{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32555395", "kind": "science-record", "revision": 8, "content_hash": "sha256:9fcf4f80e08e3b33377cb4351b00ecb70753b61c4f756f471248e8b6b3dcb594", "created_at": "2026-11-01T15:41:03Z", "updated_at": "2026-11-01T22:44:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of core genes in the progression of endometrial cancer and cancer cell-derived exosomes by an integrative analysis.", "doi": "10.1038/s41598-020-66872-3", "pmid": "32555395", "authors": ["Shuang Shi", "Qiang Tan", "Fuqiang Feng", "Heping Huang", "Jingjie Liang", "Dingren Cao", "Zhengguang Wang"], "journal": "Scientific reports", "year": 2020, "abstract": "Endometrial cancer is one of the most prevalent tumors of the female reproductive system causing serious health effects to women worldwide. Although numerous studies, including analysis of gene expression profile and cellular microenvironment have been reported in this field, pathogenesis of this disease remains unclear. In this study, we performed a system bioinformatics analysis of endometrial cancer using the Gene Expression Omnibus (GEO) datasets (GSE17025, GSE63678, and GSE115810) to identify the core genes. In addition, exosomes derived from endometrial cancer cells were also isolated and identified. First, we analyzed the differentially expressed genes (DEGs) between endometrial cancer tissues and normal tissues in clinic samples. We found that HAND2-AS1, PEG3, OGN, SFRP4, and OSR2 were co-expressed across all 3 datasets. Pathways analysis showed that several pathways associated with endometrial cancer, including \"p53 signaling pathway\", \"Glutathione metabolism\", \"Cell cycle\", and etc. Next, we selected DEGs with highly significant fold change and co-expressed across the 3 datasets and validated them in the TCGA database using Gene Expression Profiling Interactive Analysis (GEPIA). Finally, we performed a survival analysis and identified four genes (TOP2A, ASPM, EFEMP1, and FOXL2) that play key roles in endometrial cancer. We found up-regulation of TOP2A and ASPM in endometrial cancer tissues or cells, while EFEMP1 and FOXL2 were down-regulated. Furthermore, we isolated exosomes from the culturing supernatants of endometrial cancer cells (Ishikawa and HEC-1-A) and found that miR-133a, which regulates expression of FOXL2, were present in exosomes and that they could be delivered to normal endometrial cells. The common DEGs, pathways, and exosomal miRNAs identified in this study might play an important role in progression as well as diagnosis of endometrial cancer. In conclusion, our results provide insights into the pathogenesis and risk assessment of endometrial cancer. Even so, further studies are required to elucidate on the precise mechanism of action of these genes in endometrial cancer.", "claims": [{"id": "claim-method", "statement": "The analysis was performed using limma package at cut off values |log FC | > 1.0 and Adjust P value value <0.05 in these three datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32555395", "locator": "sections[14] \"Identification of differentially expressed genes\" paragraph 2", "quote": "The analysis was performed using limma package at cut off values |log FC | > 1.0 and Adjust P value value <0.05 in these three datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data that support the findings of this study are available in GEO at https://www.ncbi.nlm.nih.gov/geo/. These data were derived from the following resources available in the public domain: GSE17025, GSE63678 and GSE115810.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32555395", "locator": "sections[21] \"Data availibility\" paragraph 2", "quote": "The data that support the findings of this study are available in GEO at https://www.ncbi.nlm.nih.gov/geo/. These data were derived from the following resources available in the public domain: GSE17025, GSE63678 and GSE115810."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:32555395"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32555395", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-020-66872-3", "sha256": "sha256:6d97fd64145f89091d87851813287fb1edaf0ae6f0ca5aaefe79586771137b70", "bytes": 46804, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-020-66872-3", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7299953", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:32555395:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c25c4d2dc4c5cb5abbaeb01ad9c33c0a51f53fa426178de4ad2a493b8b1b69d1", "bytes": 950, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab2", "version": null, "note": "Top 10 differentially expressed genes in GSE63678.", "structure": {"pmcid": "PMC7299953", "section_index": 3, "section_title": "Identification of DEGs in endometrial cancer", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Top 10 differentially expressed genes in GSE63678.", "rows": [["Rank", "Probe set ID", "Gene symbol", "Description", "Regulation"], ["1", "209242_at", "PEG3", "paternally expressed 3", "Down-regulation"], ["2", "219791_s_at", "HAND2-AS1", "HAND2 antisense RNA 1", "Down-regulation"], ["3", "206067_s_at", "WT1", "WT1 transcription factor", "Down-regulation"], ["4", "205433_at", "BCHE", "butyrylcholinesterase", "Down-regulation"], ["5", "218730_s_at", "OGN", "osteoglycin", "Down-regulation"], ["6", "204653_at", "TFAP2A", "transcription factor AP-2 alpha", "Up-regulation"], ["7", "201839_s_at", "EPCAM", "epithelial cell adhesion molecule", "Up-regulation"], ["8", "201596_x_at", "KRT18", "keratin 18", "Up-regulation"], ["9", "219148_at", "PBK", "PDZ binding kinase", "Up-regulation"], ["10", "204580_at", "MMP12", "matrix metallopeptidase 12", "Up-regulation"]], "row_count": 11, "column_count": 5, "numeric_cells": 27, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:32555395:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ba71548dece57e308a01fe9503394f0c60b0023ba230a7f97d5e0518b758f774", "bytes": 974, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#Tab1", "version": null, "note": "Top 10 differentially expressed genes in GSE17025.", "structure": {"pmcid": "PMC7299953", "section_index": 3, "section_title": "Identification of DEGs in endometrial cancer", "row_count": 11, "column_count": 5}, "table": {"label": "Table 1", "caption": "Top 10 differentially expressed genes in GSE17025.", "rows": [["Rank", "Probe set ID", "Gene symbol", "Description", "Regulation"], ["1", "202768_at", "FOSB", "FBJ osteosarcoma oncogene B", "Down-regulation"], ["2", "206622_at", "TRH", "thyrotropin releasing hormone", "Down-regulation"], ["3", "219791_s_at", "HAND2-AS1", "HAND2 antisense RNA 1", "Down-regulation"], ["4", "206228_at", "PAX2", "paired box 2", "Down-regulation"], ["5", "209242_at", "PEG3", "paternally expressed 3", "Down-regulation"], ["6", "201291_s_at", "TOP2A", "DNA topoisomerase II alpha", "Up-regulation"], ["7", "1553655_at", "CDC20B", "cell division cycle 20B", "Up-regulation"], ["8", "219918_s_at", "ASPM", "abnormal spindle microtubule assembly", "Up-regulation"], ["9", "202018_s_at", "LTF", "lactotransferrin", "Up-regulation"], ["10", "205476_at", "CCL20", "C-C motif chemokine ligand 20", "Up-regulation"]], "row_count": 11, "column_count": 5, "numeric_cells": 27, "header_rows": 1, "locator": "section[3]/table-wrap[2]#Tab1"}}, {"id": "asset:table:pmid:32555395:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:de40bbb3660b773cc2b40a37d8995b85ff899527d6dcab9cb4da6dfe103ae1fb", "bytes": 993, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[3]#Tab3", "version": null, "note": "Top 10 differentially expressed genes in GSE115810.", "structure": {"pmcid": "PMC7299953", "section_index": 3, "section_title": "Identification of DEGs in endometrial cancer", "row_count": 11, "column_count": 5}, "table": {"label": "Table 3", "caption": "Top 10 differentially expressed genes in GSE115810.", "rows": [["Rank", "Probe set ID", "Gene symbol", "Description", "Regulation"], ["1", "204051_s_at", "SFRP4", "secreted frizzled related protein 4", "Down-regulation"], ["2", "219791_s_at", "HAND2-AS1", "HAND2 antisense RNA 1", "Down-regulation"], ["3", "220102_at", "FOXL2", "forkhead box L2", "Down-regulation"], ["4", "201842_s_at", "EFEMP1", "EGF containing fibulin extracellular matrix protein 1", "Down-regulation"], ["5", "206637_at", "P2RY14", "purinergic receptor P2Y14", "Down-regulation"], ["6", "201195_s_at", "SLC7A5", "solute carrier family 7 member 5", "Up-regulation"], ["7", "202357_s_at", "CFB", "complement factor B", "Up-regulation"], ["8", "209875_s_at", "SPP1", "secreted phosphoprotein 1", "Up-regulation"], ["9", "204846_at", "CP", "ceruloplasmin", "Up-regulation"], ["10", "204623_at", "TFF3", "trefoil factor 3", "Up-regulation"]], "row_count": 11, "column_count": 5, "numeric_cells": 28, "header_rows": 1, "locator": "section[3]/table-wrap[3]#Tab3"}}, {"id": "asset:table:pmid:32555395:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ec435786b6e982bc303f47e32df1348e81c3d9df792ed70cbac0022dd3432a47", "bytes": 1086, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#Tab4", "version": null, "note": "Top 10 pathways in pathway relation network of the 3 datasets (GSE17025, GSE63678 and GSE115810).", "structure": {"pmcid": "PMC7299953", "section_index": 5, "section_title": "Signaling pathway enrichment analysis", "row_count": 11, "column_count": 4}, "table": {"label": "Table 4", "caption": "Top 10 pathways in pathway relation network of the 3 datasets (GSE17025, GSE63678 and GSE115810).", "rows": [["Rank", "GSE17025", "GSE63678", "GSE115810"], ["1", "Cell cycle", "Cell cycle", "ECM-receptor interaction"], ["2", "Leukocyte transendothelial migration", "p53 signaling pathway", "PI3K-Akt signaling pathway"], ["3", "PPAR signaling pathway", "Oocyte meiosis", "Focal adhesion"], ["4", "Pathways in cancer", "Proteoglycans in cancer", "Pathways in cancer"], ["5", "Glutathione metabolism", "Progesterone-mediated oocyte maturation", "Melanoma"], ["6", "p53 signaling pathway", "Melanoma", "Protein digestion and absorption"], ["7", "ECM-receptor interaction", "Mineral absorption", "Cell adhesion molecules (CAMs)"], ["8", "Bile secretion", "Biosynthesis of antibiotics", "MAPK signaling pathway"], ["9", "Progesterone-mediated oocyte maturation", "Prostate cancer", "Amoebiasis"], ["10", "Chemokine signaling pathway", "Pathways in cancer", "Complement and coagulation cascades"]], "row_count": 11, "column_count": 4, "numeric_cells": 15, "header_rows": 1, "locator": "section[5]/table-wrap[1]#Tab4"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The analysis was performed using limma package at cut off values |log FC | > 1.0 and Adjust P value value <0.05 in these three datasets."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The data that support the findings of this study are available in GEO at https://www.ncbi.nlm.nih.gov/geo/. These data were derived from the following resources available in the public domain: GSE17025, GSE63678 and GSE115810."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32555395", "asset:table:pmid:32555395:1", "asset:table:pmid:32555395:2", "asset:table:pmid:32555395:3", "asset:table:pmid:32555395:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:04:16Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 36912, "completion_tokens": 1621, "cached_tokens": 792}}, "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:32555395", "type": "paper", "label": "pmid:32555395"}, {"id": "source:pmid:32555395", "type": "manuscript", "label": "PMID 32555395 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32555395", "type": "paper", "label": "pmid:32555395"}, {"id": "source:pmid:32555395", "type": "manuscript", "label": "PMID 32555395 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32555395", "type": "extraction", "used": ["source:pmid:32555395"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:32555395", "parent_hash": "sha256:68f04e70c6b5986cd5858a452bf52d4830b399c257d55d4779d72b1081f0f327", "fork_of": null, "generation": 7}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"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": ["ium supplemented with 10% FBS. while HEC-1-A cell lines were cultured in McCOY’s 5 A (SIGMA) supplemented with 10%", ", China). Ishikawa and 4003 cells lines were cultured in DMEM (Gibco) culture medium supplemented wit", "with 10% FBS. while HEC-1-A cell lines were cultured in McCOY’s 5 A (SIGMA) supplemented with 10% FB"], "order_basis": "paper_text_order:4975", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The analysis was performed using limma package at cut off values |log FC | > 1.0 and Adjust P value value <0.05 in these three datasets."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T00:40:06+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}}}