{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33946829", "kind": "science-record", "revision": 8, "content_hash": "sha256:e84bb6151a413c9bcc3c40b0347ef58cd2103397ebe1b2e765ae38a1dea79ed5", "created_at": "2026-11-01T15:41:34Z", "updated_at": "2026-11-01T22:46:38Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Quantitative Label-Free Comparison of the Metabolic Protein Fraction in Old and Modern Italian Wheat Genotypes by a Shotgun Approach.", "doi": "10.3390/molecules26092596", "pmid": "33946829", "authors": ["Antonella Di Francesco", "Vincenzo Cunsolo", "Rosaria Saletti", "Birte Svensson", "Vera Muccilli", "Pasquale De Vita", "Salvatore Foti"], "journal": "Molecules (Basel, Switzerland)", "year": 2021, "abstract": "Wheat represents one of the most important cereals for mankind. However, since wheat proteins are also the causative agent of several adverse reactions, during the last decades, consumers have shown an increasing interest in the old wheat genotypes, which are generally perceived as more \"natural\" and healthier than the modern ones. Comparison of nutritional value for modern and old wheat genotypes is still controversial, and to evaluate the real impact of these foods on human health comparative experiments involving old and modern genotypes are desirable. The nutritional quality of grain is correlated with its proteomic composition that depends on the interplay between the genetic characteristics of the plant and external factors related to the environment. We report here the label-free shotgun quantitative comparison of the metabolic protein fractions of two old Sicilian landraces (Russello and Timilia) and the modern variety Simeto, from the 2010-2011 and 2011-2012 growing seasons. The overall results show that Timilia presents the major differences with respect to the other two genotypes investigated. These differences may be related to different defense mechanisms and some other peculiar properties of these genotypes. On the other hand, our results confirm previous results leading to the conclusion that with respect to a nutritional value evaluation, there is a substantial equivalence between old and modern wheat genotypes. Data are available via ProteomeXchange with identifier <PXD024204>.", "claims": [{"id": "claim-method", "statement": "A protein was quantified when: (i) at least two of its unique peptides satisfied the parameters above reported; (ii) was identified in a minimum of five out of nine nanoLC-MS/MS runs per flour sample; and (iii) had a p-value < 0.05 and a significance ≥ 20 (significance method ANOVA; the significance score was calculated as the −10log10 of the significance testing p-value).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33946829", "locator": "sections[10] \"4.5. Label-Free Quantification\" paragraph 2", "quote": "A protein was quantified when: (i) at least two of its unique peptides satisfied the parameters above reported; (ii) was identified in a minimum of five out of nine nanoLC-MS/MS runs per flour sample; and (iii) had a p-value < 0.05 and a significance ≥ 20 (significance method ANOVA; the significance score was calculated as the −10log10 of the significance testing p-value)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Not applicable.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33946829", "locator": "sections[17] \"Institutional Review Board Statement\" paragraph 2", "quote": "Not applicable."}], "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:33946829"], "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:PXD024204"], "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:PXD024204"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33946829", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/molecules26092596", "sha256": "sha256:4442d0ded8262e2472f4d397b4a1bbba203425089bb6219b7515b648170e58fe", "bytes": 55717, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/molecules26092596", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8124627", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD024204", "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=PXD024204", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD024204", "version": null, "note": "Not applicable.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Not applicable.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantitative Label-free Comparison of the Metabolic Protein Fraction in Old and Modern Wheat Italian Genotypes by a Shotgun Approach", "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:33946829:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c258f05683d37bd88c5a61c1c02a92a8b8f7460871e2271aea72ac84a105a7b1", "bytes": 1698, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#molecules-26-02596-t001", "version": null, "note": "Protein profile heat map (cell color represents the fold change observed across the genotype investigated). Each cell also reports the corresponding fold change observed in the two growing seasons. Proteins marked with an asterisk were also detected as intra-genotype DAPs. For details see Table 2.", "structure": {"pmcid": "PMC8124627", "section_index": 3, "section_title": "Differentially Abundant Proteins Genotype-Related", "row_count": 25, "column_count": 6}, "table": {"label": "Table 1", "caption": "Protein profile heat map (cell color represents the fold change observed across the genotype investigated). Each cell also reports the corresponding fold change observed in the two growing seasons. Proteins marked with an asterisk were also detected as intra-genotype DAPs. For details see Table 2.", "rows": [["Proteins", "Gene Code", "Growing Season 2010/2011", "Growing Season 2011/2012", "Fold Change"], ["Fold Change", "Fold Change"], ["Russello vs. Simeto", "", "", "", "", "64"], ["Avenin-like b1", "AVLB1", "0.12", "0.12"], ["Oil body-associated protein 1A", "OBP1A", "4.75", "9.73"], ["Serpin-Z1C", "SPZ1C *", "0.4", "0.21"], ["Timilia vs. Simeto", "", "", ""], ["26 kDa endochitinase 2", "CHI2", "0.44", "0.41"], ["a-amylase inhibitor 0.28", "IAA2", "64", "64"], ["Antifungal protein R (Fragment)", "THHR", "0.27", "0.32"], ["Avenin-like b1", "AVLB1 *", "3.33", "2.5"], ["L-ascorbate peroxidase 2 cytosolic", "APX2 *", "5.15", "2.32"], ["Oil body-associated protein 1A", "OBP1A", "4.6", "9.09"], ["Subtilisin-chymotrypsin inhibitor WSCI", "ICIW", "6.61", "4.67", "1"], ["Sucrose synthase 1", "SUS1", "6.31", "3.95"], ["Sucrose synthase 3", "SUS3", "3.13", "2.1"], ["Timilia vs. Russello", "", "", ""], ["26 kD aendochitinase 2", "CHI2", "0.27", "0.33"], ["a-amylase inhibitor WDAI-3 (Fragment)", "IAA3 *", "0.39", "0.39"], ["Avenin-like b1", "AVLB1 *", "38.49", "25.39"], ["Linoleate 9S-lipoxygenase 1", "LOX1", "2.42", "2.28"], ["Serpin-Z2A", "SPZ2A", "0.02", "0.02"], ["Subtilisin-chymotrypsin inhibitor WSCI", "ICIW", "6.74", "5.81"], ["Sucrose synthase 1", "SUS1", "3.36", "2.05"], ["Sucrose synthase 3", "SUS3", "3.11", "2.3"]], "row_count": 25, "column_count": 6, "numeric_cells": 56, "header_rows": 2, "locator": "section[3]/table-wrap[1]#molecules-26-02596-t001"}}, {"id": "asset:table:pmid:33946829:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2965afa3c49282c0bb6d99fc55218bcb9b8e31516f5f0975a889aaaf9db3d7f2", "bytes": 4479, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#molecules-26-02596-t002", "version": null, "note": "List of the proteins detected as DAPs in both the growing seasons investigated: Russello vs. Simeto; Timilia vs. Simeto; Timilia vs. Russello. For each protein is reported: Accession Number as used in the Uniprot database; gene code; organism; protein description; the fold change (if ≤0.5 or ≥2); p-value observed in the growing seasons 2010–2011 and 2011–2012; significance; the number of the characterized peptides; the number of unique peptides, and the biological process in which it is involved. Proteins that were also detected as intra-genotype DAPs are reported in italics.", "structure": {"pmcid": "PMC8124627", "section_index": 3, "section_title": "Differentially Abundant Proteins Genotype-Related", "row_count": 25, "column_count": 16}, "table": {"label": "Table 2", "caption": "List of the proteins detected as DAPs in both the growing seasons investigated: Russello vs. Simeto; Timilia vs. Simeto; Timilia vs. Russello. For each protein is reported: Accession Number as used in the Uniprot database; gene code; organism; protein description; the fold change (if ≤0.5 or ≥2); p-value observed in the growing seasons 2010–2011 and 2011–2012; significance; the number of the characterized peptides; the number of unique peptides, and the biological process in which it is involved. Proteins that were also detected as intra-genotype DAPs are reported in italics.", "rows": [["UniProt Acc. No.", "Gene Code", "Organism", "Protein Description", "Growing Season 2010/2011", "Growing Season 2011/2012", "Intra-Genotype DAPs *", "Biological Process"], ["Fold Change", "p-Value", "Significance", "Peptides", "Unique Peptides", "Fold Change", "p-Value", "Significance", "Peptides", "Unique Peptides"], ["Russello vs. Simeto", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""], ["Q2A783", "AVLB1", "Wheat", "Avenin-like b1", "0.12", "4.84 × 10−11", "69.40", "7", "6", "0.12", "3.03 × 10−8", "109.29", "7", "6", "", "Storage"], ["B4FFZ9", "OBP1A", "Maize", "Oil body-associated protein 1A", "4.75", "7.00 × 10−5", "64.98", "5", "5", "9.73", "3.64 × 10−14", "88.47", "4", "4", "", "Others"], ["Q9ST58", "SPZ1C", "Wheat", "Serpin-Z1C", "0.40", "1.55 × 10−7", "48.73", "12", "5", "0.21", "1.09 × 10−8", "105.97", "11", "3", "Y (Russello)", "Defense/Inhibitor"], ["Timilia vs. Simeto", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""], ["P23951", "CHI2", "Barley", "26 kDa endochitinase 2", "0.44", "9.95 × 10−9", "79.42", "12", "7", "0.41", "3.01 × 10−5", "61.90", "12", "6", "", "Defense/Stress Related Proteins"], ["P01083", "IAA2", "Wheat", "α-amylase inhibitor 0.28", "64.00", "3.55 × 10−15", "68.66", "4", "3", "64.00", "1.13 × 10−10", "101.12", "6", "5", "", "Defense/Inhibitor"], ["P33044", "THHR", "Barley", "Antifungal protein R (Fragment)", "0.27", "4.72 × 10−18", "101.88", "2", "2", "0.32", "8.77 × 10−7", "69.64", "2", "2", "", "Defense/Stress Related Proteins"], ["Q2A783", "AVLB1", "Wheat", "Avenin-like b1", "3.33", "3.82 × 10−9", "95.07", "21", "21", "2.50", "7.97 × 10−6", "55.45", "21", "21", "Y (Timilia)", "Storage"], ["Q9FE01", "APX2", "Rice", "L-ascorbate peroxidase 2 cytosolic", "5.15", "4.43 × 10−8", "87.16", "2", "2", "2.32", "2.13 × 10−5", "51.24", "2", "2", "Y (Timilia)", "Defense/Stress Related Proteins"], ["B4FFZ9", "OBP1A", "Maize", "Oil body-associated protein 1A", "4.60", "4.17 × 10−9", "97.23", "5", "5", "9.09", "5.73 × 10−9", "106.51", "4", "4", "", "Others"], ["P82977", "ICIW", "Wheat", "Subtilisin-chymotrypsin inhibitor WSCI", "6.61", "7.87 × 10−9", "36.55", "2", "2", "4.67", "6.87 × 10−8", "84.71", "3", "3", "", "Defense/Inhibitor"], ["P31922", "SUS1", "Barley", "Sucrose synthase 1", "6.31", "1.37 × 10−7", "94.78", "10", "2", "3.95", "9.51 × 10−7", "51.48", "11", "3", "", "Starch biosynthesis"], ["Q43009", "SUS3", "Rice", "Sucrosesynthase 3", "3.13", "3.21 × 10−7", "77.26", "7", "2", "2.10", "9.56 × 10−5", "42.12", "10", "2", "", "Starch biosynthesis"], ["Timilia vs. Russello", "", "", "", "", "", "", "", "", "", "", "", "", "", "", ""], ["P23951", "CHI2", "Barley", "26 kD aendochitinase 2", "0.27", "3.29 × 10−4", "53.12", "17", "10", "0.33", "4.27 × 10−8", "87.68", "12", "6", "", "Defense/Stress Related Proteins"], ["P10846", "IAA3", "Wheat", "α-amylase inhibitor WDAI-3 (Fragment)", "0.39", "1.45 × 10−3", "36.20", "9", "4", "0.39", "3.91 × 10−6", "33.03", "8", "3", "Y (Timilia)", "Defense/Inhibitor"], ["Q2A783", "AVLB1", "Wheat", "Avenin-like b1", "38.49", "2.37 × 10−11", "99.23", "8", "6", "25.39", "1.84 × 10−8", "119.91", "8", "6", "Y (Timilia)", "Storage"], ["P29114", "LOX1", "Barley", "Linoleate 9S-lipoxygenase 1", "2.42", "1.31 × 10−6", "42.63", "8", "8", "2.28", "2.30 × 10−6", "55.34", "9", "9", "", "Others"], ["Q9ST57", "SPZ2A", "Wheat", "Serpin-Z2A", "0.02", "4.04 × 10−6", "96.72", "7", "3", "0.02", "3.47 × 10−13", "94.42", "5", "2", "", "Defense/Inhibitor"], ["P82977", "ICIW", "Wheat", "Subtilisin-chymotrypsin inhibitor WSCI", "6.74", "4.00 × 10−9", "79.02", "2", "2", "5.81", "2.35 × 10−8", "96.24", "3", "3", "", "Defense/Inhibitor"], ["P31922", "SUS1", "Barley", "Sucrose synthase 1", "3.36", "3.11 × 10−7", "68.34", "13", "3", "2.05", "2.74 × 10−5", "45.72", "12", "4", "", "Starch biosynthesis"], ["Q43009", "SUS3", "Rice", "Sucrose synthase 3", "3.11", "6.36 × 10−7", "58.15", "7", "2", "2.30", "1.03 × 10−5", "50.21", "7", "2", "", "Starch biosynthesis"]], "row_count": 25, "column_count": 16, "numeric_cells": 232, "header_rows": 2, "locator": "section[3]/table-wrap[2]#molecules-26-02596-t002"}}, {"id": "asset:table:pmid:33946829:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fe370c899ca10be93190909f500e57eee8870a12c32c3ea0f3ba03760d2627a8", "bytes": 761, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#array1", "version": null, "note": null, "structure": {"pmcid": "PMC8124627", "section_index": 13, "section_title": "Abbreviations", "row_count": 19, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["MS", "Mass Spectrometry"], ["CD", "Celiac Deasease"], ["IgE", "Immunoglobulin E"], ["NCWS", "Non Celiac Wheat Sentivity"], ["DAP", "Differentially Abundant Proteins"], ["WSCI", "Subtilisin Chymotrypsin Inhibitor"], ["ALPs", "Avenin-Like Proteins"], ["SUS1", "Sucrose Synthase 1"], ["SUS3", "Sucrose Synthase 3"], ["LOX", "Linoleate Lipoxygenase"], ["FA", "Formic Acid"], ["EDTA", "Ethylenediaminetetraacetic acid"], ["DTT", "Dithiothreitol"], ["IAA", "Iodoacetamide"], ["ACN", "Acetonitrile"], ["c-RAP", "common Repository of Adventitious Proteins"], ["PSMs", "Peptide Spectral Matches"], ["FDR", "False Discovery Rate"], ["RT", "Retention Time"]], "row_count": 19, "column_count": 2, "numeric_cells": 2, "header_rows": 0, "locator": "section[13]/table-wrap[1]#array1"}}], "gaps": ["asset:data:geo:PXD024204 not downloaded", "asset:data:geo:PXD024204 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A protein was quantified when: (i) at least two of its unique peptides satisfied the parameters above reported; (ii) was identified in a minimum of five out of nine nanoLC-MS/MS runs per flour sample; and (iii) had a p-value < 0.05 and a significance ≥ 20 (significance method ANOVA; the significance score was calculated as the −10log10 of the significance testing p-value)."}}, {"id": "method-2", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["PXD024204"], "resolved_accessions": ["PXD024204"], "statements": ["Not applicable."], "basis": "The paper names PXD024204 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:33946829", "data:geo:PXD024204", "asset:table:pmid:33946829:1", "asset:table:pmid:33946829:2", "asset:table:pmid:33946829:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD024204"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:38Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 44139, "completion_tokens": 1305, "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:33946829", "type": "paper", "label": "pmid:33946829"}, {"id": "source:pmid:33946829", "type": "manuscript", "label": "PMID 33946829 full text"}, {"id": "data:geo:PXD024204", "type": "dataset", "label": "GEO PXD024204"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33946829", "type": "paper", "label": "pmid:33946829"}, {"id": "source:pmid:33946829", "type": "manuscript", "label": "PMID 33946829 full text"}, {"id": "data:geo:PXD024204", "type": "dataset", "label": "GEO PXD024204"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33946829", "type": "extraction", "used": ["source:pmid:33946829"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD024204", "type": "accession_resolution", "used": ["data:geo:PXD024204"], "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:33946829", "parent_hash": "sha256:cb3aabf1f903320f07c3ac9aa56d786297dd808f73f3de200d40a287685385dd", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD024204 licence not read", "asset:data:geo:PXD024204 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A protein was quantified when: (i) at least two of its unique peptides satisfied the parameters above reported; (ii) was identified in a minimum of five out of nine nanoLC-MS/MS runs per flour sample; and (iii) had a p-value < 0.05 and a significance ≥ 20 (significance method ANOVA; the significance score was calculated as the −10log10 of the significance testing p-value)."], "order_basis": "analysis_only", "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":"2026-11-04T01:43:02+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}}}