{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34121996", "kind": "science-record", "revision": 7, "content_hash": "sha256:c4fbd887b0bbaf676a5f047333d601000290fab1caa2f6c9e75973a27f353e19", "created_at": "2026-11-01T15:41:38Z", "updated_at": "2026-11-01T22:03:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Top-Down Proteomics of Human Saliva Highlights Anti-inflammatory, Antioxidant, and Antimicrobial Defense Responses in Alzheimer Disease.", "doi": "10.3389/fnins.2021.668852", "pmid": "34121996", "authors": ["Cristina Contini", "Alessandra Olianas", "Simone Serrao", "Carla Deriu", "Federica Iavarone", "Mozhgan Boroumand", "Alessandra Bizzarro", "Alessandra Lauria", "Gavino Faa", "Massimo Castagnola", "Irene Messana", "Barbara Manconi", "Carlo Masullo", "Tiziana Cabras"], "journal": "Frontiers in neuroscience", "year": 2021, "abstract": "Alzheimer disease (AD) is the most prevalent neurodegenerative disease in the elderly, characterized by accumulation in the brain of misfolded proteins, inflammation, and oxidative damage leading to neuronal cell death. By considering the viewpoint that AD onset and worsening may be influenced by environmental factors causing infection, oxidative stress, and inflammatory reaction, we investigated the changes of the salivary proteome in a population of patients with respect to that in healthy controls (HCs). Indeed, the possible use of saliva as a diagnostic tool has been explored in several oral and systemic diseases. Moreover, the oral cavity continuously established adaptative and protective processes toward exogenous stimuli. In the present study, qualitative/quantitative variations of 56 salivary proteoforms, including post-translationally modified derivatives, have been analyzed by RP-HPLC-ESI-IT-MS and MS/MS analyses, and immunological methods were applied to validate MS results. The salivary protein profile of AD patients was characterized by significantly higher levels of some multifaceted proteins and peptides that were either specific to the oral cavity or also expressed in other body districts: (i) peptides involved in the homeostasis of the oral cavity; (ii) proteins acting as ROS/RNS scavengers and with a neuroprotective role, such as S100A8, S100A9, and their glutathionylated and nitrosylated proteoforms; cystatin B and glutathionylated and dimeric derivatives; (iii) proteins with antimicrobial activity, such as α-defensins, cystatins A and B, histatin 1, statherin, and thymosin β4, this last with a neuroprotective role at the level of microglia. These results suggested that, in response to injured conditions, Alzheimer patients established defensive mechanisms detectable at the oral level. Data are available via ProteomeXchange with identifier PXD021538.", "claims": [{"id": "claim-method", "statement": "A comparison between the groups of patients and controls has been performed with Mann–Whitney and Welch-corrected t-tests, depending on the distribution (skewed or normal) and the variance (unequal or homogeneous).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34121996", "locator": "sections[7] \"Quantification and Statistical Analysis\" paragraph 2", "quote": "A comparison between the groups of patients and controls has been performed with Mann–Whitney and Welch-corrected t-tests, depending on the distribution (skewed or normal) and the variance (unequal or homogeneous)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ebi.ac.uk/pride/archive/, PXD021538.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34121996", "locator": "sections[13] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ebi.ac.uk/pride/archive/, PXD021538."}], "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:34121996"], "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:PXD021538"], "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:PXD021538"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34121996", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fnins.2021.668852", "sha256": "sha256:7203baf73bf8bf3bb2391d7a15c8164ebab598c10d08019a608c451456d62fe4", "bytes": 61873, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fnins.2021.668852", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8189262", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD021538", "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=PXD021538", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD021538", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ebi.ac.uk/pride/archive/, PXD021538.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ebi.ac.uk/pride/archive/, PXD021538.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Top-down proteomics of human saliva in Alzheimer disease", "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:34121996:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:850a7afae1aeba6d09965bdce8303c9bcc5efe394302680fc710bcb3f45b9c6f", "bytes": 2345, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T1", "version": null, "note": "XIC peak areas values (mean ± SD) normalized on total protein concentration and frequencies of salivary proteins/peptides resulted to levels significantly different between the AD group and HC group.", "structure": {"pmcid": "PMC8189262", "section_index": 11, "section_title": "Results", "row_count": 27, "column_count": 4}, "table": {"label": "TABLE 1", "caption": "XIC peak areas values (mean ± SD) normalized on total protein concentration and frequencies of salivary proteins/peptides resulted to levels significantly different between the AD group and HC group.", "rows": [["Protein/peptide", "XIC peak areas × 105 (mean ± SD) and frequency", "p-Values"], ["", "AD", "HC", "AD vs HC"], ["P-C peptide", "9.8 ± 7.7 (33/35)", "5.9 ± 4.4 (34/34)", "p = 0.02 AD↑"], ["Statherin 2P", "9.7 ± 9.6 (35/35)", "1.1 ± 0.9 (33/34)", "p < 0.0001 AD↑"], ["Stath. desF43", "1.5 ± 1.3 (35/35)", "0.4 ± 0.7 (33/34)", "p < 0.0001 AD↑"], ["Stath. des1–9", "0.6 ± 0.6 (29/37)", "0.08 ± 0.1 (24/34)", "p < 0.0001 AD↑"], ["Stath. des1–13", "0.2 ± 0.3 (24/35)", "0.08 ± 0.1 (16/34)", "p = 0.01 AD↑"], ["Hst-1 1P", "1.6 ± 1.5 (33/35)", "0.8 ± 0.8 (28/34)", "p = 0.01 AD↑"], ["Hst-1 0P", "0.3 ± 0.4 (24/35)", "0.1 ± 0.2 (17/34)", "p = 0.02 AD↑"], ["Cyst A", "1.9 ± 1.6 (32/35)", "1.0 ± 0.9 (29/34)", "p = 0.007 AD↑"], ["Cyst B-SSG", "0.9 ± 1.2 (29/35)", "0.3 ± 0.3 (27/34)", "p = 0.006 AD↑"], ["Cyst-B-SSC", "0.2 ± 0.3 (20/35)", "0.08 ± 0.1 (18/34)", "•"], ["Cyst B-SS dimer", "0.6 ± 0.5 (31/35)", "0.2 ± 0.3 (27/34)", "p = 0.0006 AD↑"], ["Cyst B tot", "1.7 ± 1.9 (33/35)", "0.6 ± 0.6 (27/34)", "p = 0.002 AD↑"], ["α-defensin 1", "1.8 ± 2.0 (32/35)", "0.5 ± 0.6 (24/34)", "p = 0.0001 AD↑"], ["α-defensin 2", "1.2 ± 1.3 (30/35)", "0.4 ± 0.4 (27/34)", "p = 0.0009 AD↑"], ["α-defensin 3", "0.6 ± 0.5 (25/35)", "0.2 ± 0.3 (17/34)", "p = 0.0003 AD↑"], ["α-defensin 4", "0.2 ± 0.3 (13/35)", "0.05 ± 0.1 (11/34)", "p = 0.01 AD↑"], ["α-defensin tot", "3.9 ± 4.0 (32/35)", "1.2 ± 1.5 (24/34)", "p = 0.0005 AD↑"], ["Tβ4", "0.7 ± 0.8 (25/35)", "0.2 ± 0.4 (16/34)", "p = 0.01 AD↑"], ["S100A8", "0.6 ± 1.3 (9/35)", "0.04 ± 0.2 (2/34)", "p = 0.02 AD↑"], ["S100A8 hyperoxidized", "0.2 ± 0.4 (5/35)", "0.04 ± 0.2 (3/34)", "•"], ["S100A8-SNO", "0.8 ± 1.8 (12/35)", "Not detected", "NA"], ["S100A8 tot", "1.6 ± 2.7 (22/35)", "0.08 ± 0.2(5/34)", "p < 0.0001 AD↑"], ["S100A9(S) (all proteoforms)", "3.3 ± 3.2 (32/35)", "0.5 ± 0.8 (16/34)", "p < 0.0001 AD↑"], ["S100A9(L)-SSG", "1.5 ± 2.4 (22/35)", "0.3 ± 0.4 (16/34)", "p = 0.004 AD↑"], ["S100A9 tot", "4.8 ± 5.4 (33/35)", "0.9 ± 1.2 (19/35)", "p < 0.0001 AD↑"]], "row_count": 27, "column_count": 4, "numeric_cells": 90, "header_rows": 2, "locator": "section[11]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:PXD021538 not downloaded", "asset:data:geo:PXD021538 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "welch_t_test", "label": "Group comparison", "dsl_operations": ["welch_t"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A comparison between the groups of patients and controls has been performed with Mann–Whitney and Welch-corrected t-tests, depending on the distribution (skewed or normal) and the variance (unequal or homogeneous)."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "ANOVA"}}], "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": ["welch_t"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: welch_t_test."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["PXD021538"], "resolved_accessions": ["PXD021538"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://www.ebi.ac.uk/pride/archive/, PXD021538."], "basis": "The paper names PXD021538 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": ["welch_t"], "assets": ["source:pmid:34121996", "data:geo:PXD021538", "asset:table:pmid:34121996:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD021538"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:43Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 50182, "completion_tokens": 1001, "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:34121996", "type": "paper", "label": "pmid:34121996"}, {"id": "source:pmid:34121996", "type": "manuscript", "label": "PMID 34121996 full text"}, {"id": "data:geo:PXD021538", "type": "dataset", "label": "GEO PXD021538"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34121996", "type": "paper", "label": "pmid:34121996"}, {"id": "source:pmid:34121996", "type": "manuscript", "label": "PMID 34121996 full text"}, {"id": "data:geo:PXD021538", "type": "dataset", "label": "GEO PXD021538"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34121996", "type": "extraction", "used": ["source:pmid:34121996"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD021538", "type": "accession_resolution", "used": ["data:geo:PXD021538"], "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:34121996", "parent_hash": "sha256:3fefecd3414ec9e5d7217f56368b58eecb6511f36a91f3da26402ee8ae705774", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD021538 licence not read", "asset:data:geo:PXD021538 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": ["Top-Down Proteomics of Human Saliva Highlights Anti-inflammatory", "cipitate and immediately analyzed by RP-HPLC-ESI-MS or stored at −80°C until the analysis for up", "C peak areas measured by HPLC/low-resolution ESI-MS analysis, with the following peak parameters"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["of the salivary proteome in a population of patients with respect to that in healthy controls (HCs). I", "st-test was applied to compare the groups of patients treated with different pharmacological therapies. Su"], "order_basis": "paper_text_order:549", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["welch_t"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A comparison between the groups of patients and controls has been performed with Mann–Whitney and Welch-corrected t-tests, depending on the distribution (skewed or normal) and the variance (unequal or homogeneous)."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:36:18+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}}}