{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26693171", "kind": "science-record", "revision": 3, "content_hash": "sha256:a8bdbcb68c836ef749f83334d0bf7d62d628ab4d35dabda921b1097272871013", "created_at": "2026-11-01T15:40:14Z", "updated_at": "2026-11-01T18:47:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Delineating the glycoproteome of elongating cotton fiber cells.", "doi": "10.1016/j.dib.2015.10.015", "pmid": "26693171", "authors": ["Saravanan Kumar", "Pankaj Pandey", "Krishan Kumar", "Vijayalakshmi Rajamani", "Kethireddy Venkata Padmalatha", "Gurusamy Dhandapani", "Mogilicherla Kanakachari", "Sadhu Leelavathi", "Polumetla Ananda Kumar", "Vanga Siva Reddy"], "journal": "Data in brief", "year": 2015, "abstract": "The data presented here delineates the glycoproteome component in the elongating cotton fiber cells attained using complementary proteomic approaches followed by protein and N-linked glycosylation site identification (Kumar et al., 2013) [1]. Utilizing species specific protein sequence databases in proteomic approaches often leads to additional information that may not be obtained using cross-species databases. In this context we have reanalyzed our glycoproteome dataset with the Gossypium arboreum, Gossypium raimondii (version 2.0) and Gossypium hirsutum protein databases that has led to the identification of 21 N-linked glycosylation sites and 18 unique glycoproteins that were not reported in our previous study. The 1D PAGE and solution based glycoprotein identification data is publicly available at the ProteomeXchange Consortium via the PRIDE partner repository (Vizcaíno et al., 2013) [2] using the dataset identifier PXD000178 and the 2D PAGE based protein identification and glycopeptide approach based N-linked glycosylation site identification data is available at the ProteomeXchange Consortium via the PRIDE partner repository (Vizcaíno et al., 2013) [2] using the dataset identifier PXD002849.", "claims": [{"id": "claim-data-access", "statement": "The data is accessible via this article, via the related research article [1], and at the ProteomeXchange Consortium via the PRIDE partner repository [2] using the dataset identifier PXD000178 and PXD002849. (http://proteomecentral.proteomexchange.org)", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26693171", "locator": "sections[2] \"table-wrap\" paragraph 1", "quote": "The data is accessible via this article, via the related research article [1], and at the ProteomeXchange Consortium via the PRIDE partner repository [2] using the dataset identifier PXD000178 and PXD002849. (http://proteomecentral.proteomexchange.org)"}], "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:26693171"], "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:PXD000178"], "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:PXD000178"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26693171", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2015.10.015", "sha256": "sha256:fa8f9d3904cfe6ea0a8c6cee194c188cf9b35fd374b558ea57e8f91d44fd161c", "bytes": 19492, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2015.10.015", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4652025", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD000178", "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=PXD000178", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000178", "version": null, "note": "The data is accessible via this article, via the related research article [1], and at the ProteomeXchange Consortium via the PRIDE partner repository [2] using the dataset identifier PXD000178 and PXD002849. (http://proteomecentral.proteomexchange.org)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data is accessible via this article, via the related research article [1], and at the ProteomeXchange Consortium via the PRIDE partner repository [2] using the dataset identifier PXD000178 and PXD002849. (http://proteomecentral.proteomexchange.org)", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Cotton Fiber Glycoproteome -  Glycoproteome of elongating cotton fiber 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:PXD002849", "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=PXD002849", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002849", "version": null, "note": "The data is accessible via this article, via the related research article [1], and at the ProteomeXchange Consortium via the PRIDE partner repository [2] using the dataset identifier PXD000178 and PXD002849. (http://proteomecentral.proteomexchange.org)", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data is accessible via this article, via the related research article [1], and at the ProteomeXchange Consortium via the PRIDE partner repository [2] using the dataset identifier PXD000178 and PXD002849. (http://proteomecentral.proteomexchange.org)", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Glycoproteome of Elongating cotton fiber 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:26693171:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:66b3ba3f38a475f24f1e76236398c89c3d85da765e6264eaac4b6bfc1c957667", "bytes": 4715, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#t0005", "version": null, "note": "Glycosylation site assignment using MALDI TOF/TOF (Additional glycosylation sites exclusively reported in the current study).", "structure": {"pmcid": "PMC4652025", "section_index": 5, "section_title": "Data", "row_count": 53, "column_count": 7}, "table": {"label": "Table 1", "caption": "Glycosylation site assignment using MALDI TOF/TOF (Additional glycosylation sites exclusively reported in the current study).", "rows": [["Sl no.", "Accession no.", "Protein ID – [Source]", "Observed Mole Wt", "Sequence coverage %", "Peptides sequenced by MS/MS+modifications", "MOWSEscore"], [""], ["1", "Gorai.008G010600.1", "PREDICTED: desiccation-related protein PCC13-62-like [Gossypium raimondii]", "2669.3126", "12", "R.TLLNDVIN(+.98)STVQPYTFTAAELSN(+.98)R.T+2 Deamidated (NQ)", "224"], ["", "Cotton_A_34455_BGI-A2_v1.0", "", "", "", ""], ["", "CotAD_12989", "", "", "", ""], ["", "Cotton_D_gene_10038147*", "Predicted protein [Populus trichocarpa] Dessication related protein", "", "", "", ""], ["2", "Cotton_A_24352_BGI-A2_v1.0", "PREDICTED: PI-PLC X domain-containing protein At5g67130 [Gossypium raimondii]", "2949.3709", "12", "R.SLILQNYFPSNPN(+.98)ETAACAENSAPLVK.M+Deamidated (NQ)", "209"], ["", "CotAD_35067", "", "", "", ""], ["", "Gorai.007G214400.8", "", "", "", "", ""], ["3", "CotAD_16513", "Proline--tRNA ligase [Gossypium arboreum]", "2197.959", "4", "K.LSCN(+.98)SSSSSSEAGFSQATSFR.M+Deamidated (NQ)", "190"], ["", "Cotton_A_23586_BGI-A2_v1.0", "", "", "", ""], ["", "Gorai.001G140300.2", "", "", "", "", ""], ["4", "Gorai.010G096500.1", "Pathogenesis-related PR-1 type [Gossypium arboreum]", "1825.9076", "7", "K.LTDNPADELVAVLNAN(+.98)R.T+Deamidated (NQ)", "119"], ["", "CotAD_53847", "", "", "", "", ""], ["", "Cotton_D_gene_10026388*", "", "", "", "", ""], ["5", "Cotton_A_16611_BGI-A2_v1.0", "Monocopper oxidase-like protein SKU5 [Gossypium arboreum]", "2044.058", "7", "K.FPGPTIN(+.98)STTNNNVVVNVR.N+Deamidated (NQ)", "119"], ["", "CotAD_19756", "", "", "", "", ""], ["", "Cotton_D_gene_10015446", "", "", "", "", ""], ["6", "Gorai.009G246700.1", "PREDICTED: protein disulfide-isomerase-like [Gossypium raimondii]", "1396.668", "4", "R.STSGN(+.98)ITPYEGNR.T+Deamidated (NQ)", "88"], ["", "Cotton_A_16089_BGI-A2_v1.0", "", "", "", "", ""], ["", "CotAD_73953", "", "", "", "", ""], ["", "Cotton_D_gene_10007690*$", "", "", "", "", ""], ["7", "Gorai.013G030200.1", "PREDICTED: probable receptor protein kinase TMK1 [Gossypium raimondii]", "1692.7943", "1", "R.LN(+.98)GTIEVIQN(+.98)MSSLR.E+2 Deamidated (NQ); Oxidation (M)", "47"], ["", "Cotton_A_00858_BGI-A2_v1.0", "", "", "", "", ""], ["", "CotAD_24219", "", "", "", "", ""], ["", "Cotton_D_gene_10024539", "", "", "", "", ""], ["8", "Cotton_A_24352_BGI-A2_v1.0", "PREDICTED: PI-PLC X domain-containing protein At5g67130 [Gossypium raimondii]", "2409.0506", "7", "Q.NYFPTNPN(+.98)ETAACAENSAPLVK.M+Deamidated (NQ)", "152"], ["", "CotAD_35067", "", "", "", "", ""], ["", "Gorai.007G214400.1", "", "", "", "", ""], ["9", "Gorai.004G201700.1", "PREDICTED: protein YLS3-like [Gossypium raimondii]", "2572.1033", "10", "S.CYPYLNN(+.98)ATAKPEDDCCNPIR.Q+Deamidated (NQ)", "47"], ["", "Cotton_A_36086_BGI-A2_v1.0", "", "", "", "", ""], ["", "CotAD_48188", "", "", "", "", ""], ["10", "Gorai.007G021100.2", "PREDICTED: lipid transfer-like protein VAS [Gossypium raimondii]", "1560.7793", "12", "F.ASLN(+.98)ISTAQALN(+.98)VTR.E+2 Deamidated (NQ)", "135"], ["", "CotAD_02614", "", "", "", "", ""], ["11", "Gorai.008G216800.1", "PREDICTED: acid beta-fructofuranosidase-like [Gossypium raimondii]", "2176.928", "9", "R.PLN(+.98)TSDGSLETYFCADETR.S+Deamidated (NQ)", "50"], ["", "CotAD_31849", "", "", "", "", ""], ["12", "Cotton_A_11565_BGI-A2_v1.0", "PREDICTED: GDSL esterase/lipase At5g14450-like [Gossypium raimondii]", "1686.8147", "9", "R.RPN(+.98)ETIYEYGISPF.G+Deamidated (NQ)", "103"], ["", "Gorai.001G266600.1", "", "", "", "", ""], ["", "CotAD_07905", "", "", "", "", ""], ["13", "Gorai.006G117500.1", "PREDICTED: protein STRICTOSIDINE SYNTHASE-LIKE 3-like [Gossypium raimondii]", "1061.3817", "3", "K.DFAYTSSN(+.98)R.S+Deamidated (NQ)", "45"], ["", "CotAD_27689", "", "", "", "", ""], ["14", "Cotton_A_36266_BGI-A2_v1.0", "Hydantoin utilization C [Gossypium arboreum] Isoform of S.NO 25", "1622.6905", "3", "K.TTVDGQN(+.98)ISFLEAAR.S+Deamidated (NQ)", "51"], ["", "CotAD_68215", "", "", "", "", ""], ["15", "Gorai.003G061600.1", "PREDICTED: lysM domain receptor-like kinase 3 isoform X1 [Gossypium raimondii]", "1288.691", "1", "K.NYATN(+.98)TTFTVR.S+Deamidated (NQ)", "47"], ["", "CotAD_65258", "", "", "", "", ""], ["", "Cotton_A_27440_BGI-A2_v1.0", "", "", "", "", ""], ["16", "CotAD_16513", "Proline--tRNA ligase [Gossypium arboreum]", "3367.4499", "6", "S.GVN(+.98)YSSSVGMKLSCN(+.98)SSSSSSEAGFSQATSFR.M+Carbamyl (N-term); 2 Deamidated (NQ); Oxidation (M)", "150"], ["", "Cotton_A_23586_BGI-A2_v1.0", "", "", "", "", ""], ["", "Gorai.001G140300.3", "", "", "", "", ""], ["17", "CotAD_72223", "PREDICTED: beta-xylosidase/alpha-L-arabinofuranosidase 2 [Gossypium raimondii]", "1502.7566", "4", "T.AASFN(+.98)TSLYETIGK.V+Deamidated (NQ)", "50"], ["", "Cotton_A_27349_BGI-A2_v1.0", "", "", "", "", ""], ["", "Gorai.005G218000.2", "", "", "", "", ""], [""]], "row_count": 53, "column_count": 7, "numeric_cells": 144, "header_rows": 0, "locator": "section[5]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:26693171:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1ddf95bafd9e62e23a5ad16ae0dcb58cbe3732c53de3320d41b1bb87893747af", "bytes": 3289, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#t0010", "version": null, "note": "Additional protein identified in the current study using Gossypium species specific protein sequence databases.", "structure": {"pmcid": "PMC4652025", "section_index": 15, "section_title": "Data analysis using Scaffold and bioinformatic tools", "row_count": 21, "column_count": 7}, "table": {"label": "Table 2", "caption": "Additional protein identified in the current study using Gossypium species specific protein sequence databases.", "rows": [["Sl no.", "Accession no.", "Protein ID – [Source]", "Mole Wt (kDa)", "Observedmass(M+H)+", "Peptides sequenced by MS/MS", "MOWSE score"], [""], ["1", "Gorai.002G207900.1", "Predicted:Separase isoform X1 [Gossypium raimondii] Pepridase_C50", "215.624", "1140.65", "S.ADHLSEDVVR.D", "58"], ["2", "CotAD_40266 Gorai.004G002500.1", "Predicted:cucumisin-like [Gossypium raimondii] Peptidase_S8_3", "144.236", "2049.08", "K.LAGNNTSCPKNSTKMLPR.D+Carbamyl (L), Carbamidomethyl (C), Oxidation (M)", "54"], ["3", "CotAD_03361 Gorai.009G100400.1", "Predicted: heat shock cognate 70 kDa protein 2 like [Gossypium raimondii]", "71.222", "1568.80", "K.QFAAEEISSMVLMK.M+Ammonia-loss (Q)", "45"], ["4", "Cotton_A_01713", "Aldehyde oxidase 4-like protein [Gossypium arboreum]", "145.122", "2283.38", "K.QMTAYGLGLVKCGGTQDLLEK.V+Carbamidomethyl (C)", "57"], ["5", "Cotton_A_01770", "Predicted:Cysteine proteinase inhibitor like [Gosyypium raimondii]", "11.388", "2357.10", "M.ATLGGISQVDGSANSLEIENLAR.F+Acetyl (A)", "62"], ["6", "Cotton_A_01738", "Predicted:Auxin response factor 4-like isoform X1 [Gosyypium raimondii]", "84.086", "1429.76", "P.RASHAEFVIPFR.K", "65"], ["7", "Cotton_A_01780", "Predicted:crt homolog 1 isoform X3 [Gosyypium raimondii] CRT-Chlorouine resistance transporter", "47.582", "1165.45", "P.VGRSEGGDCTK.K+Carbamidomethyl (C)", "58"], ["8", "Cotton_A_01799", "Ribonuclease I [Gossypium arboreum]", "104.392", "1026.56", "V.TGGSGSIYER.F", "63"], ["9", "CotAD_36535 Cotton_A_04276", "Protein disulfide isomerase-like 1-4 [Gossypium arboreum]", "65.760", "1619.74", "Y.FFVDGKHKPYPGAR.N", "59"], ["10", "CotAD_73953", "Predicted:Protein disulfide-isomerase-like [Gossypium raimondii]", "52.851", "1748.81", "I.EDATANDIVGENFDVR.G", "90"], ["11", "CotAD_38843", "PREDICTED: heat shock cognate 70 kDa protein 2-like isoform X1 [Gossypium raimondii]", "70.793", "1740.73", "K.ETAEAYLGSTVKNGVVT.V", "90"], ["12", "CotAD_45862", "Fructokinase [Gossypium hirsutum]", "34.965", "1616.77", "K.QNGVSGDGILFDQGAR.T+Ammonia-loss (Q)", "72"], ["13", "CotAD_44107 Gorai.002G182000.1", "Predicted:nuclear transport factor 2 [Gossypium raimondii]", "13.373", "1705.87", "K.AFVDHYYSTFDANR.A", "42"], ["14", "CotAD_24219 Gorai.013G030200.1", "PREDICTED: probable receptor protein kinase TMK1 [Gossypium raimondii]", "102.438", "1692.79", "R.LNGTIEVIQNMSSLR.E+2 Deamidated (N); Oxidation (M) (Glycopeptide)", "47"], ["15", "CotAD_02614 Gorai.007G021100.2", "PREDICTED: lipid transfer-like protein VAS [Gossypium raimondii]", "15.572", "1560.77", "F.ASLNISTAQALNVTR.E+2 Deamidated (NQ) (Glycopeptide)", "135"], ["16", "CotAD_27689 Gorai.006G117500.1", "PREDICTED: protein STRICTOSIDINE SYNTHASE-LIKE 3-like [Gossypium raimondii]", "43.827", "1061.38", "K.DFAYTSSNR.S+Deamidated (N) (Glycopeptide)", "45"], ["17", "CotAD_68215 Cotton_A_36266", "Hydantoin utilization C [Gossypium arboreum]", "51.739", "1622.69", "K.TTVDGQNISFLEAAR.S+Deamidated (N) (Glycopeptide)", "51"], ["18", "CotAD_65258 Gorai.003G061600.1", "PREDICTED: lysM domain receptor-like kinase 3 isoform X1 [Gossypium raimondii]", "73.564", "1288.69", "K.NYATNTTFTVR.S+Deamidated (N) (Glycopeptide)", "47"], [""]], "row_count": 21, "column_count": 7, "numeric_cells": 103, "header_rows": 0, "locator": "section[15]/table-wrap[1]#t0010"}}], "gaps": ["asset:data:geo:PXD000178 not downloaded", "asset:data:geo:PXD000178 licence not read", "asset:data:geo:PXD002849 not downloaded", "asset:data:geo:PXD002849 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "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": ["PXD000178", "PXD002849"], "resolved_accessions": ["PXD000178", "PXD002849"], "statements": ["The data is accessible via this article, via the related research article [1], and at the ProteomeXchange Consortium via the PRIDE partner repository [2] using the dataset identifier PXD000178 and PXD002849. (http://proteomecentral.proteomexchange.org)"], "basis": "The paper names PXD000178, PXD002849 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": [], "assets": ["source:pmid:26693171", "data:geo:PXD000178", "asset:table:pmid:26693171:1", "asset:table:pmid:26693171:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD000178"]}, "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": "2026-10-31T18:06:44Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 16712, "completion_tokens": 1254, "cached_tokens": 512}}, "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:26693171", "type": "paper", "label": "pmid:26693171"}, {"id": "source:pmid:26693171", "type": "manuscript", "label": "PMID 26693171 full text"}, {"id": "data:geo:PXD000178", "type": "dataset", "label": "GEO PXD000178"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26693171", "type": "paper", "label": "pmid:26693171"}, {"id": "source:pmid:26693171", "type": "manuscript", "label": "PMID 26693171 full text"}, {"id": "data:geo:PXD000178", "type": "dataset", "label": "GEO PXD000178"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26693171", "type": "extraction", "used": ["source:pmid:26693171"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD000178", "type": "accession_resolution", "used": ["data:geo:PXD000178"], "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:26693171", "parent_hash": "sha256:88c19e842cc075118f27ab4e21d7b325e1488fb77e38e88b7c683aaa3eb893e6", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD000178 licence not read", "asset:data:geo:PXD000178 not downloaded", "asset:data:geo:PXD002849 licence not read", "asset:data:geo:PXD002849 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:21:27+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}}}