{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33409343", "kind": "science-record", "revision": 8, "content_hash": "sha256:21c3b8aa8cf6d09c6943faacec4d79f7f8b5e23e28cef276d100eb5dc4465669", "created_at": "2026-11-01T15:41:21Z", "updated_at": "2026-11-01T22:45:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset for transcriptome and physiological response of mature tomato seed tissues to light and heat during fruit ripening.", "doi": "10.1016/j.dib.2020.106671", "pmid": "33409343", "authors": ["Elise Bizouerne", "Benoit Ly Vu", "Joseph Ly Vu", "Jerome Verdier", "Julia Buitink", "Olivier Leprince"], "journal": "Data in brief", "year": 2021, "abstract": "Seed vigor is an estimate of how successfully a seed lot will establish seedlings under a wide range of environmental conditions, with both the embryo and the surrounding endosperm playing distinct roles in the germination behaviour. Germination and seedling establishment are essential for crop production to be both sustainable and profitable. Seed vigor traits are sequentially acquired during development via genetic programs that are poorly understood, but known to be under the strong influence of environmental conditions. To investigate how light and temperature have an impact on the molecular mechanisms governing seed vigor at harvest, RNA sequencing was performed on Solanum lycopersicum cv. Moneymaker seed tissues (i.e. embryo and endosperm) that were dissected from fruits that were submitted to standard or high temperature and/or standard or dim light. The dataset encompassed a total of 26.5 Gb raw data from mature embryo and endosperm tissues transcriptomes. The raw and mapped reads data on build SL4.0 and annotation ITAG4.0 are available under accession GSE158641 at NCBI Gene Expression Omnibus (GEO) database. Data on seed vigor characteristics are presented together with the differentially expressed gene transcripts. GO and Mapman annotations were generated on ITAG4.0 to analyse this dataset and are provided for datamining future datasets.", "claims": [{"id": "claim-method", "statement": "Number of DEGs were identified using the DEseq2 algorithm with a Benjamini-Hochberg p-value adjustment threshold set at 0.05 to control false positive rate.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33409343", "locator": "sections[3] \"Data Description\" paragraph 7", "quote": "Number of DEGs were identified using the DEseq2 algorithm with a Benjamini-Hochberg p-value adjustment threshold set at 0.05 to control false positive rate."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw and mapped reads data on build SL4.0 and annotation ITAG4.0 are available under accession GSE158641 at NCBI Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33409343", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The raw and mapped reads data on build SL4.0 and annotation ITAG4.0 are available under accession GSE158641 at NCBI Gene Expression Omnibus (GEO) database."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33409343"], "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:GSE158641"], "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:GSE158641"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33409343", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2020.106671", "sha256": "sha256:6f1e82af6e93eae7a903d333a8af4e5799770a3235323b180f2173b49246440b", "bytes": 16068, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2020.106671", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7773857", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE158641", "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=GSE158641", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE158641", "version": null, "note": "The raw and mapped reads data on build SL4.0 and annotation ITAG4.0 are available under accession GSE158641 at NCBI Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw and mapped reads data on build SL4.0 and annotation ITAG4.0 are available under accession GSE158641 at NCBI Gene Expression Omnibus (GEO) database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4804881", "GSM4804882", "GSM4804883", "GSM4804884", "GSM4804885", "GSM4804886", "GSM4804887", "GSM4804888", "GSM4804889", "GSM4804890", "GSM4804891", "GSM4804892", "GSM4804893", "GSM4804894", "GSM4804895", "GSM4804896", "GSM4804897", "GSM4804898", "GSM4804899", "GSM4804900", "GSM4804901", "GSM4804902", "GSM4804903", "GSM4804904", "GSM4804905", "GSM4804906"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "26877", "taxon": "Solanum lycopersicum", "title": "RNA sequencing of tomato seed tissues matured in different environments", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33409343:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:10ce02196d923c794d3db90cfe27db749f73aa04c78b770f2a04f7e2cdda021e", "bytes": 1703, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#utbl0001", "version": null, "note": null, "structure": {"pmcid": "PMC7773857", "section_index": 1, "section_title": "Specifications Table", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject", "Biological sciences"], ["Specific subject area", "Omics: Transcriptomics Plant Science: Plant Physiology"], ["Type of data", "Table Figure"], ["How data were acquired", "High-throughput RNA sequencing using BGISEQ-500"], ["Data format", "Raw reads (FASTQ) filtered and analysed with statistical tests. Percentages and speed of germination."], ["Parameters for data collection", "Total RNA was extracted from isolated embryo and endosperm tissues of mature Solanum lycopersicum (cv Money Maker) seeds that were harvested at 70 days after flowering (DAF) from fruits that were ripened ex planta from the breaker stage (63 DAF) onwards under standard temperature (23 °C day/ 20 °C night) or high temperature (32 °C/26 °C) and under standard light regime (16 h photoperiod, 300 µE m2 s−1) or dim light (16 h photoperiod, 25 µE m2 s−1). Seed vigor was assessed during imbibition at 20 °C in the dark in water, 71 mM NaCl or a polyethylene glycol solution (PEG 8000) both corresponding to −0.3 MPa."], ["Description of data collection", "RNA sequencing of total RNA followed by mapping and bioinformatic analysis for differential gene expression and gene set enrichment analyses. Germination data."], ["Data source location", "Institution: Institut de Recherche en Horticulture et Semences, INRA City: Beaucouzé Country: France"], ["Data accessibility", "Repository name: NCBI GEO Data identification number: GSE158641 Direct URL to data: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE158641https://data.mendeley.com/datasets/6h44fvz8×9/1"]], "row_count": 9, "column_count": 2, "numeric_cells": 3, "header_rows": 0, "locator": "section[1]/table-wrap[1]#utbl0001"}}, {"id": "asset:table:pmid:33409343:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1cf9a70fcd781ec6cf08521a39872ce2a462273203072c759be42f361411e0d6", "bytes": 1000, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl0001", "version": null, "note": "Vigor characteristics of seeds extracted from fruits that ripened ex planta at different temperature and light conditions. After drying, seeds were imbibed in the dark at 20 °C in water, 71 mM Nacl or a PEG 8000 solution corresponding to −0.3 MPa. Data are the mean of three replicates of 50 seeds. Values in brackets represent standard deviation. DL = dim light; HL, high light; HT, high temperature; ST, standard temperature, t50, time of imbibition necessary to reach 50% germination).", "structure": {"pmcid": "PMC7773857", "section_index": 3, "section_title": "Data Description", "row_count": 5, "column_count": 5}, "table": {"label": "Table 1", "caption": "Vigor characteristics of seeds extracted from fruits that ripened ex planta at different temperature and light conditions. After drying, seeds were imbibed in the dark at 20 °C in water, 71 mM Nacl or a PEG 8000 solution corresponding to −0.3 MPa. Data are the mean of three replicates of 50 seeds. Values in brackets represent standard deviation. DL = dim light; HL, high light; HT, high temperature; ST, standard temperature, t50, time of imbibition necessary to reach 50% germination).", "rows": [["Vigor trait", "ST_HL", "ST_DL", "HT_HL", "HT_DL"], ["Germination H2O", "98.0 (2.0)", "86.0 (2.0)", "78.7 (3.1)", "86.0 (4.0)"], ["Speed of germination (t50, d)", "2.8 (0.1)", "3.7 (0.1)", "3.0 (0.1)", "2.7 (0.2)"], ["Germination −0.3 MPa", "31.3 (8.1)", "6.7 (4.2)", "1.3 (1.2)", "3.3 (2.3)"], ["Germination 71 mM NaCl", "23.3 (7.0)", "16.0 (2.0)", "14.0 (5.3)", "12.0 (5.3)"]], "row_count": 5, "column_count": 5, "numeric_cells": 19, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl0001"}}, {"id": "asset:table:pmid:33409343:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8f84e18a1ae3a4185f847215511fdaa5a9feafff92b03a5c30ca122bcc0a77de", "bytes": 1781, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#tbl0002", "version": null, "note": "Summary of mapping information performed with SALMON and FastQC. End, endosperm; Em, embryo, DL = dim light; HL, high light; HT, high temperature; ST, standard temperature.", "structure": {"pmcid": "PMC7773857", "section_index": 3, "section_title": "Data Description", "row_count": 27, "column_count": 6}, "table": {"label": "Table 2", "caption": "Summary of mapping information performed with SALMON and FastQC. End, endosperm; Em, embryo, DL = dim light; HL, high light; HT, high temperature; ST, standard temperature.", "rows": [["Sample Name", "% Aligned", "M Aligned", "% Dups", "% GC", "M Seqs"], ["HT_DL_Em_1", "82.00%", "20.7", "64.60%", "42%", "25.2"], ["HT_DL_Em_2", "83.60%", "20.9", "51.10%", "43%", "25.0"], ["HT_DL_Em_3", "84.80%", "21.5", "61.90%", "43%", "25.3"], ["HT_DL_Em_4", "83.60%", "21.1", "65.40%", "43%", "25.2"], ["HT_DL_End_1", "82.70%", "20.7", "64.60%", "42%", "25.0"], ["HT_DL_End_2", "82.30%", "20.8", "62.80%", "42%", "25.3"], ["HT_DL_End_3", "83.10%", "21.0", "62.60%", "42%", "25.3"], ["HT_HL_Em_1", "81.60%", "20.5", "62.30%", "42%", "25.2"], ["HT_HL_Em_2", "81.60%", "20.7", "60.50%", "42%", "25.4"], ["HT_HL_Em_3", "80.80%", "20.4", "62.80%", "42%", "25.2"], ["HT_HL_End_1", "82.90%", "21.1", "63.60%", "42%", "25.4"], ["HT_HL_End_2", "83.40%", "21.0", "64.00%", "42%", "25.2"], ["HT_HL_End_3", "82.50%", "20.9", "64.40%", "43%", "25.4"], ["ST_DL_Em_1", "83.40%", "20.8", "57.10%", "43%", "24.9"], ["ST_DL_Em_2", "82.70%", "20.8", "59.70%", "42%", "25.2"], ["ST_DL_Em_3", "83.30%", "20.8", "66.90%", "42%", "24.9"], ["ST_DL_End_1", "82.10%", "20.7", "64.40%", "42%", "25.3"], ["ST_DL_End_2", "82.70%", "21.0", "64.50%", "42%", "25.4"], ["ST_DL_End_3", "82.60%", "21.0", "64.50%", "42%", "25.4"], ["ST_HL_Em_1", "81.90%", "20.6", "53.20%", "42%", "25.1"], ["ST_HL_Em_2", "83.30%", "21.1", "60.70%", "42%", "25.4"], ["ST_HL_Em_3", "83.20%", "20.8", "51.70%", "43%", "25.0"], ["ST_HL_Em_4", "82.10%", "20.8", "62.80%", "42%", "25.3"], ["ST_HL_End_1", "82.30%", "20.8", "62.60%", "42%", "25.3"], ["ST_HL_End_2", "83.40%", "21.1", "63.20%", "42%", "25.3"], ["ST_HL_End_3", "82.60%", "20.9", "61.70%", "42%", "25.3"]], "row_count": 27, "column_count": 6, "numeric_cells": 156, "header_rows": 1, "locator": "section[3]/table-wrap[2]#tbl0002"}}, {"id": "asset:table:pmid:33409343:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:24a0657a904cec24478b37a7696994bfb556efb646e80e3cf8ccf4a9bc14e8ec", "bytes": 719, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[3]#tbl0003", "version": null, "note": "Number of differentially expressed genes (DEGs) in embryo and endosperm tissues in different light/temperature conditions compared to standard conditions. Number of DEGs were identified using the DEseq2 algorithm with a Benjamini-Hochberg p-value adjustment threshold set at 0.05 to control false positive rate. DL = dim light; HL, high light; HT, high temperature; ST, standard temperature.", "structure": {"pmcid": "PMC7773857", "section_index": 3, "section_title": "Data Description", "row_count": 5, "column_count": 5}, "table": {"label": "Table 3", "caption": "Number of differentially expressed genes (DEGs) in embryo and endosperm tissues in different light/temperature conditions compared to standard conditions. Number of DEGs were identified using the DEseq2 algorithm with a Benjamini-Hochberg p-value adjustment threshold set at 0.05 to control false positive rate. DL = dim light; HL, high light; HT, high temperature; ST, standard temperature.", "rows": [["", "", "HT_HL / ST_HL", "ST_DL / ST_HL", "HT_DL / ST_HL"], ["Embryo", "up", "358", "82", "1"], ["down", "1561", "692", "6"], ["Endosperm", "up", "610", "60", "153"], ["down", "657", "253", "113"]], "row_count": 5, "column_count": 5, "numeric_cells": 12, "header_rows": 1, "locator": "section[3]/table-wrap[3]#tbl0003"}}], "gaps": ["asset:data:geo:GSE158641 not downloaded", "asset:data:geo:GSE158641 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": "Number of DEGs were identified using the DEseq2 algorithm with a Benjamini-Hochberg p-value adjustment threshold set at 0.05 to control false positive rate."}}], "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": "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: deseq2."}, "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": ["GSE158641"], "resolved_accessions": ["GSE158641"], "statements": ["The raw and mapped reads data on build SL4.0 and annotation ITAG4.0 are available under accession GSE158641 at NCBI Gene Expression Omnibus (GEO) database."], "basis": "The paper names GSE158641 in NCBI Gene Expression Omnibus (GEO) 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:33409343", "data:geo:GSE158641", "asset:table:pmid:33409343:1", "asset:table:pmid:33409343:2", "asset:table:pmid:33409343:3", "asset:table:pmid:33409343:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE158641"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 13711, "completion_tokens": 2005, "cached_tokens": 784}}, "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:33409343", "type": "paper", "label": "pmid:33409343"}, {"id": "source:pmid:33409343", "type": "manuscript", "label": "PMID 33409343 full text"}, {"id": "data:geo:GSE158641", "type": "dataset", "label": "GEO GSE158641"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33409343", "type": "paper", "label": "pmid:33409343"}, {"id": "source:pmid:33409343", "type": "manuscript", "label": "PMID 33409343 full text"}, {"id": "data:geo:GSE158641", "type": "dataset", "label": "GEO GSE158641"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33409343", "type": "extraction", "used": ["source:pmid:33409343"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE158641", "type": "accession_resolution", "used": ["data:geo:GSE158641"], "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:33409343", "parent_hash": "sha256:8afefc69b04e948ee334c6ccfaeb203b301229a3a44236f2237150197b765870", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE158641 licence not read", "asset:data:geo:GSE158641 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Dataset for transcriptome and physiological response of mature tomato", "ata from mature embryo and endosperm tissues transcriptomes. The raw and mapped reads data on build SL4.", "mechanisms governing seed vigor at harvest, RNA sequencing was performed on Solanum lycopersicum cv. Mo"], "order_basis": "paper_text_order:0", "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": ["Number of DEGs were identified using the DEseq2 algorithm with a Benjamini-Hochberg p-value adjustment threshold set at 0.05 to control false positive rate."], "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":"2026-11-04T03:11:01+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}