{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26598643", "kind": "science-record", "revision": 5, "content_hash": "sha256:497d081d4ba6cfc1cc0c39d4e7e128fc7890814232520212e5e8393935e7ff5f", "created_at": "2026-11-01T15:40:14Z", "updated_at": "2026-11-01T18:47:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Site-specific O-Glycosylation Analysis of Human Blood Plasma Proteins.", "doi": "10.1074/mcp.M115.053546", "pmid": "26598643", "authors": ["Marcus Hoffmann", "Kristina Marx", "Udo Reichl", "Manfred Wuhrer", "Erdmann Rapp"], "journal": "Molecular & cellular proteomics : MCP", "year": 2016, "abstract": "Site-specific glycosylation analysis is key to investigate structure-function relationships of glycoproteins, e.g. in the context of antigenicity and disease progression. The analysis, though, is quite challenging and time consuming, in particular for O-glycosylated proteins. In consequence, despite their clinical and biopharmaceutical importance, many human blood plasma glycoproteins have not been characterized comprehensively with respect to their O-glycosylation. Here, we report on the site-specific O-glycosylation analysis of human blood plasma glycoproteins. To this end pooled human blood plasma of healthy donors was proteolytically digested using a broad-specific enzyme (Proteinase K), followed by a precipitation step, as well as a glycopeptide enrichment and fractionation step via hydrophilic interaction liquid chromatography, the latter being optimized for intact O-glycopeptides carrying short mucin-type core-1 and -2 O-glycans, which represent the vast majority of O-glycans on human blood plasma proteins. Enriched O-glycopeptide fractions were subjected to mass spectrometric analysis using reversed-phase liquid chromatography coupled online to an ion trap mass spectrometer operated in positive-ion mode. Peptide identity and glycan composition were derived from low-energy collision-induced dissociation fragment spectra acquired in multistage mode. To pinpoint the O-glycosylation sites glycopeptides were fragmented using electron transfer dissociation. Spectra were annotated by database searches as well as manually. Overall, 31 O-glycosylation sites and regions belonging to 22 proteins were identified, the majority being acute-phase proteins. Strikingly, also 11 novel O-glycosylation sites and regions were identified. In total 23 O-glycosylation sites could be pinpointed. Interestingly, the use of Proteinase K proved to be particularly beneficial in this context. The identified O-glycan compositions most probably correspond to mono- and disialylated core-1 mucin-type O-glycans (T-antigen). The developed workflow allows the identification and characterization of the major population of the human blood plasma O-glycoproteome and our results provide new insights, which can help to unravel structure-function relationships. The data were deposited to ProteomeXchange PXD003270.", "claims": [{"id": "claim-data-access", "statement": "All mass spectrometry raw data as well as (glyco)peptide identifications and spectra annotations have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org)via the MassIVE repository with the dataset identifier PXD002315or MSV000079141, respectively.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26598643", "locator": "sections[15] \"Analysis of Glycopeptides\" paragraph 5", "quote": "All mass spectrometry raw data as well as (glyco)peptide identifications and spectra annotations have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org)via the MassIVE repository with the dataset identifier PXD002315or MSV000079141, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:26598643"], "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": "blocked", "blocked_on": "data:accession_unresolved", "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:PXD002315"], "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:PXD002315"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26598643", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1074/mcp.M115.053546", "sha256": "sha256:faebdaae44b098ebe51f69d0ebafb852b26258a05bd59dd8e80ca846d675e354", "bytes": 77244, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1074/mcp.M115.053546", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4739677", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002315", "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=PXD002315", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002315", "version": null, "note": "All mass spectrometry raw data as well as (glyco)peptide identifications and spectra annotations have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org)via the MassIVE repository with the dataset identifier PXD002315or MSV000079141, respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All mass spectrometry raw data as well as (glyco)peptide identifications and spectra annotations have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org)via the MassIVE repository with the dataset identifier PXD002315or MSV000079141, respectively.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD003270", "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=PXD003270", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD003270", "version": null, "note": "All mass spectrometry raw data as well as (glyco)peptide identifications and spectra annotations have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org)via the MassIVE repository with the dataset identifier PXD002315or MSV000079141, respectively.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All mass spectrometry raw data as well as (glyco)peptide identifications and spectra annotations have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org)via the MassIVE repository with the dataset identifier PXD002315or MSV000079141, respectively.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "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:26598643:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4fa80e3150e545c3b70f3e358d37449c619961da1305fcb8eb5c46a0c56b67f0", "bytes": 1138, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#TI", "version": null, "note": "Site-specific O-glycan composition of identified human blood plasma glycoproteins. Glycoproteins are listed with their UniprotKB accession number as well as the number of identified glycopeptides. O-glycosylated sites or regions are indexed with respect to the attached O-glycans (mono- and/or disialylated mucin-type core 1 O-glycans). O-glycosylation sites in bold have been pinpointed within this study. Previously unknown sites und regions are indicated by underlining. Curled brackets mark regions with several possible O-glycosylation sites. Superscript numbers indicate literature references. For every protein the number of registered, previously known, as well as new O-glycosylation sites and regions are given. For underlined proteins, glycosylated as well as non-glycosylated peptides were identified (supplemental Table S1). In addition previously reported plasma concentrations are given. HexNAc (N-acetylhexosamine), Hex (hexose), NeuAc (N-acetylneuraminic acid, sialic acid)", "structure": {"pmcid": "PMC4739677", "section_index": 22, "section_title": "Identification of the Peptide Moiety", "row_count": 0, "column_count": 0}, "table": {"label": "Table I", "caption": "Site-specific O-glycan composition of identified human blood plasma glycoproteins. Glycoproteins are listed with their UniprotKB accession number as well as the number of identified glycopeptides. O-glycosylated sites or regions are indexed with respect to the attached O-glycans (mono- and/or disialylated mucin-type core 1 O-glycans). O-glycosylation sites in bold have been pinpointed within this study. Previously unknown sites und regions are indicated by underlining. Curled brackets mark regions with several possible O-glycosylation sites. Superscript numbers indicate literature references. For every protein the number of registered, previously known, as well as new O-glycosylation sites and regions are given. For underlined proteins, glycosylated as well as non-glycosylated peptides were identified (supplemental Table S1). In addition previously reported plasma concentrations are given. HexNAc (N-acetylhexosamine), Hex (hexose), NeuAc (N-acetylneuraminic acid, sialic acid)", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[22]/table-wrap[1]#TI"}}, {"id": "asset:table:pmid:26598643:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b6a8999edea25a8e13e1d469130b3772aafa643d482ed56d691ba16dedb19912", "bytes": 826, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[2]#TII", "version": null, "note": "Detailed overview of all identified human blood plasma O-glycopeptides. For each O-glycopeptide, the corresponding glycoprotein including the UniProtKB accession number, the identified O-glycosylation site(s)/regions as well as the O-glycan composition are given, respectively. Likewise, the LC-MS retention time, the mass of the intact glycopeptide precursor, the measured peptide mass as well as the corresponding error is listed. The peptide identification using CID-MS3 was validated by the MASCOT peptide score and the Biotools score (CID). ETD based determination of the O-glycosylation site(s) was validated by the Biotools score (CID) as well as the NetOGlyc 4.0 score", "structure": {"pmcid": "PMC4739677", "section_index": 22, "section_title": "Identification of the Peptide Moiety", "row_count": 0, "column_count": 0}, "table": {"label": "Table II", "caption": "Detailed overview of all identified human blood plasma O-glycopeptides. For each O-glycopeptide, the corresponding glycoprotein including the UniProtKB accession number, the identified O-glycosylation site(s)/regions as well as the O-glycan composition are given, respectively. Likewise, the LC-MS retention time, the mass of the intact glycopeptide precursor, the measured peptide mass as well as the corresponding error is listed. The peptide identification using CID-MS3 was validated by the MASCOT peptide score and the Biotools score (CID). ETD based determination of the O-glycosylation site(s) was validated by the Biotools score (CID) as well as the NetOGlyc 4.0 score", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[22]/table-wrap[2]#TII"}}], "gaps": ["asset:data:geo:PXD002315 not downloaded", "asset:data:geo:PXD002315 licence not read", "asset:data:geo:PXD003270 not downloaded", "asset:data:geo:PXD003270 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), 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": "R4", "reachable": false, "accessions": ["PXD003270", "PXD002315"], "resolved_accessions": [], "statements": ["All mass spectrometry raw data as well as (glyco)peptide identifications and spectra annotations have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org)via the MassIVE repository with the dataset identifier PXD002315or MSV000079141, respectively."], "basis": "The paper names PXD003270, PXD002315, but the accession does not resolve in the repository (not_in_proteomexchange, not_in_proteomexchange), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26598643", "data:geo:PXD002315", "asset:table:pmid:26598643:1", "asset:table:pmid:26598643:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002315"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:06:37Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 57250, "completion_tokens": 1056, "cached_tokens": 520}}, "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:26598643", "type": "paper", "label": "pmid:26598643"}, {"id": "source:pmid:26598643", "type": "manuscript", "label": "PMID 26598643 full text"}, {"id": "data:geo:PXD002315", "type": "dataset", "label": "GEO PXD002315"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26598643", "type": "paper", "label": "pmid:26598643"}, {"id": "source:pmid:26598643", "type": "manuscript", "label": "PMID 26598643 full text"}, {"id": "data:geo:PXD002315", "type": "dataset", "label": "GEO PXD002315"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26598643", "type": "extraction", "used": ["source:pmid:26598643"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002315", "type": "accession_resolution", "used": ["data:geo:PXD002315"], "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:26598643", "parent_hash": "sha256:aa9f68b23f5ae0bec77a66a41c6975f37af05fb68f557351f8997170e638a7ea", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:PXD002315 licence not read", "asset:data:geo:PXD002315 not downloaded", "asset:data:geo:PXD003270 licence not read", "asset:data:geo:PXD003270 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"], "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": ["d O-glycopeptide fractions were subjected to mass spectrometric analysis using reversed-phase liquid chromat", "n; ETD = Electron transfer dissociation. All mass spectrometry raw data as well as (glyco)peptide identific"], "order_basis": "paper_text_order:1108", "id": "assay:1"}]},"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":"2026-11-04T00:39:41+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}}}