{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30618712", "kind": "science-record", "revision": 8, "content_hash": "sha256:1cdfd3bd7d9c4324e8402da81a7e570d1c0638dea53acd5cbbc5112594fb4663", "created_at": "2026-11-01T15:40:40Z", "updated_at": "2026-11-01T22:43:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Unbiased Proteomic Approach Identifies Unique and Coincidental Plasma Biomarkers in Repetitive mTBI and AD Pathogenesis.", "doi": "10.3389/fnagi.2018.00405", "pmid": "30618712", "authors": ["Joseph O Ojo", "Gogce Crynen", "Jon M Reed", "Rosa Ajoy", "Prashanthi Vallabhaneni", "Moustafa Algamal", "Paige Leary", "Naomi G Rafi", "Benoit Mouzon", "Michael Mullan", "Fiona Crawford"], "journal": "Frontiers in aging neuroscience", "year": 2018, "abstract": "The relationship between repetitive mild traumatic brain injury (r-mTBI) and Alzheimer's disease (AD) is well-recognized. However, the precise nature of how r-mTBI leads to or precipitates AD pathogenesis is currently not understood. Plasma biomarkers potentially provide non-invasive tools for detecting neurological changes in the brain, and can reveal overlaps between long-term consequences of r-mTBI and AD. In this study we address this by generating time-dependent molecular profiles of response to r-mTBI and AD pathogenesis in mouse models using unbiased proteomic analyses. To model AD, we used the well-validated hTau and PSAPP(APP/PS1) mouse models that develop age-related tau and amyloid pathological features, respectively, and our well-established model of r-mTBI in C57BL/6 mice. Plasma were collected at different ages (3, 9, and 15 months-old for hTau and PSAPP mice), encompassing pre-, peri- and post-\"onset\" of the cognitive and neuropathological phenotypes, or at different timepoints after r-mTBI (24 h, 3, 6, 9, and 12 months post-injury). Liquid chromatography/mass spectrometry (LC-MS) approaches coupled with Tandem Mass Tag labeling technology were applied to develop molecular profiles of protein species that were significantly differentially expressed as a consequence of mTBI or AD. Mixed model ANOVA after Benjamini-Hochberg correction, and a stringent cut-off identified 31 proteins significantly changing in r-mTBI groups over time and, when compared with changes over time in sham mice, 13 of these were unique to the injured mice. The canonical pathways predicted to be modulated by these changes were LXR/RXR activation, production of nitric oxide and reactive oxygen species and complement systems. We identified 18 proteins significantly changing in PSAPP mice and 19 proteins in hTau mice compared to their wild-type littermates with aging. Six proteins were found to be significantly regulated in all three models, i.e., r-mTBI, hTau, and PSAPP mice compared to their controls. The top canonical pathways coincidently changing in all three models were LXR/RXR activation, and production of nitric oxide and reactive oxygen species. This work suggests potential biomarkers for TBI and AD pathogenesis and for the overlap between these two, and warrant targeted investigation in human populations. Data are available via ProteomeXchange with identifier PXD010664.", "claims": [{"id": "claim-method", "statement": "After the median per peptide sequence from multiple fractions were calculated, mixed model ANOVA was used to test for significant proteins changing overtime within each group.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30618712", "locator": "sections[10] \"Data Processing and Statistical Analysis of Proteomics Data\" paragraph 2", "quote": "After the median per peptide sequence from multiple fractions were calculated, mixed model ANOVA was used to test for significant proteins changing overtime within each group."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with identifier PXD010664.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30618712", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD010664."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:30618712"], "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:PXD010664"], "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:PXD010664"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30618712", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fnagi.2018.00405", "sha256": "sha256:eca81871c048eac2f00e8e062fb0d410b12a595129c7052924e6d8a725ec8221", "bytes": 63398, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fnagi.2018.00405", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6305374", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD010664", "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=PXD010664", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD010664", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD010664.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD010664.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Unbiased proteomic analyses of plasma and brain tissue from TBI and AD mouse models II", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30618712:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f7d818ae7628f8d38aadea535a1214580d5c6d3fa8dad1297673849d0197db7f", "bytes": 251, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T1", "version": null, "note": "Significantly modulated proteins in r-sham and r-mTBI mice across multiple time points post-injury.", "structure": {"pmcid": "PMC6305374", "section_index": 14, "section_title": "Temporal Changes in Unique and Common Proteins in the Plasma of Repetitive mTBI and Sham Mice Across Multiple Post-injury Time Points", "row_count": 1, "column_count": 1}, "table": {"label": "Table 1", "caption": "Significantly modulated proteins in r-sham and r-mTBI mice across multiple time points post-injury.", "rows": [[""]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[14]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30618712:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:086350bb7a1a36967f1ddbf13c7a832aff76def9f539c23548641577014c7c6d", "bytes": 262, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T2", "version": null, "note": "Significantly modulated proteins changing with age in plasma samples from PSAPP vs. wild type littermate mice.", "structure": {"pmcid": "PMC6305374", "section_index": 17, "section_title": "Temporal Changes in Unique and Common Proteins in the Plasma of AD Mouse Models of Tauopathy (hTau) and Amyloidogenesis (PSAPP) at Different Ages; and Commonalities With Repetitive mTBI Model", "row_count": 1, "column_count": 1}, "table": {"label": "Table 2", "caption": "Significantly modulated proteins changing with age in plasma samples from PSAPP vs. wild type littermate mice.", "rows": [[""]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[17]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:30618712:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:040ff84e9804879c54b79335502d20888cd1a68d916417af51d208d3974d4125", "bytes": 248, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#T3", "version": null, "note": "Significantly modulated proteins changing with age in plasma samples from hTau vs. C57BL/6 mice.", "structure": {"pmcid": "PMC6305374", "section_index": 17, "section_title": "Temporal Changes in Unique and Common Proteins in the Plasma of AD Mouse Models of Tauopathy (hTau) and Amyloidogenesis (PSAPP) at Different Ages; and Commonalities With Repetitive mTBI Model", "row_count": 1, "column_count": 1}, "table": {"label": "Table 3", "caption": "Significantly modulated proteins changing with age in plasma samples from hTau vs. C57BL/6 mice.", "rows": [[""]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[17]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:30618712:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:65cadbcf94e5dbabcc1169d0dcc2152b722f6b281054ada6b36acb27596ce9e7", "bytes": 304, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[3]#T4", "version": null, "note": "List of common and unique significantly modulated proteins in plasma samples from repetitive mTBI, hTau, and PSAPP mice across all time points and ages.", "structure": {"pmcid": "PMC6305374", "section_index": 17, "section_title": "Temporal Changes in Unique and Common Proteins in the Plasma of AD Mouse Models of Tauopathy (hTau) and Amyloidogenesis (PSAPP) at Different Ages; and Commonalities With Repetitive mTBI Model", "row_count": 1, "column_count": 1}, "table": {"label": "Table 4", "caption": "List of common and unique significantly modulated proteins in plasma samples from repetitive mTBI, hTau, and PSAPP mice across all time points and ages.", "rows": [[""]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[17]/table-wrap[3]#T4"}}], "gaps": ["asset:data:geo:PXD010664 not downloaded", "asset:data:geo:PXD010664 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": "After the median per peptide sequence from multiple fractions were calculated, mixed model ANOVA was used to test for significant proteins changing overtime within each group."}}, {"id": "method-2", "family": "regression_modelling", "specific": "mixed_effects", "label": "Regression modelling", "dsl_operations": [], "missing_operations": ["regression_modelling_mixed_effects"], "expressible": false, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.7, "band": "medium", "quote": "Mixed model"}}], "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": ["PXD010664"], "resolved_accessions": ["PXD010664"], "statements": ["Data are available via ProteomeXchange with identifier PXD010664."], "basis": "The paper names PXD010664 in ProteomeXchange Consortium via the PRIDE partner repository 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:30618712", "data:geo:PXD010664", "asset:table:pmid:30618712:1", "asset:table:pmid:30618712:2", "asset:table:pmid:30618712:3", "asset:table:pmid:30618712:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD010664"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:11Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 43793, "completion_tokens": 990, "cached_tokens": 784}}, "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:30618712", "type": "paper", "label": "pmid:30618712"}, {"id": "source:pmid:30618712", "type": "manuscript", "label": "PMID 30618712 full text"}, {"id": "data:geo:PXD010664", "type": "dataset", "label": "GEO PXD010664"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30618712", "type": "paper", "label": "pmid:30618712"}, {"id": "source:pmid:30618712", "type": "manuscript", "label": "PMID 30618712 full text"}, {"id": "data:geo:PXD010664", "type": "dataset", "label": "GEO PXD010664"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30618712", "type": "extraction", "used": ["source:pmid:30618712"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD010664", "type": "accession_resolution", "used": ["data:geo:PXD010664"], "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:30618712", "parent_hash": "sha256:89de4f3dcfd06641b36abbe0c1ad75eb052e7d08850853c0c2fa5ac9fa4a79aa", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD010664 licence not read", "asset:data:geo:PXD010664 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Unbiased Proteomic Approach Identifies Unique and Coincidental", "pathogenesis in mouse models using unbiased proteomic analyses. To model AD, we used the well-vali", "24 h, 3, 6, 9, and 12 months post-injury for proteomic analyses (A). The tauopathy group consisted", "Data Processing and Statistical Analysis of Proteomics Data PMi Preview software was used to survey"], "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": ["of response to r-mTBI and AD pathogenesis in mouse models using unbiased proteomic analyses. To", "d the well-validated hTau and PSAPP(APP/PS1) mouse models that develop age-related tau and amyl", "e expressing human tau on a C57BL/6 and null murine tau background (generated as previously desc", "and AD mouse models. Six different groups of mice were used in this study. The mTBI group consisted"], "order_basis": "paper_text_order:612", "id": "assay:2"}, {"role": "data_generation", "definition_id": "elisa", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["tor I expression levels using antibody based ELISA approach in repetitive mTBI mice at multiple", "njury. (A) Represents ratio of BCA corrected ELISA concentration values normalized to 24 h post", "a LRG expression levels using antibody based ELISA approach in repetitive mTBI mice at multiple", "bulin expression levels using antibody based ELISA approach in sham and repetitive mTBI mice at"], "order_basis": "paper_text_order:12317", "id": "assay:3"}, {"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": ["After the median per peptide sequence from multiple fractions were calculated, mixed model ANOVA was used to test for significant proteins changing overtime within each group."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T02:39:21+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}}}