{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31497632", "kind": "science-record", "revision": 5, "content_hash": "sha256:62fed9ce9c04a148d8f7607bde56a4fe808cf7785c27ad1f174b9e9b99750ffc", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T18:51:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of de novo assembly and functional annotation of the transcriptome of blueberry (Vaccinium spp.).", "doi": "10.1016/j.dib.2019.104390", "pmid": "31497632", "authors": ["Xinpeng Qi", "Elizabeth L Ogden", "Mark K Ehlenfeldt", "Lisa J Rowland"], "journal": "Data in brief", "year": 2019, "abstract": "Blueberry is an economically important berry crop. Both production and consumption of blueberries have increased sharply worldwide in recent years at least partly due to their known health benefits. The development of improved genomic resources for blueberry, such as a well-assembled genome and transcriptome, could accelerate breeding through genomic-assisted approaches. To enrich available transcriptome data and identify genes potentially involved in fruit quality, RNA sequencing was performed on fruit tissue from two northern-adapted hybrid blueberry breeding populations. RNA-seq was carried out using the Illumina HiSeqTM 2500 platform. Because of the absence of a reference-grade genome for blueberry, a transcriptome was de novo assembled from this RNA-seq data and other publicly available transcriptome data from blueberry downloaded from the National Center for Biotechnology Information (NCBI) Short Read Archive (SRA) using Trinity. After removing redundancy, this resulted in a dataset of 91,861 blueberry unigenes. This unigene dataset was functionally annotated using the NCBI-Nr protein database. All raw reads from the breeding populations were deposited in the NCBI SRA with accession numbers SRR6281886, SRR6281887, SRR6281888, and SRR6281889. The de novo transcriptome assembly was deposited at NCBI Transcriptome Shotgun Assembly (TSA) database with accession number GGAB00000000. These data will provide real expression evidence for the blueberry genome gene prediction and gene functional annotation and a reference transcriptome for future gene expression studies involving blueberry fruit.", "claims": [{"id": "claim-data-access", "statement": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31497632", "locator": "sections[1] \"p\" paragraph 1", "quote": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly"}], "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:31497632"], "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_unresolved", "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:SRR6281886"], "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:SRR6281886"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31497632", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104390", "sha256": "sha256:f7e910ea83f044f61ea5f18cf789de655a9b801d4f1952096ace6e4ddf7baea0", "bytes": 10117, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104390", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6718820", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:SRR6281886", "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=SRR6281886", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281886", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRR6281887", "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=SRR6281887", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281887", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRR6281888", "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=SRR6281888", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281888", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRR6281889", "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=SRR6281889", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRR6281889", "version": null, "note": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31497632:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ca80133e3994803ed94e1682426df16757caa296881f76581cb9d72303ff514e", "bytes": 1876, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications Table", "structure": {"pmcid": "PMC6718820", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specifications Table", "rows": [["Subject area", "Biology"], ["More specific subject area", "Transcriptomics"], ["Type of data", "Transcriptome sequences"], ["How data was acquired", "Illumina HiSeqTM 2500 sequencing platform"], ["Data format", "Raw and analyzed"], ["Experimental factors", "Ripe fruit was collected from two field-grown blueberry breeding populations segregating for the waxy coating on fruit"], ["Experimental features", "Total RNA was extracted from bulked waxy and non-waxy fruit tissue from two blueberry breeding populations segregating for the waxy coating on fruit. RNA was used for cDNA library construction. Paired-end RNA-seq data was generated using the Illumina HiSeqTM 2500 sequencing platform. Trinity software was used to perform de novo assembly of clean reads from this data and other blueberry transcriptome data downloaded from NCBI SRA. The unigene dataset was functionally annotated using NCBI-Nr protein database."], ["Data source location", "USDA-ARS, Genetic Improvement of Fruits and Vegetables Laboratory, Beltsville, MD 20705, USA"], ["Data accessibility", "NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly"], ["Related research article", "Xinpeng Qi, Elizabeth L. Ogden, Mark K. Ehlenfeldt, and Lisa J. Rowland. Transcriptome analysis identifies genes related to the waxy coating on blueberry fruit in two northern-adapted rabbiteye breeding populations, “under review”."]], "row_count": 10, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31497632:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b92d1d6a1a0f2f59522d4d600575524d102040bf63e367241c75a253d607d87d", "bytes": 947, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6718820", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the Data1.The RNA-seq and assembled transcriptome datasets provide real expression evidence for use to the scientific research community in gene prediction and functional annotation of the emerging blueberry genome.2.The RNA-seq dataset is useful to scientists in identifying differentially expressed genes between blueberry fruit with and without the waxy coating and, thus, genes associated with wax accumulation in berry fruit.3.The expression profiles are available as raw sequence reads that can be further processed and analyzed by researchers using their own bioinformatic algorithms.4.The de novo assembled transcriptome is useful as a reference transcriptome to other scientists working to identify differentially expressed genes in blueberry and in related Vaccinium species."]], "row_count": 1, "column_count": 1, "numeric_cells": 1, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:31497632:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:878d54a943595bbd757fb9ef9dc394cf98f530bfef8b63df27cde387fcc33ff6", "bytes": 503, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "RNA-seq of two northern-adapted rabbiteye hybrid blueberry breeding populations.", "structure": {"pmcid": "PMC6718820", "section_index": 2, "section_title": "Data", "row_count": 5, "column_count": 3}, "table": {"label": "Table 1", "caption": "RNA-seq of two northern-adapted rabbiteye hybrid blueberry breeding populations.", "rows": [["Library", "Number of plants in bulk", "Number of clean reads"], ["‘Nocturne’ x T 300 non-waxy", "9", "69,318,222"], ["‘Nocturne’ x T 300 waxy", "10", "97,629,788"], ["‘Nocturne’ x US 1212 non-waxy", "10", "68,222,558"], ["‘Nocturne’ x US 1212 waxy", "13", "81,404,420"]], "row_count": 5, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[2]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:31497632:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9930d6c3982ea50f1b483a87743013b46540f39334a49bd84b5f806bacfe47bc", "bytes": 722, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[2]#tbl2", "version": null, "note": "Statistics of the blueberry transcriptome raw assembly, quality assessment, and redundancy elimination.", "structure": {"pmcid": "PMC6718820", "section_index": 2, "section_title": "Data", "row_count": 11, "column_count": 2}, "table": {"label": "Table 2", "caption": "Statistics of the blueberry transcriptome raw assembly, quality assessment, and redundancy elimination.", "rows": [["Total “genes” from Trinity assembly", "251,974"], ["Assembly N50 length", "806"], ["Total assembled bases", "208,124,831"], ["‘Nocturne’ x T 300 non-waxy (%)", "87.16a"], ["‘Nocturne’ x T 300 waxy (%)", "92.00a"], ["‘Nocturne’ x US 1212 non-waxy (%)", "93.36a"], ["‘Nocturne’ x US 1212 waxy (%)", "91.63a"], ["Total full-length SwissProt protein hits", "9909"], ["Total unigene number", "91,861"], ["Unigene N50 length", "1144"], ["Total unigene bases", "66,642,205"]], "row_count": 11, "column_count": 2, "numeric_cells": 17, "header_rows": 0, "locator": "section[2]/table-wrap[2]#tbl2"}}], "gaps": ["asset:data:geo:SRR6281886 not downloaded", "asset:data:geo:SRR6281886 licence not read", "asset:data:geo:SRR6281887 not downloaded", "asset:data:geo:SRR6281887 licence not read", "asset:data:geo:SRR6281888 not downloaded", "asset:data:geo:SRR6281888 licence not read", "asset:data:geo:SRR6281889 not downloaded", "asset:data:geo:SRR6281889 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "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": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": ["SRR6281886", "SRR6281887", "SRR6281888", "SRR6281889"], "resolved_accessions": [], "statements": ["NCBI SRA accession numbers of SRR6281886(https://www.ncbi.nlm.nih.gov/sra/SRR6281886), SRR6281887 (https://www.ncbi.nlm.nih.gov/sra/SRR6281887), SRR6281888 (https://www.ncbi.nlm.nih.gov/sra/SRR6281888), and SRR6281889 (https://www.ncbi.nlm.nih.gov/sra/SRR6281889)for raw reads;NCBI TSA accession number of GGAB00000000 (https://www.ncbi.nlm.nih.gov/nuccore/GGAB00000000.1/)for assembly"], "basis": "The paper names SRR6281886, SRR6281887, SRR6281888, SRR6281889, but the accession does not resolve in the repository (not_in_ncbi_sra, not_in_ncbi_sra, not_in_ncbi_sra, not_in_ncbi_sra), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31497632", "data:geo:SRR6281886", "asset:table:pmid:31497632:1", "asset:table:pmid:31497632:2", "asset:table:pmid:31497632:3", "asset:table:pmid:31497632:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:SRR6281886"]}, "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": "2026-10-31T18:16:10Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 9076, "completion_tokens": 2442, "cached_tokens": 528}}, "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:31497632", "type": "paper", "label": "pmid:31497632"}, {"id": "source:pmid:31497632", "type": "manuscript", "label": "PMID 31497632 full text"}, {"id": "data:geo:SRR6281886", "type": "dataset", "label": "GEO SRR6281886"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31497632", "type": "paper", "label": "pmid:31497632"}, {"id": "source:pmid:31497632", "type": "manuscript", "label": "PMID 31497632 full text"}, {"id": "data:geo:SRR6281886", "type": "dataset", "label": "GEO SRR6281886"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31497632", "type": "extraction", "used": ["source:pmid:31497632"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-SRR6281886", "type": "accession_resolution", "used": ["data:geo:SRR6281886"], "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:31497632", "parent_hash": "sha256:573733412da0739fe14df29240c0bc3ca39fcbb0d1364d5114bacf9c17156a60", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:SRR6281886 licence not read", "asset:data:geo:SRR6281886 not downloaded", "asset:data:geo:SRR6281887 licence not read", "asset:data:geo:SRR6281887 not downloaded", "asset:data:geo:SRR6281888 licence not read", "asset:data:geo:SRR6281888 not downloaded", "asset:data:geo:SRR6281889 licence not read", "asset:data:geo:SRR6281889 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["vo assembly and functional annotation of the transcriptome of blueberry (Vaccinium spp.).", "ueberry, such as a well-assembled genome and transcriptome, could accelerate breeding through genomic-a", "mic-assisted approaches. To enrich available transcriptome data and identify genes potentially involved", "of a reference-grade genome for blueberry, a transcriptome was de novo assembled from this RNA-seq data"], "order_basis": "paper_text_order:16", "id": "assay:1"}]},"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":"2026-11-04T02:35:09+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}}}