{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28932774", "kind": "science-record", "revision": 8, "content_hash": "sha256:50d99e2da42f88167ad415a333a465742b9d853a10472b30ef097d88862f07c3", "created_at": "2026-11-01T15:40:28Z", "updated_at": "2026-11-01T22:43:06Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptomic and bioinformatics analysis of the early time-course of the response to prostaglandin F2 alpha in the bovine corpus luteum.", "doi": "10.1016/j.dib.2017.08.026", "pmid": "28932774", "authors": ["Heather Talbott", "Xiaoying Hou", "Fang Qiu", "Pan Zhang", "Chittibabu Guda", "Fang Yu", "Robert A Cushman", "Jennifer R Wood", "Cheng Wang", "Andrea S Cupp", "John S Davis"], "journal": "Data in brief", "year": 2017, "abstract": "RNA expression analysis was performed on the corpus luteum tissue at five time points after prostaglandin F2 alpha treatment of midcycle cows using an Affymetrix Bovine Gene v1 Array. The normalized linear microarray data was uploaded to the NCBI GEO repository (GSE94069). Subsequent statistical analysis determined differentially expressed transcripts ± 1.5-fold change from saline control with P ≤ 0.05. Gene ontology of differentially expressed transcripts was annotated by DAVID and Panther. Physiological characteristics of the study animals are presented in a figure. Bioinformatic analysis by Ingenuity Pathway Analysis was curated, compiled, and presented in tables. A dataset comparison with similar microarray analyses was performed and bioinformatics analysis by Ingenuity Pathway Analysis, DAVID, Panther, and String of differentially expressed genes from each dataset as well as the differentially expressed genes common to all three datasets were curated, compiled, and presented in tables. Finally, a table comparing four bioinformatics tools' predictions of functions associated with genes common to all three datasets is presented. These data have been further analyzed and interpreted in the companion article \"Early transcriptome responses of the bovine mid-cycle corpus luteum to prostaglandin F2 alpha includes cytokine signaling\" [1].", "claims": [{"id": "claim-method", "statement": "Linear Models for Microarray Analysis (LIMMA) [6] in the Bioconductor suite [7] under the statistical program R [8] was applied to compare the log ratio between each of the PGF2α time points and the saline control after adjusting for the box effect.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28932774", "locator": "sections[8] \"Microarray statistics\" paragraph 2", "quote": "Linear Models for Microarray Analysis (LIMMA) [6] in the Bioconductor suite [7] under the statistical program R [8] was applied to compare the log ratio between each of the PGF2α time points and the saline control after adjusting for the box effect."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28932774", "locator": "sections[2] \"table-wrap\" paragraph 1", "quote": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables"}], "state": "complete"}, {"id": "claim-target-result", "statement": "RNA expression in the corpus luteum was analyzed with Affymetrix microarrays, and differentially expressed transcripts were identified by ≥1.5-fold change from saline controls with P ≤ 0.05 using normalized linear data available from NCBI GEO under GSE94069.", "kind": "quantitative", "target": {"value": 1.5, "unit": "fold change", "tolerance": null, "source": "Subsequent statistical analysis determined differentially expressed transcripts ± 1.5-fold change from saline control with P ≤ 0.05."}, "evidence": [{"asset": "source:pmid:28932774", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "RNA expression analysis was performed on the corpus luteum tissue at five time points after prostaglandin F2 alpha treatment of midcycle cows using an Affymetrix Bovine Gene v1 Array."}, {"asset": "source:pmid:28932774", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The normalized linear microarray data was uploaded to the NCBI GEO repository (GSE94069)."}, {"asset": "source:pmid:28932774", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Subsequent statistical analysis determined differentially expressed transcripts ± 1.5-fold change from saline control with P ≤ 0.05."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "RNA expression in the corpus luteum was analyzed with Affymetrix microarrays, and differentially expressed transcripts were identified by ≥1.5-fold change from saline controls with P ≤ 0.05 using normalized linear data available from NCBI GEO under GSE94069.", "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:28932774"], "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:GSE23348"], "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:GSE23348"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28932774", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2017.08.026", "sha256": "sha256:022d0bfb6ce7ec493b50112349054e0aed27f0f0b00463b7414fbac087afdc08", "bytes": 19970, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2017.08.026", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5596332", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE23348", "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=GSE23348", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE23348", "version": null, "note": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM572967", "GSM572968", "GSM572969", "GSM572970", "GSM572971", "GSM572972", "GSM572973", "GSM572974", "GSM572975", "GSM572976", "GSM572977", "GSM572978", "GSM572979", "GSM572980", "GSM572981", "GSM572982", "GSM572983", "GSM572984", "GSM572985", "GSM572986", "GSM572987", "GSM572988", "GSM572989", "GSM572990", "GSM572991", "GSM572992", "GSM572993", "GSM572994", "GSM572995", "GSM572996"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "2112", "taxon": "Bos taurus", "title": "Prostaglandin F2α -induced changes in transcriptome of bovine mid cycle versus early corpus luteum", "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:GSE27961", "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=GSE27961", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27961", "version": null, "note": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM691457", "GSM691458", "GSM691459", "GSM691460", "GSM691461", "GSM691462", "GSM691463", "GSM691464", "GSM691465", "GSM691466", "GSM691467", "GSM691468"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "2112", "taxon": "Bos taurus; Bubalus bubalis", "title": "Global changes in gene expression of buffalo cow corpus luteum during prostaglandin F2alpha- induced luteolysis", "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:GSE94069", "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=GSE94069", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE94069", "version": null, "note": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2468219", "GSM2468220", "GSM2468221", "GSM2468222", "GSM2468223", "GSM2468224", "GSM2468225", "GSM2468226", "GSM2468227", "GSM2468228", "GSM2468229", "GSM2468230", "GSM2468231", "GSM2468232", "GSM2468233"], "sample_count": 15, "group_sizes": null, "group_sizes_basis": null, "platform": "17645", "taxon": "Bos taurus", "title": "Early temporal transcriptome responses of the bovine mid-cycle corpus luteum to prostaglandin F2 alpha indicates cytokine activation", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28932774:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0c3dfd47f95634018c6c9786a65e8a3a918c352b7eb4d6952ecfce2c85bf7a8a", "bytes": 3718, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#t0005", "version": null, "note": "Canonical pathways of PGF2α time course ⁎.", "structure": {"pmcid": "PMC5596332", "section_index": 4, "section_title": "1. Data", "row_count": 37, "column_count": 10}, "table": {"label": "Table 1", "caption": "Canonical pathways of PGF2α time course ⁎.", "rows": [["", "0.5 h", "1 h", "2 h", "4 h", ""], ["Ingenuity Canonical Pathways", "z-score", "P-value (B-H)", "z-score", "P-value (B-H)", "z-score", "P-value (B-H)", "z-score", "P-value (B-H)", "|Avg.| z-score"], ["Death Receptor Signaling", "", "", "", "", "", "", "−2.71", "3.23E-01", "0.90"], ["Integrin Signaling", "", "", "", "", "", "", "−2.68", "4.69E-01", "0.89"], ["UVA-Induced MAPK Signaling", "", "2.51E-02", "", "2.65E-01", "", "7.96E-01", "−2.50", "1.64E-01", "0.83"], ["MIF Regulation of Innate Immunity", "", "1.58E-02", "", "8.71E-02", "", "6.44E-01", "2.45", "3.44E-01", "0.82"], ["Retinoic acid Mediated Apoptosis Signaling", "", "", "", "", "", "4.81E-01", "−2.45", "1.78E-01", "0.82"], ["Melanocyte Development and Pigmentation Signaling", "", "", "", "", "", "", "−2.32", "1.64E-01", "0.77"], ["TREM1 Signaling", "", "", "", "", "", "7.89E-01", "2.31", "1.10E-01", "0.77"], ["CREB Signaling in Neurons", "", "", "", "", "", "", "−2.18", "4.61E-01", "0.73"], ["Aldosterone Signaling in Epithelial Cells", "", "4.37E-02", "", "7.76E-02", "", "4.89E-01", "−2.14", "9.55E-02", "0.71"], ["NGF Signaling", "", "", "", "", "", "8.39E-01", "−2.13", "4.79E-02", "0.71"], ["Calcium Signaling", "", "", "", "", "", "", "−2.11", "2.64E-01", "0.53"], ["Toll-like Receptor Signaling", "", "2.24E-02", "", "6.61E-02", "2.00", "2.99E-01", "2.14", "2.69E-02", "1.03"], ["ILK Signaling", "", "5.25E-02", "2.45", "2.34E-02", "1.63", "7.31E-01", "", "1.60E-01", "1.36"], ["Inflammasome pathway", "", "", "", "", "", "7.55E-01", "2.00", "2.98E-01", "0.50"], ["MIF-mediated Glucocorticoid Regulation", "", "", "", "", "", "", "2.00", "5.16E-01", "0.50"], ["JAK/Stat Signaling", "", "2.24E-02", "", "2.45E-02", "", "3.49E-01", "−2.00", "8.32E-02", "0.50"], ["Granzyme B Signaling", "", "", "", "", "", "7.43E-01", "−2.00", "2.30E-01", "0.50"], ["Dopamine-DARPP32 Feedback in cAMP Signaling", "", "", "", "6.15E-01", "", "", "−2.00", "4.50E-01", "0.50"], ["Signaling by Rho Family GTPases", "", "7.59E-02", "2.00", "1.61E-01", "", "", "", "", "0.67"], ["LPS/IL-1 Mediated Inhibition of RXR Function", "", "2.57E-01", "", "", "2.00", "7.43E-01", "1.90", "5.79E-01", "0.97"], ["LXR/RXR Activation", "", "", "", "", "−1.34", "4.99E-01", "−2.32", "1.61E-01", "0.92"], ["Cholecystokinin/Gastrin-mediated Signaling", "", "2.45E-02", "2.00", "3.89E-02", "2.65", "2.99E-01", "0.69", "6.76E-02", "1.33"], ["TGF-β Signaling", "", "2.24E-02", "", "7.76E-02", "2.00", "5.45E-01", "1.16", "1.66E-01", "0.79"], ["Acute Phase Response Signaling", "", "4.37E-02", "1.00", "7.76E-02", "2.12", "4.81E-01", "1.53", "1.23E-01", "1.16"], ["HMGB1 Signaling", "", "3.09E-02", "2.00", "2.45E-02", "1.89", "3.44E-01", "0.69", "1.34E-01", "1.14"], ["Gαq Signaling", "", "", "", "6.41E-01", "−0.45", "7.46E-01", "−2.07", "3.13E-01", "0.63"], ["Colorectal Cancer Metastasis Signaling", "", "7.41E-02", "2.00", "1.61E-01", "1.13", "7.52E-01", "−0.38", "2.59E-01", "0.69"], ["Endothelin-1 Signaling", "", "4.90E-02", "2.00", "8.71E-02", "", "", "−0.66", "3.94E-01", "0.34"], ["PI3K Signaling in B Lymphocytes", "", "1.41E-02", "", "1.22E-01", "1.34", "4.81E-01", "−0.21", "2.69E-02", "0.28"], ["Corticotropin Releasing Hormone Signaling", "", "1.41E-02", "", "3.89E-02", "", "6.43E-01", "−0.54", "2.00E-01", "0.18"], ["IL-8 Signaling", "", "5.62E-02", "2.00", "1.08E-01", "0.45", "8.39E-01", "−1.09", "4.00E-01", "0.34"], ["NRF2-mediated Oxidative Stress Response", "", "1.41E-02", "0.45", "1.00E-02", "0.38", "1.75E-01", "0.24", "1.11E-01", "0.27"], ["Cardiac Hypertrophy Signaling", "", "2.86E-01", "", "2.88E-01", "1.63", "7.99E-01", "−2.04", "1.71E-01", "0.10"], ["IGF-1 Signaling", "", "1.41E-02", "1.00", "1.91E-02", "0.82", "2.41E-01", "−1.29", "8.51E-02", "0.13"], ["IL-17A Signaling in Gastric Cells", "", "1.41E-02", "", "6.61E-02", "", "4.99E-01", "", "6.10E-01", ""]], "row_count": 37, "column_count": 10, "numeric_cells": 204, "header_rows": 2, "locator": "section[4]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:28932774:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6a3d6dca90c092ec36f794bf0abd371b5bf319c87694958c561ec04d7092fab4", "bytes": 5881, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[2]#t0010", "version": null, "note": "Canonical pathways of dataset comparison ⁎.", "structure": {"pmcid": "PMC5596332", "section_index": 4, "section_title": "1. Data", "row_count": 62, "column_count": 8}, "table": {"label": "Table 2", "caption": "Canonical pathways of dataset comparison ⁎.", "rows": [["", "GSE94069", "GSE23348", "GSE27961", ""], ["Ingenuity Canonical Pathways", "z-score", "P-value (B-H)", "z-score", "P-value (B-H)", "z-score", "P-value (B-H)", "|Avg.| z-score"], ["TREM1 Signaling", "2.31", "1.90E-01", "4.24", "3.55E-01", "2.24", "4.34E-01", "2.93"], ["p38 MAPK Signaling", "1.34", "7.94E-01", "3.36", "1.66E-01", "2.53", "1.75E-01", "2.41"], ["Acute Phase Response Signaling", "1.53", "1.19E-01", "3.58", "2.19E-01", "2.12", "6.24E-01", "2.41"], ["Dendritic Cell Maturation", "", "1.13E-01", "3.27", "2.90E-01", "1.41", "5.18E-01", "2.34"], ["Inflammasome pathway", "2.00", "3.20E-01", "2.65", "5.13E-01", "", "5.10E-01", "2.33"], ["MIF Regulation of Innate Immunity", "2.45", "3.52E-01", "2.00", "2.67E-01", "", "", "2.23"], ["CREB Signaling in Neurons", "−2.18", "4.67E-01", "", "", "", "", "2.18"], ["LPS/IL-1 Mediated Inhibition of RXR Function", "1.90", "5.85E-01", "2.45", "1.80E-01", "", "2.26E-01", "2.18"], ["Role of IL-17F in Allergic Inflammatory Airway Diseases", "1.27", "4.68E-01", "3.00", "1.20E-01", "2.24", "1.35E-01", "2.17"], ["LXR/RXR Activation", "−2.32", "1.17E-01", "−2.83", "1.35E-01", "−1.34", "4.28E-01", "2.16"], ["Aldosterone Signaling in Epithelial Cells", "−2.14", "9.12E-01", "", "1.75E-01", "", "4.99E-01", "2.14"], ["Type I Diabetes Mellitus Signaling", "", "6.11E-01", "2.11", "4.70E-01", "", "", "2.11"], ["IL-6 Signaling", "1.23", "2.57E-01", "3.41", "2.75E-01", "1.67", "3.27E-01", "2.10"], ["MIF-mediated Glucocorticoid Regulation", "2.00", "5.18E-01", "2.00", "1.61E-01", "", "", "2.00"], ["Granzyme B Signaling", "−2.00", "2.32E-01", "", "6.98E-01", "", "7.60E-01", "2.00"], ["Dopamine-DARPP32 Feedback in cAMP Signaling", "−2.00", "4.62E-01", "", "", "", "", "2.00"], ["Role of Wnt/GSK-3β Signaling in the Pathogenesis of Influenza", "", "", "", "", "2.00", "5.10E-01", "2.00"], ["Toll-like Receptor Signaling", "2.14", "2.57E-01", "2.71", "5.62E-01", "1.00", "6.24E-01", "1.95"], ["PI3K/AKT Signaling", "2.13", "2.57E-01", "1.90", "6.92E-01", "1.67", "3.83E-01", "1.90"], ["Actin Nucleation by ARP-WASP Complex", "", "", "1.63", "1.58E-01", "2.00", "5.10E-01", "1.82"], ["ILK Signaling", "", "1.53E-01", "2.32", "5.25E-01", "1.29", "1.59E-01", "1.81"], ["Retinoic acid Mediated Apoptosis Signaling", "−2.45", "1.74E-01", "-1.00", "1.61E-01", "", "7.26E-01", "1.73"], ["HMGB1 Signaling", "0.45", "1.90E-01", "2.99", "2.82E-01", "1.67", "3.45E-01", "1.70"], ["Regulation of Actin-based Motility by Rho", "", "", "1.34", "5.77E-01", "2.00", "7.60E-01", "1.67"], ["Rac Signaling", "", "4.67E-01", "2.14", "1.70E-01", "1.13", "5.31E-01", "1.64"], ["Cholecystokinin/Gastrin-mediated Signaling", "0.69", "7.80E-01", "2.31", "2.57E-01", "1.89", "4.75E-01", "1.63"], ["VDR/RXR Activation", "0.82", "1.19E-01", "1.67", "2.34E-01", "2.24", "2.82E-01", "1.58"], ["NF-κB Signaling", "0.54", "2.57E-01", "3.27", "2.75E-01", "0.91", "4.34E-01", "1.57"], ["iNOS Signaling", "1.00", "1.14E-01", "2.00", "3.21E-01", "", "", "1.50"], ["Role of Pattern Recognition Receptors in Recognition of Bacteria and Viruses", "−0.28", "1.66E-01", "3.21", "4.37E-01", "", "4.84E-01", "1.47"], ["Ephrin Receptor Signaling", "", "", "0.82", "3.93E-01", "2.00", "5.85E-01", "1.41"], ["Agrin Interactions at Neuromuscular Junction", "0.38", "5.27E-01", "2.00", "5.86E-01", "1.63", "1.59E-01", "1.34"], ["Tec Kinase Signaling", "−1.21", "5.31E-01", "3.50", "7.80E-01", "1.41", "6.59E-01", "1.23"], ["ERK5 Signaling", "0.28", "8.32E-01", "1.41", "5.75E-01", "2.00", "5.51E-01", "1.23"], ["Production of Nitric Oxide and Reactive Oxygen Species in Macrophages", "−0.76", "1.90E-01", "3.15", "3.39E-01", "", "", "1.20"], ["UVA-Induced MAPK Signaling", "−2.67", "1.19E-01", "", "1.90E-01", "0.45", "5.51E-01", "1.11"], ["PI3K Signaling in B Lymphocytes", "−0.21", "2.57E-01", "2.36", "5.13E-01", "", "", "1.08"], ["Colorectal Cancer Metastasis Signaling", "−0.56", "2.18E-01", "2.70", "7.80E-01", "1.00", "3.70E-01", "1.05"], ["Basal Cell Carcinoma Signaling", "−0.45", "6.34E-01", "", "", "2.45", "3.70E-01", "1.00"], ["B Cell Receptor Signaling", "−0.58", "9.77E-01", "2.83", "8.71E-01", "0.71", "6.50E-01", "0.99"], ["Phospholipase C Signaling", "−1.41", "4.62E-01", "3.32", "5.32E-01", "1.00", "5.10E-01", "0.97"], ["Glioma Invasiveness Signaling", "−0.30", "2.69E-01", "2.11", "8.32E-01", "1.00", "1.38E-01", "0.94"], ["Oncostatin M Signaling", "−0.45", "4.23E-01", "2.24", "9.12E-01", "", "4.95E-01", "0.90"], ["Neuregulin Signaling", "−0.30", "3.13E-01", "2.00", "5.81E-01", "", "7.60E-01", "0.85"], ["JAK/Stat Signaling", "−2.00", "7.94E-01", "0.33", "8.32E-01", "", "", "0.84"], ["Calcium Signaling", "−2.11", "2.77E-01", "", "", "0.45", "1.38E-01", "0.83"], ["Role of RIG1-like Receptors in Antiviral Innate Immunity", "−0.45", "1.90E-01", "2.00", "5.75E-01", "", "", "0.78"], ["Type II Diabetes Mellitus Signaling", "−0.58", "3.36E-01", "2.12", "2.23E-01", "", "", "0.77"], ["PKCθ Signaling in T Lymphocytes", "−1.41", "1.66E-01", "2.50", "3.72E-01", "", "", "0.55"], ["NGF Signaling", "−2.13", "5.10E-01", "2.33", "2.85E-01", "1.34", "6.32E-01", "0.51"], ["Fcγ Receptor-mediated Phagocytosis in Macrophages and Monocytes", "−1.73", "3.97E-01", "2.12", "2.31E-01", "1.13", "4.28E-01", "0.51"], ["Role of NFAT in Regulation of the Immune Response", "−1.50", "3.75E-01", "2.50", "6.92E-01", "", "", "0.50"], ["Cardiac Hypertrophy Signaling", "−2.40", "1.69E-01", "1.70", "4.00E-01", "2.14", "4.34E-01", "0.48"], ["Death Receptor Signaling", "−2.71", "3.36E-01", "0.28", "3.89E-01", "1.00", "7.24E-01", "0.48"], ["Wnt/Ca+ pathway", "−1.13", "4.67E-01", "0.45", "2.92E-01", "2.00", "5.10E-01", "0.44"], ["Gαq Signaling", "−2.36", "4.40E-01", "1.51", "2.39E-01", "", "", "0.43"], ["CNTF Signaling", "−2.11", "1.33E-01", "1.34", "3.51E-01", "", "5.26E-01", "0.39"], ["IL-8 Signaling", "−1.90", "4.19E-01", "2.00", "5.10E-01", "0.58", "4.70E-01", "0.23"], ["Integrin Signaling", "−2.68", "4.88E-01", "1.51", "4.99E-01", "1.39", "4.34E-01", "0.07"], ["Melanocyte Development and Pigmentation Signaling", "−2.32", "1.56E-01", "1.34", "4.90E-01", "0.82", "4.34E-01", "0.05"]], "row_count": 62, "column_count": 8, "numeric_cells": 368, "header_rows": 2, "locator": "section[4]/table-wrap[2]#t0010"}}, {"id": "asset:table:pmid:28932774:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d775ce8ed5e2d05d6532c98101b8ea08d518c0dd20c250031bf502911fac9413", "bytes": 2503, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[3]#t0015", "version": null, "note": "Canonical pathways of common genes ⁎.", "structure": {"pmcid": "PMC5596332", "section_index": 4, "section_title": "1. Data", "row_count": 30, "column_count": 4}, "table": {"label": "Table 3", "caption": "Canonical pathways of common genes ⁎.", "rows": [["Ingenuity Canonical Pathways", "z-score", "P-value", "Molecules"], ["Glioma Invasiveness Signaling", "2.00", "1.74E-03", "PIK3CA, ITGAV, PLAUR, CD44"], ["IL-6 Signaling", "2.00", "2.00E-03", "IL18, PIK3CA, SRF, CD14, IL33"], ["Acute Phase Response Signaling", "2.00", "2.57E-02", "IL18, PIK3CA, SERPINE1, IL33"], ["NF-κB Signaling", "2.00", "3.16E-02", "IL18, PIK3CA, BMP2, IL33"], ["PDGF Signaling", "1.00", "3.63E-03", "PIK3CA, SRF, SPHK1, PDGFC"], ["LXR/RXR Activation", "−1.00", "7.41E-03", "IL18, CD14, ARG2, IL33"], ["Atherosclerosis Signaling", "", "1.05E-03", "IL18, TNFRSF12A, MMP1, IL33, PDGFC"], ["HIF1α Signaling", "", "1.07E-03", "PIK3CA, LDHA, SLC2A1, MMP1, PDGFC"], ["GDP-glucose Biosynthesis", "", "1.10E-03", "HK2, PGM5"], ["IL-10 Signaling", "", "1.23E-03", "IL18, CD14, ARG2, IL33"], ["Hepatic Fibrosis / Hepatic Stellate Cell Activation", "", "1.29E-03", "BAMBI, CD14, SERPINE1, AGTR1, MMP1, PDGFC"], ["Glucose and Glucose-1-phosphate Degradation", "", "1.45E-03", "HK2, PGM5"], ["Bladder Cancer Signaling", "", "2.34E-03", "CDKN1A, THBS1, MMP1, PDGFC"], ["Human Embryonic Stem Cell Pluripotency", "", "2.57E-03", "INHBA, PIK3CA, SPHK1, BMP2, PDGFC"], ["TGF-β Signaling", "", "3.24E-03", "INHBA, TGIF1, SERPINE1, BMP2"], ["Granulocyte Adhesion and Diapedesis", "", "3.80E-03", "IL18, SDC4, CLDN1, MMP1, IL33"], ["Agranulocyte Adhesion and Diapedesis", "", "4.79E-03", "IL18, SDC4, CLDN1, MMP1, IL33"], ["Role of Osteoblasts, Osteoclasts and Chondrocytes in Rheumatoid Arthritis", "", "4.79E-03", "IL18, PIK3CA, BMP2, SPP1, MMP1, IL33"], ["Role of Tissue Factor in Cancer", "", "1.07E-02", "PIK3CA, ITGAV, PLAUR, MMP1"], ["LPS/IL-1 Mediated Inhibition of RXR Function", "", "1.12E-02", "IL18, CD14, HS3ST5, NR5A2, IL33"], ["VDR/RXR Activation", "", "1.41E-02", "CD14, CDKN1A, SPP1"], ["Altered T Cell and B Cell Signaling in Rheumatoid Arthritis", "", "1.41E-02", "IL18, SPP1, IL33"], ["Palmitate Biosynthesis I (Animals)", "", "1.45E-02", "OXSM"], ["Fatty Acid Biosynthesis Initiation II", "", "1.45E-02", "OXSM"], ["Toll-like Receptor Signaling", "", "1.48E-02", "IL18, CD14, IL33"], ["Role of Hypercytokinemia/hyperchemokinemia in the Pathogenesis of Influenza", "", "1.78E-02", "IL18, IL33"], ["Graft-versus-Host Disease Signaling", "", "1.91E-02", "IL18, IL33"], ["Macropinocytosis Signaling", "", "1.95E-02", "PIK3CA, CD14, PDGFC"], ["Hepatic Cholestasis", "", "2.00E-02", "IL18, CD14, NR5A2, IL33"]], "row_count": 30, "column_count": 4, "numeric_cells": 58, "header_rows": 1, "locator": "section[4]/table-wrap[3]#t0015"}}, {"id": "asset:table:pmid:28932774:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3fa5bfce73ac93ebd46c9e7585fa3c3696371c3be26ddd3a2f87bac9067bfcee", "bytes": 3474, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[4]#t0020", "version": null, "note": "Comparison of bioinformatic tools ⁎.", "structure": {"pmcid": "PMC5596332", "section_index": 4, "section_title": "1. Data", "row_count": 56, "column_count": 5}, "table": {"label": "Table 4", "caption": "Comparison of bioinformatic tools ⁎.", "rows": [["", "DAVID (124/124)", "IPA (116/124)", "Panther (94/124)", "String (93/124)"], ["Canonical Pathways", "P-value", "P-value", "P-value", "False Discovery Rate"], ["TGF-beta signaling pathway", "5.20E-03", "3.24E-03", "2.21E-02", "2.94E-02"], ["p53 signaling pathway", "2.20E-02", "3.89E-02", "", "2.26E-02"], ["Proteoglycans in cancer", "1.50E-03", "", "", "8.24E-03"], ["HIF-1 signaling pathway", "9.50E-03", "1.07E-03", "", ""], ["ECM-receptor interaction", "6.10E-03", "", "", "8.24E-03"], ["Bladder cancer", "4.50E-02", "2.34E-03", "", ""], ["Atherosclerosis Signaling", "", "1.05E-03", "", ""], ["GDP-glucose Biosynthesis", "", "1.10E-03", "", ""], ["IL-10 Signaling", "", "1.23E-03", "", ""], ["Hepatic Fibrosis/Hepatic Stellate Cell Activation", "", "1.29E-03", "", ""], ["Glucose and Glucose-1-phosphate Degradation", "", "1.45E-03", "", ""], ["Glioma Invasiveness Signaling", "", "1.74E-03", "", ""], ["Human Embryonic Stem Cell Pluripotency", "", "2.57E-03", "", ""], ["PDGF Signaling", "", "3.63E-03", "", ""], ["Granulocyte Adhesion and Diapedesis", "", "3.80E-03", "", ""], ["Agranulocyte Adhesion and Diapedesis", "", "4.79E-03", "", ""], ["Role of Osteoblasts, Osteoclasts and Chondrocytes in Rheumatoid Arthritis", "", "4.79E-03", "", ""], ["Plasminogen activating cascade", "", "", "7.05E-03", ""], ["LXR/RXR Activation", "", "7.41E-03", "", ""], ["Role of Tissue Factor in Cancer", "", "1.07E-02", "", ""], ["LPS/IL-1 Mediated Inhibition of RXR Function", "", "1.12E-02", "", ""], ["VDR/RXR Activation", "", "1.41E-02", "", ""], ["Altered T Cell and B Cell Signaling in Rheumatoid Arthritis", "", "1.41E-02", "", ""], ["Palmitate Biosynthesis I (Animals)", "", "1.45E-02", "", ""], ["Fatty Acid Biosynthesis Initiation II", "", "1.45E-02", "", ""], ["Toll-like Receptor Signaling", "", "1.48E-02", "", ""], ["Role of Hypercytokinemia/hyperchemokinemia in the Pathogenesis of Influenza", "", "1.78E-02", "", ""], ["Graft-versus-Host Disease Signaling", "", "1.91E-02", "", ""], ["Macropinocytosis Signaling", "", "1.95E-02", "", ""], ["Hepatic Cholestasis", "", "2.00E-02", "", ""], ["Coagulation System", "", "2.40E-02", "", ""], ["LPS-stimulated MAPK Signaling", "", "2.45E-02", "", ""], ["PPAR Signaling", "", "2.45E-02", "", ""], ["Acute Phase Response Signaling", "", "2.57E-02", "", ""], ["HER-2 Signaling in Breast Cancer", "", "2.57E-02", "", ""], ["RNA degradation", "2.60E-02", "", "", ""], ["Role of Cytokines in Mediating Communication between Immune Cells", "", "2.69E-02", "", ""], ["Prostate Cancer Signaling", "", "2.75E-02", "", ""], ["Aldosterone Signaling in Epithelial Cells", "", "2.75E-02", "", ""], ["Trehalose Degradation II (Trehalase)", "", "2.88E-02", "", ""], ["Pyruvate Fermentation to Lactate", "", "2.88E-02", "", ""], ["Arginine Degradation I (Arginase Pathway)", "", "2.88E-02", "", ""], ["NF-κB Signaling", "", "3.16E-02", "", ""], ["tRNA Splicing", "", "3.16E-02", "", ""], ["Cholecystokinin/Gastrin-mediated Signaling", "", "3.31E-02", "", ""], ["Role of Oct4 in Mammalian Embryonic Stem Cell Pluripotency", "", "3.80E-02", "", ""], ["Glucocorticoid Receptor Signaling", "", "3.98E-02", "", ""], ["Nitric Oxide Signaling in the Cardiovascular System", "", "3.98E-02", "", ""], ["Glioma Signaling", "", "4.27E-02", "", ""], ["Urea Cycle", "", "4.27E-02", "", ""], ["Arginine Degradation VI (Arginase 2 Pathway)", "", "4.27E-02", "", ""], ["Pentose Phosphate Pathway (Non-oxidative Branch)", "", "4.27E-02", "", ""], ["p38 MAPK Signaling", "", "4.47E-02", "", ""], ["FXR/RXR Activation", "", "4.68E-02", "", ""]], "row_count": 56, "column_count": 5, "numeric_cells": 75, "header_rows": 2, "locator": "section[4]/table-wrap[4]#t0020"}}], "gaps": ["asset:data:geo:GSE23348 not downloaded", "asset:data:geo:GSE23348 licence not read", "asset:data:geo:GSE27961 not downloaded", "asset:data:geo:GSE27961 licence not read", "asset:data:geo:GSE94069 not downloaded", "asset:data:geo:GSE94069 licence not read"]}, "analysis": {"state": "partial", "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": "Linear Models for Microarray Analysis (LIMMA) [6] in the Bioconductor suite [7] under the statistical program R [8] was applied to compare the log ratio between each of the PGF2α time points and the saline control after adjusting for the box effect."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "bootstrap_mean_difference", "expected_value": 1.5, "unit": "fold change", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["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": "R1", "reachable": true, "accessions": ["GSE94069", "GSE23348", "GSE27961"], "resolved_accessions": ["GSE94069", "GSE23348", "GSE27961"], "statements": ["Raw data is in the public NCBI repository GEO (GSE94069), curated bioinformatics predictions are presented within the article as tables"], "basis": "The paper names GSE94069, GSE23348, GSE27961 in NCBI GEO repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:28932774", "data:geo:GSE23348", "asset:table:pmid:28932774:1", "asset:table:pmid:28932774:2", "asset:table:pmid:28932774:3", "asset:table:pmid:28932774:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE23348"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:10Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 45001, "completion_tokens": 4574, "cached_tokens": 1824}}, "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:28932774", "type": "paper", "label": "pmid:28932774"}, {"id": "source:pmid:28932774", "type": "manuscript", "label": "PMID 28932774 full text"}, {"id": "data:geo:GSE23348", "type": "dataset", "label": "GEO GSE23348"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28932774", "type": "paper", "label": "pmid:28932774"}, {"id": "source:pmid:28932774", "type": "manuscript", "label": "PMID 28932774 full text"}, {"id": "data:geo:GSE23348", "type": "dataset", "label": "GEO GSE23348"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28932774", "type": "extraction", "used": ["source:pmid:28932774"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE23348", "type": "accession_resolution", "used": ["data:geo:GSE23348"], "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:28932774", "parent_hash": "sha256:4e541cccee58926245a371eb4585632343fe0035e99f1371e838d2531d8f3f51", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE23348 licence not read", "asset:data:geo:GSE23348 not downloaded", "asset:data:geo:GSE27961 licence not read", "asset:data:geo:GSE27961 not downloaded", "asset:data:geo:GSE94069 licence not read", "asset:data:geo:GSE94069 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": 0.83, "evidence": ["Transcriptomic and bioinformatics analysis of the early tim", "interpreted in the companion article \"Early transcriptome responses of the bovine mid-cycle corpus lut"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"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": ["Bovine Gene v1 Array. The normalized linear microarray data was uploaded to the NCBI GEO repository", "in tables. A dataset comparison with similar microarray analyses was performed and bioinformatics an", "F2 alpha treatment of midcycle cows using an Affymetrix Bovine Gene v1 Array. The normalized linear"], "order_basis": "paper_text_order:245", "id": "assay:2"}, {"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": ["Linear Models for Microarray Analysis (LIMMA) [6] in the Bioconductor suite [7] under the statistical program R [8] was applied to compare the log ratio between each of the PGF2α time points and the saline control after adjusting for the box effect."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:35:42+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}}}