{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40579006", "kind": "science-record", "revision": 4, "content_hash": "sha256:2491ea64879a1fe0a69318280681ba85ff94b56fa8eaec39d995bdd5341920c5", "created_at": "2026-11-01T20:30:40Z", "updated_at": "2026-11-01T22:56:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "NeuroD2 Modulates Hippocampal Neuronal Organization and Axon Guidance During Aging.", "doi": "10.21873/invivo.14000", "pmid": "40579006", "authors": ["Merve Beker", "Busenur Bolat", "Bahar Sarikamis Johnson", "Nilufer Ercin", "Rabia Kalkan Cakmak", "Sare B Kaya", "Nail Besli", "Ulkan Celik", "Mustafa C Beker"], "journal": "In vivo (Athens, Greece)", "year": 2025, "abstract": "BACKGROUND/AIM: Biological aging refers to the progressive deterioration of an organism's functions due to accumulated cellular and molecular damage. NeuroD2, a critical transcription factor, plays a crucial role in neuronal development and synaptic maturation. This study investigates the role of NeuroD2 in hippocampal neuron organization, focusing on hilar mossy cells during aging, and employs bioinformatics to identify NeuroD2 targets linked to cellular aging.\nMATERIALS AND METHODS: We used 21 adult C57Bl/6 mice, categorized into three age groups: young (2 months), old (12 months), and very old (24 months). Mice were administered BrdU intraperitoneally for three consecutive days, 10 days before euthanasia. The brains were harvested and analyzed using immunofluorescence, Western blotting, and quantitative real-time PCR to evaluate NeuroD2 expression and associated signaling pathways in hippocampal tissue. Additionally, bioinformatics analysis was performed using two open-access datasets (ProteomeXchange Consortium, Dataset identifier: PXD043352; Gene Expression Omnibus, GEO: GSE67539) and to explore potential interactions between NeuroD2 targets and biological aging components.\nRESULTS: Our results revealed that NeuroD2 expression changed significantly with age and correlated with AKT signaling. Moreover, we identified a potential link between NeuroD2 activity and the AKT pathway, indicating NeuroD2's role in mitigating aging-related stress. Bioinformatics analysis identified 513 down-regulated and 638 up-regulated proteins, with NeuroD2 targets involved in axonal projection showing increased expression in older mice. Contrary to expectations, pathway enrichment analysis highlighted axon guidance molecules rather than oxidative stress markers.\nCONCLUSION: This study underscores NeuroD2's critical role in preserving hippocampal integrity and reveals molecular mechanisms underlying age-related neuronal changes. Our findings provide insights into the role of NeuroD2 in regulating key pathways during healthy aging, potentially mitigating the impacts of aging.", "claims": [{"id": "claim-method", "statement": "Data were expressed as mean±standard deviation (SD) and were analyzed using a one-way ANOVA test in the statistical package SPSS for group comparisons. Following a significant ANOVA result, the least significant difference (LSD) test was applied as a post hoc analysis to determine specific group differences.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40579006", "locator": "sections[2] \"Materials and Methods\" paragraph 12", "quote": "Data were expressed as mean±standard deviation (SD) and were analyzed using a one-way ANOVA test in the statistical package SPSS for group comparisons. Following a significant ANOVA result, the least significant difference (LSD) test was applied as a post hoc analysis to determine specific group differences."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Supplementary data, obtained and reprocessed from these two sources, is available online at Figshare (19).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40579006", "locator": "sections[2] \"Materials and Methods\" paragraph 11", "quote": "Supplementary data, obtained and reprocessed from these two sources, is available online at Figshare (19)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "NeuroD2 expression changed significantly with age and correlated with AKT signaling.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40579006", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Our results revealed that NeuroD2 expression changed significantly with age and correlated with AKT signaling."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "NeuroD2 expression changed significantly with age and correlated with AKT signaling.", "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:40579006"], "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:GSE67539"], "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:GSE67539"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40579006", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21873/invivo.14000", "sha256": "sha256:b77cd8bd4b2f19d7320c9d78c8f17a7e4a323768e02d27254088653c2d9e5cdc", "bytes": 48599, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21873/invivo.14000", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12223602", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE67539", "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=GSE67539", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE67539", "version": null, "note": "Supplementary data, obtained and reprocessed from these two sources, is available online at Figshare (19).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Supplementary data, obtained and reprocessed from these two sources, is available online at Figshare (19).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1649148", "GSM1649149", "GSM1649150", "GSM1649151", "GSM1649152"], "sample_count": 5, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "NeuroD2 ChIP-SEQ from embryonic cortex", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD043352", "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=PXD043352", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD043352", "version": null, "note": "Supplementary data, obtained and reprocessed from these two sources, is available online at Figshare (19).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Supplementary data, obtained and reprocessed from these two sources, is available online at Figshare (19).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Global quantitative proteomics of mouse hippocampus during ageing", "resolution_checked_at": "2026-11-01T20:16:17Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE67539 not downloaded", "asset:data:geo:GSE67539 licence not read", "asset:data:geo:PXD043352 not downloaded", "asset:data:geo:PXD043352 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": "Data were expressed as mean±standard deviation (SD) and were analyzed using a one-way ANOVA test in the statistical package SPSS for group comparisons. Following a significant ANOVA result, the least significant difference (LSD) test was applied as a post hoc analysis to determine specific group differences."}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": "image_quantification", "specific": "densitometry", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "densitometr"}}], "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": ["PXD043352", "GSE67539"], "resolved_accessions": ["PXD043352", "GSE67539"], "statements": ["Supplementary data, obtained and reprocessed from these two sources, is available online at Figshare (19)."], "basis": "The paper names PXD043352, GSE67539 in ProteomeXchange Consortium 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:40579006", "data:geo:GSE67539"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE67539"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:55:05Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13538, "completion_tokens": 2222, "cached_tokens": 264}}, "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:40579006", "type": "paper", "label": "pmid:40579006"}, {"id": "source:pmid:40579006", "type": "manuscript", "label": "PMID 40579006 full text"}, {"id": "data:geo:GSE67539", "type": "dataset", "label": "GEO GSE67539"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40579006", "type": "paper", "label": "pmid:40579006"}, {"id": "source:pmid:40579006", "type": "manuscript", "label": "PMID 40579006 full text"}, {"id": "data:geo:GSE67539", "type": "dataset", "label": "GEO GSE67539"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40579006", "type": "extraction", "used": ["source:pmid:40579006"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE67539", "type": "accession_resolution", "used": ["data:geo:GSE67539"], "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:40579006", "parent_hash": "sha256:0e13de28c947b5a3010bff44c53c4ae801154ab15d6c89a316941075f19bc8a5", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE67539 licence not read", "asset:data:geo:GSE67539 not downloaded", "asset:data:geo:PXD043352 licence not read", "asset:data:geo:PXD043352 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"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": [", old (12 months), and very old (24 months). Mice were administered BrdU intraperitoneally for thre", "00). Experimental groups. Adult male C57BL/6 mice were used in this study. Only male mice were chos", "BL/6 mice were used in this study. Only male mice were chosen to prevent hormonal controversies. Mi", "ect newly born cells in the hippocampus, the mice were intraperitoneally injected with 100 mg/kg 5’"], "order_basis": "paper_text_order:656", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["The brains were harvested and analyzed using immunofluorescence, Western blotting, and quantitative real-tim", "ded and kept for protein and RNA extraction. Immunofluorescence. Brain tissues were cut in a cryostat (CM305", "arl Zeiss, Oberkochen, Germany). BrdU double immunofluorescence staining. To analyze newly born cells in the", "ronal sections of 20 μm were used for double immunofluorescence staining of BrdU/NeuN and BrdU/GFAP (16). Br"], "order_basis": "paper_text_order:802", "id": "assay:2"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ested and analyzed using immunofluorescence, Western blotting, and quantitative real-time PCR to evaluate", "focal Zeiss LSM 800 microscope (Carl Zeiss). Western blot. From mice that are 2, 12, and 24 months old"], "order_basis": "paper_text_order:822", "id": "assay:3"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["rescence, Western blotting, and quantitative real-time PCR to evaluate NeuroD2 expression and associate", "ic levels of the proteins (16). Quantitative real-time PCR analysis. Dissected hippocampal tissue was u", "by adding 80 μl of nuclease-free water. For real-time PCR, appropriate NeuroD2 forward (5’-GCTACTCCAAG", "l. Then, 1 μl of cDNA samples was added. The real-time PCR reaction was performed under the determined"], "order_basis": "paper_text_order:857", "id": "assay:4"}, {"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["100, and blocked with 10% normal goat serum (NGS) for 1 h. The sections were treated with ant", "(PBS with 0.3% Triton X-100) containing 10% NGS. Slides were incubated with the NeuN antibod", "AP (3656, Cell Signaling Technologies) in 2% NGS containing PBST. On the next day, after wash", "0, Thermo Fisher Scientific) in PBST with 2% NGS. Afterward, the slides underwent washing and"], "order_basis": "paper_text_order:4105", "id": "assay:5"}, {"role": "data_generation", "definition_id": "cell_imaging", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["cation to identify the nuclei. Subsequently, confocal microscopy was used to study the sections (LSM 800, Car", "identify the nuclei. Subsequently, confocal microscopy was used to study the sections (LSM 800, Car"], "order_basis": "paper_text_order:4594", "id": "assay:6"}, {"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": ["Data were expressed as mean±standard deviation (SD) and were analyzed using a one-way ANOVA test in the statistical package SPSS for group comparisons. Following a significant ANOVA result, the least significant difference (LSD) test was applied as a post hoc analysis to determine specific group differences."], "order_basis": "consumes_earlier_output", "id": "assay:7"}]},"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":"2026-11-04T01:48:39+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}}}