the highest scores and the number of DE genes involved in the networks.", "structure": {"pmcid": "PMC5447371", "section_index": 8, "section_title": "Network analyses", "row_count": 10, "column_count": 4}, "table": {"label": "Table 1", "caption": "Designations of functional networks of \"top diseases and functions\" known from mammalian (mouse, rat or human) in vivo and in vitro systems, which were extracted by the IPA software using the datasets obtained from the different pH comparisons. For each pH comparison, the table presents the three functional networks with the highest scores and the number of DE genes involved in the networks.", "rows": [["Dataset", "Score", "Genes involved", "Functional networks (top diseases and functions)"], ["pH 7.8 vs. 7.4", "40", "29", "Cell morphology, cellular assembly and organization, cellular function and maintenance"], ["40", "29", "Connective tissue disorders, inflammatory disease, inflammatory response"], ["36", "27", "Cellular development, cellular growth and proliferation, nervous system development and function"], ["pH 8.4 vs. 7.4", "39", "29", "Embryonic development, organ development, organ morphology"], ["37", "28", "Connective tissue disorders, cellular assembly and organization, cellular function and maintenance"], ["35", "27", "Connective tissue development and function, skeletal and muscular system development and function, tissue development"], ["pH 8.4 vs. 7.8", "43", "23", "Cellular development, cellular growth and proliferation, organ development"], ["38", "21", "Molecular transport, cardiovascular system development and function, organismal development"], ["24", "15", "Skeletal and muscular system development and function, carbohydrate metabolism, nucleic acid metabolism"]], "row_count": 10, "column_count": 4, "numeric_cells": 21, "header_rows": 1, "locator": "section[8]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE84907 not downloaded", "asset:data:geo:GSE84907 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Robust Multi-Array Average (RMA) normalization", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Primary data analysis was carried out with the Affymetrix Expression Console 1.4.1.46 software including the Robust Multiarray Average module for normalization."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Robust Multi-Array Average (RMA) normalization), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE84907"], "resolved_accessions": ["GSE84907"], "statements": ["Pathway analyses data are within this article; microarray data are available from the Gene Expression Omnibus database (GEO accession:GSE84907)"], "basis": "The paper names GSE84907 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:28580407", "data:geo:GSE84907", "asset:table:pmid:28580407:1", "asset:table:pmid:28580407:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE84907"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:13Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 26688, "completion_tokens": 3516, "cached_tokens": 1304}}, "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:28580407", "type": "paper", "label": "pmid:28580407"}, {"id": "source:pmid:28580407", "type": "manuscript", "label": "PMID 28580407 full text"}, {"id": "data:geo:GSE84907", "type": "dataset", "label": "GEO GSE84907"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28580407", "type": "paper", "label": "pmid:28580407"}, {"id": "source:pmid:28580407", "type": "manuscript", "label": "PMID 28580407 full text"}, {"id": "data:geo:GSE84907", "type": "dataset", "label": "GEO GSE84907"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28580407", "type": "extraction", "used": ["source:pmid:28580407"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE84907", "type": "accession_resolution", "used": ["data:geo:GSE84907"], "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:28580407", "parent_hash": "sha256:229f8408459441dc1f33b8206f03b69847e2c85d0acfb2e47eb10566ffaf5947", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE84907 licence not read", "asset:data:geo:GSE84907 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["teoblast-like cells cultured at alkaline pH: Microarray data (Affymetrix GeneChip Mouse 2.0 ST).", "ls cultured at alkaline pH: Microarray data (Affymetrix GeneChip Mouse 2.0 ST).", "s. To identify differential gene expression, microarray data were collected with Affymetrix GeneChip", "was the central role of p38 MAP kinase. The microarray data presented here are related to the resea"], "order_basis": "paper_text_order:8", "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": 0.93, "evidence": ["ine pH: Microarray data (Affymetrix GeneChip Mouse 2.0 ST).", "sign, materials and methods Cell culture The mouse-osteoblast precursor cell line MC3T3-E1 [3]"], "order_basis": "paper_text_order:45", "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":"2026-11-04T03:05:44+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}}}