{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39448672", "kind": "science-record", "revision": 3, "content_hash": "sha256:0aebe399fb13d1ea88cc0ce1b720d211d7b0584cd076b30372cf2c503fd300fb", "created_at": "2026-11-01T20:29:42Z", "updated_at": "2026-11-01T22:55:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of SLC31A1 as a prognostic biomarker and a target for therapeutics in breast cancer.", "doi": "10.1038/s41598-024-76162-x", "pmid": "39448672", "authors": ["Hongtao Fu", "Shanshan Dong", "Kun Li"], "journal": "Scientific reports", "year": 2024, "abstract": "Copper-induced cell death is regulated through protein lipoylation, which is critical for gene expression and phenotypic regulation. Neverless, the role of Cuproptosis-related genes in breast cancer (BC) remains unknown. This study aimed to construct a prognostic signature based on the expression of Cuproptosis-related genes in order to guide the diagnosis and treatment for BC. Cuproptosis-related genes prognostic signature has ata of 1250 BC tissues and 583 normal breast tissues were obtained from The Cancer Genome Atlas (TCGA), Genotype Tissue Expression (GTEx), and GEO GSE65212. The prognostic signature was established and evaluated with nineteen Cuproptosis-related genes. A series of in silico analyses based on SLC31A1, included expression analysis, independent prognostic analysis, correlation analysis, immune-related analysis and survival analysis. Finally, a series of cell experiments (including quantitative real-time polymerase chain reaction and western blot), and mice experiments were applied to evaluate the impact of SLC31A1 on BC. Cuproptosis-related genes prognostic signature has good predictive promising for survival in BC patients. We discovered that SLC31A1SLC31A1 was overexpressed in BC and was its independent prognostic factor. High expression of the SLC31A1 was correlated with poor prognosis and immune infiltrating of BC. SLC31A1 expression is associated with immune, chemotherapeutic and targeted therapy outcomes in BC. The proliferation, migration, and invasiveness of Her2 + enriched BC cells were decreased by SLC31A1 knockdown, also resulting in a decrease in tumor volume in mouse model. SLC31A1 is a candidate biomarker or therapeutic target in precision oncology, with diagnostic and prognostic significance in BC.", "claims": [{"id": "claim-method", "statement": "We performed through multivariate cox regression analysis and then iterative analysis through step function to obtain the prognosis model. We used log rank and univariate Cox regression to compare the difference in survival between two or more groups, and performed timeROC (v 0.4) analysis to determine the accuracy of the discriminant prediction model.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39448672", "locator": "sections[5] \"Cuproptosis-related genes prognostic model\" paragraph 2", "quote": "We performed through multivariate cox regression analysis and then iterative analysis through step function to obtain the prognosis model. We used log rank and univariate Cox regression to compare the difference in survival between two or more groups, and performed timeROC (v 0.4) analysis to determine the accuracy of the discriminant prediction model."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated and analysed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GEO (GSE65212, http://www.ncbi.nlm.nih.gov/geo).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39448672", "locator": "sections[42] \"notes\" paragraph 1", "quote": "The datasets generated and analysed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GEO (GSE65212, http://www.ncbi.nlm.nih.gov/geo)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The low-risk subgroup had better survival outcomes than the high-risk subgroup (p = 7.84e-06).", "kind": "quantitative", "target": {"value": 7.0, "unit": "p-value", "tolerance": null, "source": "K-M survival curves showed that the outcomes of BC cases in the low-risk subgroup were better than those with high-risk (p = 7.84e-06) (Fig. 1B, d)."}, "evidence": [{"asset": "source:pmid:39448672", "locator": "sections[25] \"Construction of a prognostic signature in cuproptosis-related genes\" paragraph 2", "quote": "K-M survival curves showed that the outcomes of BC cases in the low-risk subgroup were better than those with high-risk (p = 7.84e-06) (Fig. 1B, d)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The low-risk subgroup had better survival outcomes than the high-risk subgroup (p = 7.84e-06).", "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:39448672"], "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:GSE65212"], "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:GSE65212"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39448672", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-024-76162-x", "sha256": "sha256:2e7fdb7a5c788dabf7e655c32a641853b9fc32a09c194f758b9cf8cea6059135", "bytes": 48883, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-024-76162-x", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11502855", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE65212", "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=GSE65212", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65212", "version": null, "note": "The datasets generated and analysed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GEO (GSE65212, http://www.ncbi.nlm.nih.gov/geo).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and analysed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GEO (GSE65212, http://www.ncbi.nlm.nih.gov/geo).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1589620", "GSM1589621", "GSM1589622", "GSM1589623", "GSM1589624", "GSM1589625", "GSM1589626", "GSM1589627", "GSM1589628", "GSM1589629", "GSM1589630", "GSM1589631", "GSM1589632", "GSM1589633", "GSM1589634", "GSM1589635", "GSM1589636", "GSM1589637", "GSM1589638", "GSM1589639", "GSM1589640", "GSM1589641", "GSM1589642", "GSM1589643", "GSM1589644", "GSM1589645", "GSM1589646", "GSM1589647", "GSM1589648", "GSM1589649", "GSM1589650", "GSM1589651", "GSM1589652", "GSM1589653", "GSM1589654", "GSM1589655", "GSM1589656", "GSM1589657", "GSM1589658", "GSM1589659", "GSM1589660", "GSM1589661", "GSM1589662", "GSM1589663", "GSM1589664", "GSM1589665", "GSM1589666", "GSM1589667", "GSM1589668", "GSM1589669", "GSM1589670", "GSM1589671", "GSM1589672", "GSM1589673", "GSM1589674", "GSM1589675", "GSM1589676", "GSM1589677", "GSM1589678", "GSM1589679", "GSM1589680", "GSM1589681", "GSM1589682", "GSM1589683", "GSM1589684", "GSM1589685", "GSM1589686", "GSM1589687", "GSM1589688", "GSM1589689", "GSM1589690", "GSM1589691", "GSM1589692", "GSM1589693", "GSM1589694", "GSM1589695", "GSM1589696", "GSM1589697", "GSM1589698", "GSM1589699", "GSM1589700", "GSM1589701", "GSM1589702", "GSM1589703", "GSM1589704", "GSM1589705", "GSM1589706", "GSM1589707", "GSM1589708", "GSM1589709", "GSM1589710", "GSM1589711", "GSM1589712", "GSM1589713", "GSM1589714", "GSM1589715", "GSM1589716", "GSM1589717", "GSM1589718", "GSM1589719", "GSM1589720", "GSM1589721", "GSM1589722", "GSM1589723", "GSM1589724", "GSM1589725", "GSM1589726", "GSM1589727", "GSM1589728", "GSM1589729", "GSM1589730", "GSM1589731", "GSM1589732", "GSM1589733", "GSM1589734", "GSM1589735", "GSM1589736", "GSM1589737", "GSM1589738", "GSM1589739", "GSM1589740", "GSM1589741", "GSM1589742", "GSM1589743", "GSM1589744", "GSM1589745", "GSM1589746", "GSM1589747", "GSM1589748", "GSM1589749", "GSM1589750", "GSM1589751", "GSM1589752", "GSM1589753", "GSM1589754", "GSM1589755", "GSM1589756", "GSM1589757", "GSM1589758", "GSM1589759", "GSM1589760", "GSM1589761", "GSM1589762", "GSM1589763", "GSM1589764", "GSM1589765", "GSM1589766", "GSM1589767", "GSM1589768", "GSM1589769", "GSM1589770", "GSM1589771", "GSM1589772", "GSM1589773", "GSM1589774", "GSM1589775", "GSM1589776", "GSM1589777", "GSM1589778", "GSM1589779", "GSM1589780", "GSM1589781", "GSM1589782", "GSM1589783", "GSM1589784", "GSM1589785", "GSM1589786", "GSM1589787", "GSM1589788", "GSM1589789", "GSM1589790", "GSM1589791", "GSM1589792", "GSM1589793", "GSM1589794", "GSM1589795", "GSM1589796", "GSM1589797"], "sample_count": 178, "group_sizes": null, "group_sizes_basis": null, "platform": "14877", "taxon": "Homo sapiens", "title": "Expression profiling of breast cancer samples from Institut Curie (Maire cohort) -- BrainArray CDF", "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:GSE65212 not downloaded", "asset:data:geo:GSE65212 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We performed through multivariate cox regression analysis and then iterative analysis through step function to obtain the prognosis model. We used log rank and univariate Cox regression to compare the difference in survival between two or more groups, and performed timeROC (v 0.4) analysis to determine the accuracy of the discriminant prediction model."}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log rank"}}, {"id": "method-3", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 7.0, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE65212"], "resolved_accessions": ["GSE65212"], "statements": ["The datasets generated and analysed during the current study are available in the TCGA repository (https://portal.gdc.cancer.gov/), GEO (GSE65212, http://www.ncbi.nlm.nih.gov/geo)."], "basis": "The paper names GSE65212 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:39448672", "data:geo:GSE65212"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE65212"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:36:55Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14362, "completion_tokens": 2243, "cached_tokens": 256}}, "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:39448672", "type": "paper", "label": "pmid:39448672"}, {"id": "source:pmid:39448672", "type": "manuscript", "label": "PMID 39448672 full text"}, {"id": "data:geo:GSE65212", "type": "dataset", "label": "GEO GSE65212"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39448672", "type": "paper", "label": "pmid:39448672"}, {"id": "source:pmid:39448672", "type": "manuscript", "label": "PMID 39448672 full text"}, {"id": "data:geo:GSE65212", "type": "dataset", "label": "GEO GSE65212"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39448672", "type": "extraction", "used": ["source:pmid:39448672"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE65212", "type": "accession_resolution", "used": ["data:geo:GSE65212"], "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:39448672", "parent_hash": "sha256:3fe597eaba9930c1ed7c484fff2d7c752f25329e1e2a8a6b7526985a9bc99e6d", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE65212 licence not read", "asset:data:geo:GSE65212 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["tive real-time polymerase chain reaction and western blot), and mice experiments were applied to evalu"], "order_basis": "paper_text_order:1023", "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": ["enriched BC cells were decreased by SLC31A1 knockdown, also resulting in a decrease in tumor volum", "Methods Cell culture and transfection Cell line were from the Chinese Academy of S", "GGAGAATT-3′, GeneChem, Shanghai, China) were transfected into the SKBR3 cell lines using Lipofectamin", "rding to the manufacturer’s protocols. After transfection, the SKBR3 cell lines were harvested for fur"], "order_basis": "paper_text_order:1619", "id": "assay:2"}, {"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": ["o resulting in a decrease in tumor volume in mouse model. SLC31A1 is a candidate biomarker or therape", "o resulting in a decrease in tumor volume in mouse model. SLC31A1 is a candidate biomarker or t"], "order_basis": "paper_text_order:1677", "id": "assay:3"}, {"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": ["se Academy of Science (Shanghai, China). The cell line was grown in a sterile and humidified cell culture inc", "d 5% CO2. MCF-7, BT474, SKBR3 and MDA-MB-231 cell lines was cultured using MEM (Procell, Wuhan, China) containing", "ntration of 10% FBS and 1% P/S. MCF-10 A was cultured with the following medium: DMEM + 5% HS + 20ng/ml", "cell culture incubator at 37 °C and 5% CO2. MCF-7, BT474, SKBR3 and MDA-MB-231 cell lines was"], "order_basis": "paper_text_order:1931", "id": "assay:4"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We performed through multivariate cox regression analysis and then iterative analysis through step function to obtain the prognosis model. We used log rank and univariate Cox regression to compare the difference in survival between two or more groups, and performed timeROC (v 0.4) analysis to determine the accuracy of the discriminant prediction model."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"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":"2026-11-04T01:24:18+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}}}