{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31805126", "kind": "science-record", "revision": 7, "content_hash": "sha256:9da2ee69fdf0fe73a1eb9fb7790f894cd2bd503bdc87346d47bae9ae5aa222dd", "created_at": "2026-11-01T15:40:53Z", "updated_at": "2026-11-01T21:22:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "IGF-1-enhanced miR-513a-5p signaling desensitizes glioma cells to temozolomide by targeting the NEDD4L-inhibited Wnt/β-catenin pathway.", "doi": "10.1371/journal.pone.0225913", "pmid": "31805126", "authors": ["Ku-Chung Chen", "Peng-Hsu Chen", "Kuo-Hao Ho", "Chwen-Ming Shih", "Chih-Ming Chou", "Chia-Hsiung Cheng", "Chin-Cheng Lee"], "journal": "PloS one", "year": 2019, "abstract": "Temozolomide (TMZ) is a first-line alkylating agent for glioblastoma multiforme (GBM). Clarifying the mechanisms inducing TMZ insensitivity may be helpful in improving its therapeutic effectiveness against GBM. Insulin-like growth factor (IGF)-1 signaling and micro (mi)RNAs are relevant in mediating GBM progression. However, their roles in desensitizing GBM cells to TMZ are still unclear. We aimed to identify IGF-1-mediated miRNA regulatory networks that elicit TMZ insensitivity for GBM. IGF-1 treatment attenuated TMZ cytotoxicity via WNT/β-catenin signaling, but did not influence glioma cell growth. By miRNA array analyses, 93 upregulated and 148 downregulated miRNAs were identified in IGF-1-treated glioma cells. miR-513a-5p from the miR-513a-2 gene locus was upregulated by IGF-1-mediated phosphoinositide 3-kinase (PI3K) signaling. Its elevated levels were also observed in gliomas versus normal cells, in array data of The Cancer Genome Atlas (TCGA), and the GSE61710, GSE37366, and GSE41032 datasets. In addition, lower levels of neural precursor cell-expressed developmentally downregulated 4-like (NEDD4L), an E3 ubiquitin protein ligase that inhibits WNT signaling, were found in gliomas by analyzing cells, arrays, and RNA sequencing data of TCGA glioma patients. Furthermore, a negative correlation was identified between miR-513a-5p and NEDD4L in glioma. NEDD4L was also validated as a direct target gene of miR-513a-5p, and it was reduced by IGF-1 treatment. Overexpression of NEDD4L inhibited glioma cell viability and reversed IGF-1-repressed TMZ cytotoxicity. In contrast, miR-513a-5p significantly affected NEDD4L-inhibited WNT signaling and reduced TMZ cytotoxicity. These findings demonstrate a distinct role of IGF-1 signaling through miR-513a-5p-inhibited NEDD4L networks in influencing GBM's drug sensitivity to TMZ.", "claims": [{"id": "claim-data-access", "statement": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31805126", "locator": "sections[7] \"Microarray, pathway analysis, and survival rate analysis\" paragraph 2", "quote": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297."}], "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:31805126"], "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:GSE140297"], "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:GSE140297"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31805126", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0225913", "sha256": "sha256:5d2c41fe09b5ef43ac6334b290f85a0fc697d2125013cc82c099d67d76442967", "bytes": 45959, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0225913", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6894868", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE140297", "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=GSE140297", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE140297", "version": null, "note": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM4159069", "GSM4159070", "GSM4159071", "GSM4159072"], "sample_count": 4, "group_sizes": null, "group_sizes_basis": null, "platform": "18310", "taxon": "Homo sapiens", "title": "IGF-1-mediated microRNA profile in glioblastoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE37366", "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=GSE37366", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37366", "version": null, "note": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM916825", "GSM916826", "GSM916827", "GSM916828", "GSM916829", "GSM916830", "GSM969939", "GSM969940", "GSM969941", "GSM969942", "GSM969943", "GSM969944"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "15829;6884", "taxon": "Homo sapiens", "title": "A Pro-survival OncomiR for Glioma Stem Cells is Associated with Tumor Recurrence", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE41032", "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=GSE41032", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE41032", "version": null, "note": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1007018", "GSM1007019", "GSM1007020", "GSM1007021", "GSM1007022", "GSM1007023"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "15516", "taxon": "Homo sapiens", "title": "miRNA profiles of brain glioma stem cells and normal neural stem cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE61710", "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=GSE61710", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE61710", "version": null, "note": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1511526", "GSM1511527", "GSM1511528", "GSM1511529", "GSM1511530", "GSM1511531", "GSM1511532", "GSM1511533", "GSM1511534", "GSM1511535", "GSM1511536", "GSM1511537", "GSM1511538", "GSM1511539", "GSM1511540", "GSM1511541", "GSM1511542"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "10656", "taxon": "Homo sapiens", "title": "Analysis of microRNA expression profile in malignant glioma tissues", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE140297 not downloaded", "asset:data:geo:GSE140297 licence not read", "asset:data:geo:GSE37366 not downloaded", "asset:data:geo:GSE37366 licence not read", "asset:data:geo:GSE41032 not downloaded", "asset:data:geo:GSE41032 licence not read", "asset:data:geo:GSE61710 not downloaded", "asset:data:geo:GSE61710 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "GEO2R", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“Microarray data from the GEO dataset were analyzed by GEO2R.”"}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (GEO2R), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE140297", "GSE61710", "GSE37366", "GSE41032"], "resolved_accessions": ["GSE140297", "GSE61710", "GSE37366", "GSE41032"], "statements": ["All the array data were uploaded to Gene Expression Omnibus (GEO) database as accession number GSE140297."], "basis": "The paper names GSE140297, GSE61710, GSE37366, GSE41032 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31805126", "data:geo:GSE140297"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE140297"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:50Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 38280, "completion_tokens": 1844, "cached_tokens": 785}}, "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:31805126", "type": "paper", "label": "pmid:31805126"}, {"id": "source:pmid:31805126", "type": "manuscript", "label": "PMID 31805126 full text"}, {"id": "data:geo:GSE140297", "type": "dataset", "label": "GEO GSE140297"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31805126", "type": "paper", "label": "pmid:31805126"}, {"id": "source:pmid:31805126", "type": "manuscript", "label": "PMID 31805126 full text"}, {"id": "data:geo:GSE140297", "type": "dataset", "label": "GEO GSE140297"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31805126", "type": "extraction", "used": ["source:pmid:31805126"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE140297", "type": "accession_resolution", "used": ["data:geo:GSE140297"], "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:31805126", "parent_hash": "sha256:a1c9b86d316878ed724e642ff5388d1253b3d0f9519e1a73cc853cbebc116d49", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE140297 licence not read", "asset:data:geo:GSE140297 not downloaded", "asset:data:geo:GSE37366 licence not read", "asset:data:geo:GSE37366 not downloaded", "asset:data:geo:GSE41032 licence not read", "asset:data:geo:GSE41032 not downloaded", "asset:data:geo:GSE61710 licence not read", "asset:data:geo:GSE61710 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["d in gliomas by analyzing cells, arrays, and RNA sequencing data of TCGA glioma patients. Furthermore, a", "ts with normal controls using microarray and RNA sequencing (RNA Seq) data from TCGA database, we found", "ormal control groups from the microarray and RNA sequencing (RNA Seq) data of TCGA database. Detection o"], "order_basis": "paper_text_order:1329", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ls and methods Cell culture, treatments, and transfection Minimum essential Eagle medium (MEM) was use", "tured cells for another 48 h. To conduct the transfection experiments, cells were seeded into a 12-wel", "LO 3’UTR reporter plasmids were respectively transfected with Lipofectamine 3000 (Invitrogen) accordi", "uced glioma cell viability. After cells were transfected with the indicated doses of NEDD4L cDNA-cont"], "order_basis": "paper_text_order:1991", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ses of IGF-1 and TMZ were added to overnight-cultured cells for the indicated times. For inhibitor", "then 200 ng/ml IGF-1 was added to overnight-cultured cells for another 48 h. To conduct the trans"], "order_basis": "paper_text_order:2654", "id": "assay:3"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["L in GBM patients with normal controls using microarray and RNA sequencing (RNA Seq) data from TCGA", "s compared to normal control groups from the microarray and RNA sequencing (RNA Seq) data of TCGA da"], "order_basis": "paper_text_order:3978", "id": "assay:4"}, {"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": ["mRNA levels were respectively measured by an immunoblotting assay and a real-time PCR. β-Actin and GAPDH", "24 h, NEDD4L protein levels were measured by immunoblotting assays. Cell viability was measured by an MT"], "order_basis": "paper_text_order:5186", "id": "assay:5"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ly measured by an immunoblotting assay and a real-time PCR. β-Actin and GAPDH levels were used as inter"], "order_basis": "paper_text_order:5213", "id": "assay:6"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ng assays. Cell viability was measured by an MTT assay. Data are the mean ± SD of three indep"], "order_basis": "paper_text_order:5670", "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":"2026-11-04T00:46:01+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}}}