{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26217750", "kind": "science-record", "revision": 5, "content_hash": "sha256:c371e0ffd77d441b7f2894d465d41e67b25e23dab2471fb1a331efd064e8cf90", "created_at": "2026-11-01T15:40:09Z", "updated_at": "2026-11-01T18:47:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Quantitative proteomics of rat and human pancreatic beta cells.", "doi": "10.1016/j.dib.2015.02.019", "pmid": "26217750", "authors": ["B Brackeva", "G Kramer", "J P C Vissers", "G A Martens"], "journal": "Data in brief", "year": 2015, "abstract": "Data set description: This data set is composed by label-free alternate-scanning LC-MS/MS proteomics analysis human and Wistar rat pancreatic islet endocrine cells. The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat). From these mass spectrometry data, 'relative molar amount units' between cell types and across species were calculated. Biological relevance: These data provide a quantitative view on the unfractionated proteomes of human and rat beta and alpha cells. It is likely biased towards the proteins with higher molar abundance, relating to core functional pathways, but also includes several proteins with an islet-enriched expression. The quality of the cell preps is state-of-the-art, and the label-free quantitation is both precise and accurate, allowing detailed quantitative analysis.", "claims": [{"id": "claim-data-access", "statement": "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26217750", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper reports highly reproducible label-free alternate-scanning LC-MS/MS protein quantification with overall technical plus biological imprecision below 20%, using geometric normalization for cross-cell-type and cross-species comparisons; the source data were deposited through ProteomeXchange/PRIDE as PXD001539 for human samples and PXD001816 for rat samples.", "kind": "quantitative", "target": {"value": 20.0, "unit": "per cent", "tolerance": null, "source": "We showed that alternate-scanning LC-MS/MS generated highly reproducible protein quantifications (with overall technical plus biological imprecision<20% and high accuracies as judged by correct measurement of multi-enzyme stoichiometry [4])."}, "evidence": [{"asset": "source:pmid:26217750", "locator": "sections[2] \"Value of the data\" paragraph 2", "quote": "We showed that alternate-scanning LC-MS/MS generated highly reproducible protein quantifications (with overall technical plus biological imprecision<20% and high accuracies as judged by correct measurement of multi-enzyme stoichiometry [4])."}, {"asset": "source:pmid:26217750", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper reports highly reproducible label-free alternate-scanning LC-MS/MS protein quantification with overall technical plus biological imprecision below 20%, using geometric normalization for cross-cell-type and cross-species comparisons; the source data were deposited through ProteomeXchange/PRIDE as PXD001539 for human samples and PXD001816 for rat samples.", "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:26217750"], "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:PXD001539"], "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:PXD001539"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26217750", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2015.02.019", "sha256": "sha256:88df643b6b106f3ceb0c1f34ef86d0df20c07713aae75dc18591cbf036f17515", "bytes": 15152, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2015.02.019", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4510137", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD001539", "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=PXD001539", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD001539", "version": null, "note": "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantitative proteomics of human pancreatic beta cells", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD001816", "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=PXD001816", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD001816", "version": null, "note": "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Quantitative proteomics of rat and human pancreatic beta cells", "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:26217750:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:af6fc7bb341cd9a6d20b647bcf2117ab1502e807dd5cd6f3bc3bdb33b5108fbf", "bytes": 2415, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0015", "version": null, "note": null, "structure": {"pmcid": "PMC4510137", "section_index": 1, "section_title": "Specifications table", "row_count": 23, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Rat and human pancreatic beta cell proteomics"], ["Type of data", "Excel tables"], ["How data was acquired", "Label-free alternate-scanning LC-MS proteomics; Nanoscale LC separation of tryptic peptides was performed with"], ["", "a nanoACQUITY system (Waters Corporation), equipped with a"], ["", "Symmetry C18 5 mm, 2 cm 6180 mm precolumn and an Atlantis"], ["", "C18 3 mm, 25 cm 675 mm or a Atlantis C18 3 mm, 15 cm"], ["", "675 mm analytical reversed phase column (Waters Corporation)."], ["Data format", "Raw/Analyzed"], ["Experimental factors", "Proteomes of rat alpha and beta cells were studied immediately after cell isolation, without in vitro culture or treatment. Proteins were typically extracted within 4 h of animal killing. Human beta cells were prepared from islet-enriched pancreas fractions, cultured for 6–14 days after human organ procurement. Selected fractions cleared for research were then trypsin-dissociated into single cell suspensions and FACS-sorted according to cell size, granularity and zinc content to an average insulin-purity of 60%. Proteomes of these cells was studied immediately after cell isolation without additional treatment or further culture."], ["Experimental features", "Proteomes were recorded using label-free LC-MS/MS. Accurate mass precursor and fragment ion LC-MS data were collected in data independent, alternate scanning (LC-MSE) mode of acquisition [2,3]. Biological interpretation of the “relative molar amount units” was done after geometric normalization to a network of stable reference proteins [4–8]"], ["Data source location", "Rat data: Waters Corp., Manchester, UK, Analyst: J.P.C. Vissers"], ["", "Human data: Department of Medical Biochemistry, Academisch Medisch Centrum, Amsterdam, the Netherlands, Analyst: G. Kramer"], ["Data accessibility", "Raw data uploaded to ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers"], ["", "PXD001539: human data"], ["", "Project DOI: 10.6019/PXD001539"], ["", "Reviewer account details:"], ["", "Username: reviewer99564@ebi.ac.uk"], ["", "Password: pJzPiCIj"], ["", "PXD001816: rat data"], ["", "Project DOI: 10.6019/PXD001816"], ["", "Username: reviewer43213@ebi.ac.uk"], ["", "Password: y2B5bYLW"]], "row_count": 23, "column_count": 2, "numeric_cells": 11, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0015"}}, {"id": "asset:table:pmid:26217750:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8cd17ca70be354c7cee7724a1be947b7fb2b5e26794d14c621906eb9d761ea3a", "bytes": 2522, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t0005", "version": null, "note": "Overview of all technical replicate LC-MS/MS injections of the indicated independent biological isolates. First column indicated the sample name, second column listed the codes of individual technical replicates, as used in the supplementary raw MZml data files.", "structure": {"pmcid": "PMC4510137", "section_index": 3, "section_title": "Data, full experimental design, materials and methods", "row_count": 43, "column_count": 6}, "table": {"label": "Table 1", "caption": "Overview of all technical replicate LC-MS/MS injections of the indicated independent biological isolates. First column indicated the sample name, second column listed the codes of individual technical replicates, as used in the supplementary raw MZml data files.", "rows": [["Human pancreas number", "Code tech. Replicate", "", "% insulin+", "% dead", "Rapigest"], ["HP2010 #3121", "20111012_s4b", "human beta cells, donor 1", "68", "4", "0.50%"], ["", "20111103_s4a", "", "", "", ""], ["", "20111103_s4c", "", "", "", ""], ["HP2064 #1421", "20111103_s5a", "human beta cells, donor 2", "62", "3", "0.50%"], ["", "20111103_s5b", "", "", "", ""], ["", "20111103_s5c", "", "", "", ""], ["HP2785 #2721", "20111103_s6a", "human beta cells, donor 3", "58", "2", "0.50%"], ["", "20111103_s6b", "", "", "", ""], ["", "20111103_s6c", "", "", "", ""], ["HP2789 #1821", "20111103_s7a", "human beta cells, donor 4", "53", "4", "0.50%"], ["", "20111103_s7b", "", "", "", ""], ["", "20111103_s7c", "", "", "", ""], ["HP2703 #2", "20111103_s8a", "human duct/exocrine", "2", "24", "0.50%"], ["", "20111103_s8b", "", "", "", ""], ["", "20111103_s8c", "", "", "", ""], ["HP2010 #3121 1% Rapigest", "20111103_s16a", "re-extraction of HP2010", "68", "4", "1.00%"], ["", "20111103_s16b", "at 1% Rapigest", "", "", ""], ["", "20111103_s16c", "(data not further used)", "", "", ""], [""], ["Rat beta cells", "Code tech. Replicate", "", "% insulin+", "% glucagon", "Rapigest"], [""], ["beta 001", "011108_002", "biological replicate 1", "90", "3", "0.50%"], ["", "011108_003", "(pool of 25 animals)", "", "(average)", ""], ["", "011108_004", "", "", "", ""], ["beta 002", "011108_010", "biological replicate 2", "", "", ""], ["", "011108_011", "(pool of 25 animals)", "", "", ""], ["", "011108_012", "", "", "", ""], ["beta 003", "011108_019", "biological replicate 3", "", "", ""], ["", "011108_020", "(pool of 25 animals)", "", "", ""], ["", "011108_021", "", "", "", ""], [""], ["Rat alpha cells", "Code tech. Replicate", "", "% insulin+", "% glucagon", "Rapigest"], [""], ["alpha 001", "011108_006", "biological replicate 1", "2", "94", "0.50%"], ["", "011108_007", "(pool of 25 animals)", "", "(average)", ""], ["", "011108_008", "co-isolated with beta 001", "", "", ""], ["alpha 002", "011108_014", "biological replicate 2", "", "", ""], ["", "011108_015", "(pool of 25 animals)", "", "", ""], ["", "011108_016", "co-isolated with beta 002", "", "", ""], ["alpha 003", "011108_022", "biological replicate 3", "", "", ""], ["", "011108_023", "(pool of 25 animals)", "", "", ""], ["", "011108_024", "co-isolated with beta 003", "", "", ""]], "row_count": 43, "column_count": 6, "numeric_cells": 93, "header_rows": 1, "locator": "section[3]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:26217750:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8e42dfec8266326590ff00d8722666806dbc0728f11773afd96d2e670887a160", "bytes": 747, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#t0010", "version": null, "note": "Overview of total proteins identified and quantified by LC-MS/MS in the various cell preparations, along criteria specified in Materials & Methods.", "structure": {"pmcid": "PMC4510137", "section_index": 3, "section_title": "Data, full experimental design, materials and methods", "row_count": 9, "column_count": 6}, "table": {"label": "Table 2", "caption": "Overview of total proteins identified and quantified by LC-MS/MS in the various cell preparations, along criteria specified in Materials & Methods.", "rows": [["", "", "rat", "human"], ["", "", "beta", "alpha", "beta", "exocrine"], ["number of proteins identified", "n≥1", "506", "417", "462", "372"], ["number of proteins quantified", "n≥2", "465", "353", "413", "300"], ["GEO-normalized molar amount", "highest", "3.61", "8.22", "8.95", "14.74"], ["", "lowest", "0.02", "0.02", "0.01", "0.06"], ["", "dynamic range", "226", "548", "746", "246"], ["biological replicates (x)", "", "3", "3", "4", "1"], ["technical replicates (n)", "", "3", "3", "3", "3"]], "row_count": 9, "column_count": 6, "numeric_cells": 30, "header_rows": 2, "locator": "section[3]/table-wrap[2]#t0010"}}], "gaps": ["asset:data:geo:PXD001539 not downloaded", "asset:data:geo:PXD001539 licence not read", "asset:data:geo:PXD001816 not downloaded", "asset:data:geo:PXD001816 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 20.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": ["method", "operations"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["PXD001539", "PXD001816"], "resolved_accessions": ["PXD001539", "PXD001816"], "statements": ["The mass spectrometry data of the human and rat pancreatic beta cells and the resulting proteome search output from ProteinLynx GlobalSERVER (PLGS) have been deposited to the ProteomeXchange Consortium [1] via the PRIDE partner repository with the dataset identifiers PXD001539 (human) and PXD001816 (rat)."], "basis": "The paper names PXD001539, PXD001816 in ProteomeXchange Consortium and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26217750", "data:geo:PXD001539", "asset:table:pmid:26217750:1", "asset:table:pmid:26217750:2", "asset:table:pmid:26217750:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD001539"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:17Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 33301, "completion_tokens": 3973, "cached_tokens": 1560}}, "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:26217750", "type": "paper", "label": "pmid:26217750"}, {"id": "source:pmid:26217750", "type": "manuscript", "label": "PMID 26217750 full text"}, {"id": "data:geo:PXD001539", "type": "dataset", "label": "GEO PXD001539"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26217750", "type": "paper", "label": "pmid:26217750"}, {"id": "source:pmid:26217750", "type": "manuscript", "label": "PMID 26217750 full text"}, {"id": "data:geo:PXD001539", "type": "dataset", "label": "GEO PXD001539"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26217750", "type": "extraction", "used": ["source:pmid:26217750"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD001539", "type": "accession_resolution", "used": ["data:geo:PXD001539"], "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:26217750", "parent_hash": "sha256:3da2a920e1a9001bd6c37ec5e15ec746d7265c727e68f1d3667863ed59f5fcfb", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:PXD001539 licence not read", "asset:data:geo:PXD001539 not downloaded", "asset:data:geo:PXD001816 licence not read", "asset:data:geo:PXD001816 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Quantitative proteomics of rat and human pancreatic beta cells.", "C-MS/MS proteomics analysis human and Wistar rat pancreatic islet endocrine cells. The mass s", "The mass spectrometry data of the human and rat pancreatic beta cells and the resulting prot", "on the unfractionated proteomes of human and rat beta and alpha cells. It is likely biased to"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Quantitative proteomics of rat and human pancreatic beta cells.", "ed by label-free alternate-scanning LC-MS/MS proteomics analysis human and Wistar rat pancreatic isl", "s described [9,10]. Cells were processed for proteomics immediately after cell isolation without add", "se cells were then immediately processed for proteomics, exactly as done for the rat cells, without"], "order_basis": "paper_text_order:0", "id": "assay:2"}, {"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["alyzed islet endocrine cell preparations: (i)FACS-purified rat insulin-producing beta cells (9", "s, 3 technical replicate injections each:(ii)FACS-enriched rat glucagon-producing alpha cells", "plicates each. Rat alpha and beta cells were FACS-purified as described [9,10]. Cells were pro", "without additional culture or treatment.(iii)FACS-enriched human beta cell preparations (n=4 d"], "order_basis": "paper_text_order:1195", "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":"2026-11-04T00:45:03+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}}}