{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32784357", "kind": "science-record", "revision": 7, "content_hash": "sha256:c201d6f60d14ad76a086f846a9acfa407db19b94c2078b0d80bf2d3970d91c37", "created_at": "2026-11-01T15:41:07Z", "updated_at": "2026-11-01T22:02:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Phenylpropanoids Are Connected to Cell Wall Fortification and Stress Tolerance in Avocado Somatic Embryogenesis.", "doi": "10.3390/ijms21165679", "pmid": "32784357", "authors": ["Carol A Olivares-García", "Martín Mata-Rosas", "Carolina Peña-Montes", "Francisco Quiroz-Figueroa", "Aldo Segura-Cabrera", "Laura M Shannon", "Victor M Loyola-Vargas", "Juan L Monribot-Villanueva", "Jose M Elizalde-Contreras", "Enrique Ibarra-Laclette", "Mónica Ramirez-Vázquez", "José A Guerrero-Analco", "Eliel Ruiz-May"], "journal": "International journal of molecular sciences", "year": 2020, "abstract": "Somatic embryogenesis (SE) is a valuable model for understanding the mechanism of plant embryogenesis and a tool for the mass production of plants. However, establishing SE in avocado has been complicated due to the very low efficiency of embryo induction and plant regeneration. To understand the molecular foundation of the SE induction and development in avocado, we compared embryogenic (EC) and non-embryogenic (NEC) cultures of two avocado varieties using proteomic and metabolomic approaches. Although Criollo and Hass EC exhibited similarities in the proteome and metabolome profile, in general, we observed a more active phenylpropanoid pathway in EC than NEC. This pathway is associated with the tolerance of stress responses, probably through the reinforcement of the cell wall and flavonoid production. We could corroborate that particular polyphenolics compounds, including p-coumaric acid and t-ferulic acid, stimulated the production of somatic embryos in avocado. Exogen phenolic compounds were associated with the modification of the content of endogenous polyphenolic and the induction of the production of the putative auxin-a, adenosine, cellulose and 1,26-hexacosanediol-diferulate. We suggest that in EC of avocado, there is an enhanced phenylpropanoid metabolism for the production of the building blocks of lignin and flavonoid compounds having a role in cell wall reinforcement for tolerating stress response. Data are available at ProteomeXchange with the identifier PXD019705.", "claims": [{"id": "claim-data-access", "statement": "Data are available at ProteomeXchange with the identifier PXD019705.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32784357", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available at ProteomeXchange with the identifier PXD019705."}], "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:32784357"], "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:PXD019705"], "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:PXD019705"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32784357", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/ijms21165679", "sha256": "sha256:a870edbb62ae0782acf760cf0708a8c4a21426a7ad42171e6736d599fc548194", "bytes": 75472, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/ijms21165679", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7460882", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD019705", "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=PXD019705", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD019705", "version": null, "note": "Data are available at ProteomeXchange with the identifier PXD019705.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available at ProteomeXchange with the identifier PXD019705.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomics study in somatic embryogenesis in avocado", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32784357:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a039f3a484077aa4d138c1bdd05f25dcc87d9a9043547bdcd12d48cc2c517243", "bytes": 5060, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#ijms-21-05679-t001", "version": null, "note": "The endogenous concentration of phenolic compounds (mg g−1 fresh weight) in embryogenic cultures of Criollo and Hass avocado treated with different concentrations of p-coumaric (1 and 10 µM) and trans-ferulic acid (10 and 100 µM) during 6 and 12 h, and 14 and 28 days. The analysis was carried out with dynamic multiple reaction monitoring (dMRM) study. Replicate values, error standard and statistic values are presented in Table S2. p-hydroxybenzoic acid (PHBA), vanillin (VA), p-coumaric acid (p-CA), trans-ferulic acid (t-FA), SA (Sinapic acid) and trans-cinnamic acid (t-CA). We indicated in bold and italic the values described in the text.", "structure": {"pmcid": "PMC7460882", "section_index": 6, "section_title": "2.4. The Improvement of the Production of Embryos in Avocado EC Is Associated with the Alteration of the Endogenous Content of Polyphenolic Compounds", "row_count": 31, "column_count": 10}, "table": {"label": "Table 1", "caption": "The endogenous concentration of phenolic compounds (mg g−1 fresh weight) in embryogenic cultures of Criollo and Hass avocado treated with different concentrations of p-coumaric (1 and 10 µM) and trans-ferulic acid (10 and 100 µM) during 6 and 12 h, and 14 and 28 days. The analysis was carried out with dynamic multiple reaction monitoring (dMRM) study. Replicate values, error standard and statistic values are presented in Table S2. p-hydroxybenzoic acid (PHBA), vanillin (VA), p-coumaric acid (p-CA), trans-ferulic acid (t-FA), SA (Sinapic acid) and trans-cinnamic acid (t-CA). We indicated in bold and italic the values described in the text.", "rows": [["Cultivar Time", "Treatment", "PHBA", "VA", "p-CA", "Quercetin 3,4’-di-O-glucoside", "t-FA", "SA", "Naringin", "t-CA"], ["Criollo 0 h", "0 µM Control", "0.11 ± 0.01", "0.11 ± 0.01", "0.42 ± 0.01", "0.02 ± 0.01", "0.23 ± 0.01", "0", "0.07 ± 0.01", "0.02 ± 0.01"], ["1 µM p-CA", "0.11 ± 0.01", "0.11 ± 0.01", "0.42 ± 0.01", "0.02 ± 0.01", "0.23 ± 0.01", "0", "0.07 ± 0.01", "0.02 ± 0.01"], ["1 µM t-FA", "0.11 ± 0.01", "0.11 ± 0.01", "0.42 ± 0.01", "0.02 ± 0.01", "0.23 ± 0.01", "0", "0.07 ± 0.01", "0.02 ± 0.01"], ["Hass 0 h", "0 µM Control", "0.21 ± 0.01", "0.03 ± 0.03", "0.66 ± 0.02", "0.01 ± 0.01", "0.09 ± 0.01", "0", "0", "0.04 ± 0.01"], ["10 µM p-CA", "0.21 ± 0.01", "0.03 ± 0.03", "0.66 ± 0.02", "0.01 ± 0.01", "0.09 ± 0.01", "0", "0", "0.04 ± 0.01"], ["100 µM t-FA", "0.21 ± 0.01", "0.03 ± 0.03", "0.66 ± 0.02", "0.01 ± 0.01", "0.09 ± 0.01", "0", "0", "0.04 ± 0.01"], ["Criollo 6 h", "0 µM Control", "0.58 ± 0.01 ***", "0.22 ± 0.01 ***", "0.85 ± 0.01 ***", "1.66 ± 0.07 ***", "1.12 ± 0.01 ***", "0.7 ± 0.01 ***", "0.34 ± 0.01 ***", "0.06 ± 0.01 **"], ["1 µM p-CA", "0.64 ± 0.05 ***", "0.06 ± 0.01 **", "0.29 ± 0.01 **", "0 *", "0.12 ± 0.01 **", "0 **", "0 **", "0.4 ± 0.01 ***"], ["1 µM t-FA", "0.38 ± 0.01 **", "0.05 ± 0.01 **", "0.18 ± 0.01 **", "0.03 ± 0.04 **", "0.28 ± 0.01 **", "0 **", "0 **", "0.11 ± 0.01 ***"], ["Hass 6 h", "0 µM Control", "0.29 ± 0.01 *", "0.06 ± 0.01 *", "0.62 ± 0.01 *", "0.33 ± 0.05 *", "1 ± 0.01 **", "0.86 ± 0.02 ***", "0.06 ± 0.01 *", "0.03 ± 0 *"], ["10 µM p-CA", "0.25 ± 0.01 *", "0.05 ± 0.001 *", "0.7 ± 0.01 **", "0.02 ± 0.03 **", "0.13 ± 0.01 *", "0 *", "0 *", "0.29 ± 0.01 *"], ["100 µM t-FA", "0.32 ± 0.01 *", "0.24 ± 0.01 ***", "1.39 ± 0.01 ***", "0.62 ± 0.02 ***", "10.6 ± 0.22 ***", "0.64 ± 0.02 **", "0.18 ± 0.02 ***", "0.98 ± 0.02 ***"], ["Criollo 12 h", "0 µM Control", "0.21 ± 0.01 **", "0.15 ± 0.01 ***", "0.61 ± 0.01 ***", "0.62 ± 0.04 ***", "0.52 ± 0.01 ***", "0.72 ± 0.02 ***", "0.05 ± 0.01 ***", "0.02 ± 0.01 **"], ["1 µM p-CA", "0.25 ± 0.01 ***", "0.06 ± 0.01 **", "0.46 ± 0.01 **", "0 **", "0.26 ± 0.01 **", "0 **", "0 ***", "0.15 ± 0.01 ***"], ["1 µM t-FA", "0.18 ± 0 *", "0.04 ± 0.01 *", "0.18 ± 0.01 *", "0 **", "0.12 ± 0.01 *", "0 **", "0 ***", "0.03 ± 0.01 **"], ["Hass 12 h", "0 µM Control", "0.6 ± 0.01 ***", "0.11 ± 0.01 *", "0.94 ± 0.02 ***", "0.18 ± 0.02 ***", "0.86 ± 0.07 ***", "0.42 ± 0.01 ***", "0.21 ± 0.01 ***", "0.12 ± 0.01 **"], ["10 µM p-CA", "0.2 ± 0 *", "0.03 ± 0.001 *", "0.24 ± 0.01 *", "0.04 ± 0.01 **", "0.13 ± 0.01 *", "0 *", "0 *", "0.08 ± 0.01 *"], ["100 µM t-FA", "0.4 ± 0 *", "0.17 ± 0.01 ***", "0.48 ± 0.01 *", "0.05 ± 0.04 **", "0.39 ± 0.01 *", "0 *", "0.22 ± 0.01 ***", "0.08 ± 0.01 *"], ["Criollo 14 days", "0 µM Control", "1.12 ± 0.02 ***", "0.06 ± 0.001 ***", "1.28 ± 0.02 ***", "0.3 ± 0.01 ***", "0.23 ± 0.01 *", "0.03 ± 0.02 ***", "0 ***", "0.01 ± 0.02 ***"], ["1 µM p-CA", "0.09 ± 0.001 *", "0.05 ± 0.01 **", "0.39 ± 0.01 *", "0 **", "0.28 ± 0.02 **", "0 **", "0 ***", "0.01 ± 0.02 ***"], ["1 µM t-FA", "0.12 ± 0.01 **", "0.02 ± 0.01 *", "1.18 ± 0.08 **", "0 **", "0.56 ± 0.03 ***", "0.02 ± 0.01 *****", "0 ***", "0.02 ± 0.01 ***"], ["Hass 14 days", "0 µM Control", "0.09 ± 0.01 *", "0.03 ± 0.01 ***", "0.69 ± 0.03 ***", "0 *", "0.4 ± 0.01 **", "0.01 ± 0.01 **", "0 ***", "0.02 ± 0.01 ***"], ["10 µM p-CA", "0.11 ± 0.01 **", "0.03 ± 0.01 ***", "0.24 ± 0.02 *", "0.06 ± 0.01 **", "0.55 ± 0.03 **", "0.1 ± 0.02 ***", "0 ***", "0.01 ± 0.01 **"], ["100 µM t-FA", "0 *", "0 *", "0 *", "0 *", "7.06 ± 3.63 ***", "0 **", "0 ***", "0 *"], ["Criollo 28days", "0 µM Control", "0.62 ± 0.01 *", "0.05 ± 0.01 **", "0.96 ± 0 ***", "0 ***", "0.72 ± 0.01 ***", "0.23 ± 0.01 **", "0 ***", "0.5 ± 0 ***"], ["1 µM p-CA", "3.56 ± 0.06 ***", "0 *", "0.05 ± 0.04 *", "0 ***", "0 *", "0 *", "0 ***", "0 *"], ["1 µM t-FA", "1.35 ± 0.02 **", "0.08 ± 0 ***", "0.74 ± 0.01 **", "0.02 ± 0.04 ***", "0.12 ± 0.10 **", "1.55 ± 0.12 ***", "0 ***", "0.03 ± 0 **"], ["Hass 28 days", "0 µM Control", "0.4 ± 0 *", "0.05 ± 0 **", "1.14 ± 0.01 ***", "0 ***", "0.78 ± 0.01 **", "0.04 ± 0.01 ***", "0 ***", "0.01 ± 0 ***"], ["10 µM p-CA", "1.36 ± 0.03 ***", "0 *", "0.02 ± 0.02 *", "0 ***", "7.75 ± 4.43 ***", "0 *", "0 ***", "0 **"], ["100 µM t-FA", "1.12 ± 0.01 **", "0.03 ± 0 *", "0.16 ± 0.01 *", "0 ***", "0.08 ± 0 **", "0.01 ± 0.01 **", "0 ***", "0 **"]], "row_count": 31, "column_count": 10, "numeric_cells": 281, "header_rows": 1, "locator": "section[6]/table-wrap[1]#ijms-21-05679-t001"}}, {"id": "asset:table:pmid:32784357:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:def8a48456f802a37ea5c38adea0ddc43c528bea95f242dee873e695eeabb0cf", "bytes": 1321, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[31]/table-wrap[1]#array1", "version": null, "note": null, "structure": {"pmcid": "PMC7460882", "section_index": 31, "section_title": "Abbreviations", "row_count": 32, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["ALH2C4", "Aldehyde dehydrogenase family 2-member C4"], ["c-CA", "cis-cinnamic acid"], ["p-CA", "p-coumaric acid"], ["t-CA", "trans-cinnamic acid"], ["CAD9", "Cinnamyl alcohol dehydrogenase 9"], ["BSA", "Bovine serum albumin"], ["CCoAOMT", "Caffeoyl-CoA O-methyltransferase"], ["CCoAOMT1", "Caffeoyl-CoA O-methyltransferase 1"], ["C4H/ CYP73A5", "Cinnamic acid 4-hydroxylases"], ["4CL1", "4-coumarate: CoA ligase 1"], ["EC", "Embryogenic callus"], ["EMSN", "Extracellular matrix surface Network"], ["EP", "Embryogenic potency"], ["t-FA", "trans-ferulic acid"], ["GLM", "General linear model"], ["LDOX", "Leucoanthocyanidin dioxygenase"], ["MS", "Murashige and Skoog"], ["MSP", "Murashige and Skoog medium supplemented with 0.1 mg L−1 picloram"], ["NEC", "Non-embryogenic callus"], ["OMT1", "Flavone 3’-O-methyltransferase 1"], ["PAL1", "Phenylalanine ammonia-lyase 1"], ["PCA", "Principal component analysis"], ["PHBA", "p-hydroxybenzoic acid"], ["POX52", "Peroxidase 52"], ["PP", "Phenylpropanoid pathway"], ["ROS", "Reactive oxygen species"], ["SA", "Sinapic acid"], ["SE", "Somatic embryogenesis"], ["TCEP", "tris (2-carboxyethyl) phosphine"], ["TMT", "Tandem mass tags"], ["VBE", "Vanillyl benzyl ether"], ["VA", "Vanillin"]], "row_count": 32, "column_count": 2, "numeric_cells": 13, "header_rows": 0, "locator": "section[31]/table-wrap[1]#array1"}}], "gaps": ["asset:data:geo:PXD019705 not downloaded", "asset:data:geo:PXD019705 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": 0.8, "band": "high", "quote": "LIMMA"}}, {"id": "method-2", "family": null, "specific": null, "label": "Mann–Whitney U-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“The statistical analysis of the endogenous content of phenolic compounds was carried out with a Mann–Whitney U-test (n = 3, p < 0.05).”"}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["PXD019705"], "resolved_accessions": ["PXD019705"], "statements": ["Data are available at ProteomeXchange with the identifier PXD019705."], "basis": "The paper names PXD019705 in ProteomeXchange 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:32784357", "data:geo:PXD019705", "asset:table:pmid:32784357:1", "asset:table:pmid:32784357:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD019705"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:46Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 62498, "completion_tokens": 1087, "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:32784357", "type": "paper", "label": "pmid:32784357"}, {"id": "source:pmid:32784357", "type": "manuscript", "label": "PMID 32784357 full text"}, {"id": "data:geo:PXD019705", "type": "dataset", "label": "GEO PXD019705"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32784357", "type": "paper", "label": "pmid:32784357"}, {"id": "source:pmid:32784357", "type": "manuscript", "label": "PMID 32784357 full text"}, {"id": "data:geo:PXD019705", "type": "dataset", "label": "GEO PXD019705"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32784357", "type": "extraction", "used": ["source:pmid:32784357"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD019705", "type": "accession_resolution", "used": ["data:geo:PXD019705"], "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:32784357", "parent_hash": "sha256:0a8c1298c2ff176e207a7356b7dda73a6747032673e776211c0d1bdfb035d7f6", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD019705 licence not read", "asset:data:geo:PXD019705 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["for quantification of relative expression by qPCR, Data S1: Differential proteins identified i", "ic acid for 28 days, Figure S6: Quantitative real-time PCR validation of for genes involved in phenylpr"], "order_basis": "paper_text_order:3037", "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": ["nd NEC (-), based on LIMMA (linear model for microarray data), Table S2: Statistical analysis of val", "d David Functional annotation Bioinformatics Microarray analysis (https://david.ncifcrf.gov/) using"], "order_basis": "paper_text_order:3277", "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": 0.8, "evidence": ["LIMMA"], "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":"2026-11-04T03:16:25+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}}}