{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32111039", "kind": "science-record", "revision": 7, "content_hash": "sha256:dbc510da81c6e10a7fe806aa4dcc343fc1cdc9d0701f3f39982a861b69ca7d32", "created_at": "2026-11-01T15:40:57Z", "updated_at": "2026-11-01T22:01:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomic Analysis of Mucopolysaccharidosis IIIB Mouse Brain.", "doi": "10.3390/biom10030355", "pmid": "32111039", "authors": ["Valeria De Pasquale", "Michele Costanzo", "Rosa Anna Siciliano", "Maria Fiorella Mazzeo", "Valeria Pistorio", "Laura Bianchi", "Emanuela Marchese", "Margherita Ruoppolo", "Luigi Michele Pavone", "Marianna Caterino"], "journal": "Biomolecules", "year": 2020, "abstract": "Mucopolysaccharidosis IIIB (MPS IIIB) is an inherited metabolic disease due to deficiency of α-N-Acetylglucosaminidase (NAGLU) enzyme with subsequent storage of undegraded heparan sulfate (HS). The main clinical manifestations of the disease are profound intellectual disability and neurodegeneration. A label-free quantitative proteomic approach was applied to compare the proteome profile of brains from MPS IIIB and control mice to identify altered neuropathological pathways of MPS IIIB. Proteins were identified through a bottom up analysis and 130 were significantly under-represented and 74 over-represented in MPS IIIB mouse brains compared to wild type (WT). Multiple bioinformatic analyses allowed to identify three major clusters of the differentially abundant proteins: proteins involved in cytoskeletal regulation, synaptic vesicle trafficking, and energy metabolism. The proteome profile of NAGLU-/- mouse brain could pave the way for further studies aimed at identifying novel therapeutic targets for the MPS IIIB. Data are available via ProteomeXchange with the identifier PXD017363.", "claims": [{"id": "claim-method", "statement": "A Student’s t test was used to select proteins showing significant changes between the analyzed datasets, resulting in two-tailed p values.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32111039", "locator": "sections[7] \"2.5. Quantitative Label-Free Proteomic Analysis\" paragraph 2", "quote": "A Student’s t test was used to select proteins showing significant changes between the analyzed datasets, resulting in two-tailed p values."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with the identifier PXD017363.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32111039", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with the identifier PXD017363."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:32111039"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32111039", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/biom10030355", "sha256": "sha256:115419db70cdfbfefba1b434eaddf9cd73da450f260b753669d019a76bc11fd4", "bytes": 67353, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/biom10030355", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7175334", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:32111039:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6b91a3940dd2979cb8cf356268b25a0869b26262a5fa0a48f64cca1838813e53", "bytes": 16535, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#biomolecules-10-00355-t001", "version": null, "note": "Dysregulated proteins in NAGLU−/− mouse brains compared to WT.", "structure": {"pmcid": "PMC7175334", "section_index": 12, "section_title": "3.2. Quantitative Analysis of Differentially Expressed Proteins in Brain Samples from MPS IIIB and WT Mice", "row_count": 205, "column_count": 6}, "table": {"label": "Table 1", "caption": "Dysregulated proteins in NAGLU−/− mouse brains compared to WT.", "rows": [["Swiss-Prot Code", "Gene Name", "Protein Description", "Fold NSAF", "p Value", "Subcellular Localization"], ["Q545B6", "Stmn1", "Stathmin", "−12.6", "0.00002", "CK"], ["Q9QYX7", "Pclo", "Protein piccolo", "−8.4", "0.00101", "CK, GA"], ["Q6P9K8", "Caskin1", "Caskin-1", "−3.8", "0.00262", "CK"], ["A8DUK2", "Hbbt1", "Beta-globin", "−3.4", "0.00008", "C"], ["Q4VAE3", "Tmem65", "Transmembrane protein 65", "−3.3", "0.00374", "M, PM"], ["Q8CHF1", "mKIAA0531", "Kinesin-like protein (Fragment)", "−3.2", "0.00232", "CK"], ["P17563", "Selenbp1", "Selenium-binding protein 1", "−3.2", "0.00046", "CK, N"], ["Q4KMM3", "Oxr1", "Oxidation resistance protein 1", "−3", "0.00036", "M, N"], ["A2AS98", "Nckap1", "Nck-associated protein 1", "−2.9", "0.00209", "CK, PM"], ["C7G3P1", "Ppfia3", "MKIAA0654 protein (Fragment)", "−2.6", "0.00328", "CK"], ["Q8BVQ5", "Ppme1", "Protein phosphatase methylesterase 1", "−2.5", "0.00345", "N"], ["Q3UVN5", "Nsfl1c", "Putative uncharacterized protein", "−2.5", "0.00002", "CK, GA, N"], ["Q9R0Q6", "Arpc1a", "Actin-related protein 2/3 complex subunit 1A", "−2.4", "0.00036", "CK, N, PM"], ["Q3TF14", "Ahcy", "Adenosylhomocysteinase", "−2.4", "0.00329", "CK, N"], ["Q9CX86", "Hnrnpa0", "Heterogeneous nuclear ribonucleoprotein A0", "−2.4", "0.00165", "N"], ["Q9Z1B3", "Plcb1", "1-phosphatidylinositol 4,5-bisphosphate phosphodiesterase beta-1", "−2.4", "0.00671", "CK, N, PM"], ["O54991", "Cntnap1", "Contactin-associated protein 1", "−2.3", "0.00626", "PM"], ["B0V2P5", "Dmxl2", "DmX-like protein 2", "−2.3", "0.01109", "PM"], ["E9Q8N8", "Slc4a4", "Anion exchange protein", "−2.3", "0.0011", "PM"], ["B1AQX9", "Srcin1", "SRC kinase-signaling inhibitor 1", "−2.3", "0.0004", "CK"], ["P24472", "Gsta4", "Glutathione S-transferase A4", "−2.3", "0.00125", "M"], ["Q3UK83", "Hnrnpa1", "Putative uncharacterized protein", "−2.2", "0.00047", "ERS, N"], ["D3Z4J3", "Myo5a", "Unconventional myosin-Va", "−2.2", "0.00636", "CK, C, ER, En, GA, Ly, Pe"], ["Q61411", "Hras", "GTPase HRas", "−2.2", "0.00583", "C, GA, N, PM"], ["Q9Z0X1", "Aifm1", "Apoptosis-inducing factor 1, mitochondrial", "−2.1", "0.00398", "CK, M, N"], ["B2L107", "Vsnl1", "Visinin-like protein 1", "−2.1", "0.00018", "C"], ["Q9DBF1", "Aldh7a", "Alpha-aminoadipic semialdehyde dehydrogenase", "−2.1", "0.02264", "C, M, N"], ["Q3TJF2", "Ola1", "Obg-like ATPase 1", "−2.1", "0.00001", "CK, C, N"], ["Q8VDD5", "Myh9", "Myosin-9", "−2", "0.01358", "C, CK, N, PM"], ["Q9JJK2", "Lancl2", "LanC-like protein 2", "−2", "0.00232", "C, CK, N, PM"], ["E9Q2L2", "Dlg2", "Disks large homolog 2", "−2", "0.00218", "PM"], ["Q91VR5", "Ddx1", "ATP-dependent RNA helicase DDX1", "−2", "0.00216", "C, M, N"], ["Q9JHU4", "Dync1h1", "Cytoplasmic dynein 1 heavy chain 1", "−2", "0.00407", "CK, N"], ["Q99PU5", "Acsbg1", "Long-chain-fatty-acid--CoA ligase ACSBG1", "−1.9", "0.01942", "ER, PM"], ["Q64010", "Crk", "Adapter molecule crk", "−1.9", "0.0031", "CK, PM"], ["P14733", "Lmnb1", "Lamin-B1", "−1.9", "0.02293", "CK, N"], ["P54775", "Psmc4", "26S protease regulatory subunit 6B", "−1.9", "0.03099", "CK, N"], ["A0A1S6GWI0", "Ndufa8", "NADH dehydrogenase (Ubiquinone) 1 alpha subcomplex, 8", "−1.8", "0.00156", "M"], ["Q3U741", "Ddx17", "DEAD (Asp-Glu-Ala-Asp) box polypeptide 17, isoform CRA_a", "−1.8", "0.00085", "C, N"], ["Q3TIQ2", "Rpl12", "Putative uncharacterized protein", "−1.8", "0.01139", "C, N"], ["P70168", "Kpnb1", "Importin subunit beta-1", "−1.7", "0.00011", "C, M, N"], ["Q80TZ3", "Dnajc6", "Putative tyrosine-protein phosphatase auxilin", "−1.7", "0.00164", "C"], ["Q5DTG0", "Atp8a1", "Phospholipid-transporting ATPase (Fragment)", "−1.7", "0.00428", "ER, GA, PM"], ["Q9QXS1", "Plec", "Plectin", "−1.7", "0.00377", "C, CK, PM"], ["Q921F2", "Tardbp", "TAR DNA-binding protein 43", "−1.7", "0.00786", "N"], ["B2RX08", "Sptb", "Spectrin beta chain", "−1.7", "0.00319", "C, CK, PM"], ["Q3TKG4", "Psmc3", "Putative uncharacterized protein (Fragment)", "−1.6", "0.00396", "N"], ["Q3UH59", "Myh10", "Myosin-10", "−1.6", "0.02527", "C, CK, PM"], ["Q9JM76", "Arpc3", "Actin-related protein 2/3 complex subunit 3", "−1.6", "0.01437", "C, N"], ["A0A1S6GWJ8", "Uncharacterized protein", "–1,5", "0.02713", ""], ["Q3UN60", "Mpp6", "Membrane protein, palmitoylated 6 (MAGUK p55 subfamily member 6), isoform CRA_b", "−1.5", "0.00085", "PM"], ["Q91XV3", "Basp1", "Brain acid soluble protein 1", "−1.5", "0.00001", "N, PM"], ["Q07076", "Anxa7", "Annexin A7", "−1.5", "0.01183", "C, ER, ERS, N, PM"], ["Q3UY05", "Ndufs8", "Putative uncharacterized protein", "−1.4", "0.00008", "M"], ["A0A0R4J0Q5", "Lmnb2", "Lamin-B2", "−1.4", "0.03275", "CK, N"], ["Q4FJX9", "Sod2", "Superoxide dismutase", "−1.4", "0.01379", "M"], ["Q91VN4", "Chchd6", "MICOS complex subunit Mic25", "−1.4", "0.01573", "C, M"], ["O88737", "Bsn", "Protein bassoon", "−1.3", "0.00915", "C, GA"], ["Q3UWW9", "Psmd11", "Putative uncharacterized protein", "−1.3", "0.01386", "C, N"], ["O08788", "Dctn1", "Dynactin subunit 1", "−1.3", "0.01243", "CK, C, ERS, N"], ["A0A0R4J275", "Ndufa12", "NADH dehydrogenase [ubiquinone] 1 alpha subcomplex subunit 12", "−1.3", "0.0197", "C, M"], ["Q63932", "Map2k2", "Dual specificity mitogen-activated protein kinase kinase 2", "−1.3", "0.01951", "CK, C, ER, En, GA, M, N, PM"], ["Q61361", "Bcan", "Brevican core protein", "−1.3", "0.01264", "ERS"], ["Q3V117", "Acly", "ATP-citrate synthase", "−1.3", "0.0078", "C, M, N, PM"], ["Q8R570", "Snap47", "Synaptosomal-associated protein 47", "−1.3", "0.00248", "C, PM"], ["Q9DCS9", "Ndufb10", "NADH dehydrogenase [ubiquinone] 1 beta subcomplex subunit 10", "−1.2", "0.01688", "M"], ["P14824", "Anxa6", "Annexin A6", "−1.2", "0.01378", "C, En, ERS, Ly, M, N, PM"], ["P54071", "Idh2", "Isocitrate dehydrogenase [NADP], mitochondrial", "−1.2", "0.00039", "C, M, Pe"], ["Q7TSJ2", "Map6", "Microtubule-associated protein 6", "−1.2", "0.00159", "CK, GA"], ["Q8BGN3", "Enpp6", "Ectonucleotide pyrophosphatase/phosphodiesterase family member 6", "−1.2", "0.03099", "ERS, PM"], ["Q9CZD3", "Gars", "Glycine--tRNA ligase", "−1.2", "0.01474", "C, ERS, M"], ["A0A0R4J083", "Acadl", "Long-chain-specific acyl-CoA dehydrogenase, mitochondrial", "−1.2", "0.03611", "M"], ["Q8CGK3", "Lonp1", "Lon protease homolog, mitochondrial", "−1.1", "0.01936", "C, M, N"], ["E9Q7Q3", "Tpm3", "Tropomyosin alpha-3 chain", "−1.1", "0.00355", "CK, C"], ["Q8BWT1", "Acaa2", "3-ketoacyl-CoA thiolase, mitochondrial", "−1.1", "0.04478", "M"], ["P61226", "Rap2b", "Ras-related protein Rap-2b", "−1.1", "0.03025", "C, En, ERS, PM"], ["Q8R5C5", "Actr1b", "Beta-centractin", "−1.1", "0.00172", "CK"], ["E9Q0J5", "Kif21a", "Kinesin-like protein KIF21A", "−1.1", "0.04345", "CK, C, PM"], ["B9EKR1", "Ptprz1", "Receptor-type tyrosine-protein phosphatase zeta", "−1.1", "0.01214", "ERS, PM"], ["Q6ZQ38", "Cand1", "Cullin-associated NEDD8-dissociated protein 1", "−1", "0.00177", "C, GA, N"], ["Q9JI91", "Actn2", "Alpha-actinin-2", "−1", "0.00286", "CK, PM"], ["P68040", "Rack1", "Receptor of activated protein C kinase 1", "−1", "0.03823", "CK, M, N, PM"], ["E9PUL5", "Prrt2", "Proline-rich transmembrane protein 2", "−1", "0.0411", "PM"], ["F6SEU4", "Syngap1", "Ras/Rap GTPase-activating protein SynGAP", "−1", "0.03268", "PM"], ["Q8CHG1", "Dclk1", "MKIAA0369 protein (Fragment)", "−1", "0.02306", "PM"], ["Q61490", "Alcam", "CD166 antigen", "−1", "0.03414", "PM"], ["D3Z656", "Synj1", "Synaptojanin-1", "−1", "0.02126", "PM"], ["H3BIV5", "Akap5", "A-kinase anchor protein 5", "−1", "0.01709", "CK, PM"], ["Q8VD37", "Sgip1", "SH3-containing GRB2-like protein 3-interacting protein 1", "−1", "0.04017", "CK, PM"], ["W6PPR4", "Ank3", "480-kDa ankyrinG", "−1", "0.00579", "CK, C, PM"], ["Q9CWS0", "Ddah1", "N(G),N(G)-dimethylarginine dimethylaminohydrolase 1", "−0.9", "0.04649", "M"], ["Q11011", "Npepps", "Puromycin-sensitive aminopeptidase", "−0.9", "0.00505", "C, N"], ["Q3TXE5", "Canx", "Putative uncharacterized protein", "−0.9", "0.00488", "ER, PM"], ["Q3UAG2", "Pgd", "6-phosphogluconate dehydrogenase, decarboxylating", "−0.9", "0.02403", "C"], ["Q99JX6", "Anxa6", "Annexin", "−0.9", "0.04313", "C, En, ERS, Ly, M, N, PM"], ["A0A0G2JEG8", "Amph", "Amphiphysin", "−0.9", "0.00912", "CK, PM"], ["Q99P72", "Rtn4", "Reticulon-4", "−0.9", "0.01061", "ER, N, PM"], ["Q49S98", "Slc32a1", "Putative uncharacterized protein", "−0.9", "0.04098", "PM"], ["B2RQQ5", "Map1b", "Microtubule-associated protein 1B", "−0.9", "0.03443", "CK, C, PM"], ["D3Z2H9", "Tpm3", "Uncharacterized protein", "−0.9", "0.02982", "CK, C"], ["Q6ZQ61", "Matr3", "MCG121979, isoform CRA_c (Fragment)", "−0.8", "0.01811", "N"], ["Q3TE45", "Sdhb", "Succinate dehydrogenase [ubiquinone] iron-sulfur subunit, mitochondrial", "−0.8", "0.01667", "M, N, PM"], ["Q0VF55", "Atp2b3", "Calcium-transporting ATPase", "−0.8", "0.03416", "PM"], ["Q3UEG9", "Flot2", "Putative uncharacterized protein", "−0.8", "0.02632", "CK, En, PM"], ["Q91V61", "Sfxn3", "Sideroflexin-3", "−0.8", "0.00937", "M"], ["P61164", "Actr1a", "Alpha-centractin", "−0.8", "0.03531", "CK"], ["Q571M2", "Hspa4", "MKIAA4025 protein (Fragment)", "−0.7", "0.00487", "C, ERS, N"], ["Q9Z2Y3", "Homer1", "Homer protein homolog 1", "−0.7", "0.01584", "C, PM"], ["E9Q455", "Tpm1", "Tropomyosin alpha-1 chain", "−0.7", "0.04225", "C"], ["A2A5Y6", "Mapt", "Microtubule-associated protein", "−0.7", "0.04838", "CK, C, N, PM"], ["A0A1S6GWH1", "Uncharacterized protein", "–0,7", "0.02404", ""], ["P35486", "Pdha1", "Pyruvate dehydrogenase E1 component subunit alpha, somatic form, mitochondrial", "−0.6", "0.00552", "M, N"], ["Q8CC13", "Ap1b1", "AP complex subunit beta", "−0.6", "0.03216", "C, GA"], ["E9Q2W9", "Actn4", "Alpha-actinin-4 (Fragment)", "−0.6", "0.00847", "CK, C, N"], ["Q8BVE3", "Atp6v1h", "V-type proton ATPase subunit H", "−0.6", "0.02175", "C, Ly"], ["A0A0A6YY91", "Ncam1", "Neural cell adhesion molecule 1 (Fragment)", "−0.6", "0.0182", "CK, PM"], ["Q3TYK4", "Prkar1a", "Putative uncharacterized protein", "−0.6", "0.01177", "CK, C, PM"], ["P12960", "Cntn1", "Contactin-1", "−0.6", "0.02931", "PM"], ["Q3TPZ5", "Dctn2", "Dynactin 2", "−0.6", "0.00054", "CK, C"], ["A0A1L1SV25", "Actn4", "Alpha-actinin-4", "−0.6", "0.0286", "CK, C, N"], ["P19246", "Nefh", "Neurofilament heavy polypeptide", "−0.5", "0.04106", "CK, M, N, PM"], ["A0A0R4J117", "Igsf8", "Immunoglobulin superfamily member 8", "−0.5", "0.04908", "PM"], ["Q68FG2", "Sptbn2", "Spectrin beta chain", "−0.5", "0.04372", "CK, C, ER, En, GA"], ["Q80YU5", "Mog", "Myelin oligodendrocyte glycoprotein (Fragment)", "−0.5", "0.02477", "C, ER, M, PM"], ["E9QB01", "Ncam1", "Neural cell adhesion molecule 1", "−0.5", "0.03648", "C, PM"], ["Q01853", "Vcp", "Transitional endoplasmic reticulum ATPase", "−0.5", "0.03249", "C, ER, N"], ["P09041", "Pgk2", "Phosphoglycerate kinase 2", "−0.4", "0.03696", "C"], ["Q7TPR4", "Actn1", "Alpha-actinin-1", "−0.4", "0.01557", "CK, N, PM"], ["P63011", "Rab3a", "Ras-related protein Rab-3A", "−0.4", "0.0162", "C, En, Ly, PM"], ["P09411", "Pgk1", "Phosphoglycerate kinase 1", "−0.3", "0.01617", "C, ERS, PM"], ["O08599", "Stxbp1", "Syntaxin-binding protein 1", "0.1", "0.03134", "CK, C, M, PM"], ["A0A0A0MQA5", "Tuba4a", "Tubulin alpha chain (Fragment)", "0.2", "0.01472", "CK"], ["P68369", "Tuba1a", "Tubulin alpha-1A chain", "0.2", "0.02299", "CK, En"], ["Q52L87", "Tuba1c", "Tubulin alpha chain", "0.3", "0.0146", "CK, N"], ["P50396", "Gdi1", "Rab GDP dissociation inhibitor alpha", "0.3", "0.03464", "GA"], ["P60710", "Actb", "Actin, cytoplasmic 1", "0.3", "0.02793", "CK, C, N, PM"], ["Q9CZU6", "Cs", "Citrate synthase, mitochondrial", "0.3", "0.00075", "M"], ["P05202", "Got2", "Aspartate aminotransferase, mitochondrial", "0.3", "0.03387", "M, PM"], ["P63038", "Hspd1", "60 kDa heat shock protein, mitochondrial", "0.3", "0.02215", "CK, ER, En, ERS, GA, M, PM"], ["E9Q912", "Rap1gds1", "RAP1, GTP-GDP dissociation stimulator 1", "0.3", "0.00467", "CK, ER, M"], ["B2CSK2", "", "Heat shock protein 1-like protein", "0.3", "0.00172", ""], ["O88935", "Syn1", "Synapsin-1", "0.3", "0.03624", "CK, C, GA, N"], ["P68033", "Actc1", "Actin, alpha cardiac muscle 1", "0.3", "0.00986", "CK"], ["P08249", "Mdh2", "Malate dehydrogenase, mitochondrial", "0.3", "0.00731", "M"], ["Q03265", "Atp5a1", "ATP synthase subunit alpha, mitochondrial", "0.3", "0.00169", "M, N, PM"], ["Q99KI0", "Aco2", "Aconitate hydratase, mitochondrial", "0.3", "0.00087", "C, M"], ["P17879", "Hspa1b", "Heat shock 70 kDa protein 1B", "0.4", "0.00362", "CK, C, M, N, PM"], ["O08553", "Dpysl2", "Dihydropyrimidinase-related protein 2", "0.4", "0.00004", "CK, C, M, PM"], ["Q5FW97", "EG433182", "Enolase 1, alpha non-neuron", "0.4", "0.00346", "C"], ["Q64332", "Syn2", "Synapsin-2", "0.4", "0.01708", "PM"], ["Q3TQ70", "Gnb1", "Beta1 subnuit of GTP-binding protein", "0.4", "0.01897", "PM"], ["P62631", "Eef1a2", "Elongation factor 1-alpha 2", "0.4", "0.00011", "N"], ["P80316", "Cct5", "T-complex protein 1 subunit epsilon", "0.4", "0.04942", "CK, C"], ["Q8CE19", "Syn2", "Putative uncharacterized protein", "0.4", "0.02198", "PM"], ["Q3UA81", "Eef1a1", "Elongation factor 1-alpha", "0.4", "0.00003", "CK, C, M, PM"], ["Q8C2Q7", "Hnrnph1", "Heterogeneous nuclear ribonucleoprotein H", "0.4", "0.01261", "C, N"], ["Q9D6F9", "Tubb4a", "Tubulin beta-4A chain", "0.4", "0.00031", "CK"], ["P17751", "Tpi1", "Triosephosphate isomerase", "0.4", "0.00008", "C"], ["P48774", "Gstm5", "Glutathione S-transferase Mu 5", "0.4", "0.01045", "C, ERS"], ["P18872", "Gnao1", "Guanine nucleotide-binding protein G(o) subunit alpha", "0.4", "0.00334", "PM"], ["Q3UYK6", "Slc1a2", "Amino acid transporter", "0.4", "0.03711", "PM"], ["Q8BVI4", "Qdpr", "Dihydropteridine reductase", "0.4", "0.02048", "C, M"], ["Q9D2G2", "Dlst", "Dihydrolipoyllysine-residue succinyltransferase component of 2-oxoglutarate dehydrogenase complex, mitochondrial", "0.4", "0.00639", "M, N, PM"], ["Q3UD06", "Atp5c1", "ATP synthase subunit gamma", "0.4", "0.00728", "M"], ["P68372", "Tubb4b", "Tubulin beta-4B chain", "0.4", "0.00008", "CK"], ["P99024", "Tubb5", "Tubulin beta-5 chain", "0.4", "0.00005", "CK, C, M"], ["P56480", "Atp5b", "ATP synthase subunit beta, mitochondrial", "0.4", "0.00166", "M, PM"], ["E9QKR0", "Gnb2", "Guanine nucleotide-binding protein G(I)/G(S)/G(T) subunit beta-2", "0.4", "0.0162", "PM"], ["B2RSN3", "Tubb2b", "Tubulin beta chain", "0.4", "0.00013", "CK"], ["Q7TMM9", "Tubb2a", "Tubulin beta-2A chain", "0.4", "0.0001", "CK"], ["P63017", "Hspa8", "Heat shock cognate 71 kDa protein", "0.4", "0.0001", "CK, C, En, ERS, Ly, N, PM"], ["Q3TIC8", "Uqcrc1", "Putative uncharacterized protein", "0.4", "0.00014", "C, M"], ["P26443", "Glud1", "Glutamate dehydrogenase 1, mitochondrial", "0.4", "0.00008", "M"], ["Q3TYV5", "Cnp", "2′,3′-cyclic-nucleotide 3′-phosphodiesterase", "0.5", "0.00001", "ERS"], ["B7U582", "", "Heat shock protein 70-2", "0.5", "0.00001", ""], ["Q8BH95", "Echs1", "Enoyl-CoA hydratase, mitochondrial", "0.5", "0.03689", "M"], ["Q6P1J1", "Crmp1", "Crmp1 protein", "0.5", "0.00045", "CK, C, N"], ["B2CY77", "Rpsa", "Laminin receptor (Fragment)", "0.5", "0.01872", "C, ERS, N, PM"], ["Q922F4", "Tubb6", "Tubulin beta-6 chain", "0.5", "0.00002", "CK"], ["Q9ERD7", "Tubb3", "Tubulin beta-3 chain", "0.5", "0.00003", "CK"], ["Q60930", "Vdac2", "Voltage-dependent anion-selective channel protein 2", "0.5", "0.00247", "M"], ["P14152", "Mdh1", "Malate dehydrogenase, cytoplasmic", "0.5", "0.00092", "C, M"], ["A6ZI44", "Aldoa", "Fructose-bisphosphate aldolase", "0.5", "0.00156", "CK, C, ERS, M, N, PM"], ["Q80X68", "Csl", "Citrate synthase", "0.5", "0.00001", "N"], ["A2AQ07", "Tubb1", "Tubulin beta-1 chain", "0.5", "0.00009", "CK"], ["P01831", "Thy1", "Thy-1 membrane glycoprotein", "0.6", "0.00272", "C, ER, PM"], ["A0A1S6GWG6", "Uncharacterized protein", "0,6", "0.00144", ""], ["Q3UBZ3", "Capza2", "Putative uncharacterized protein", "0.6", "0.03767", "CK"], ["Q9D6M3", "Slc25a22", "Mitochondrial glutamate carrier 1", "0.6", "0.02851", "M"], ["O08749", "Dld", "Dihydrolipoyl dehydrogenase, mitochondrial", "0.6", "0.00293", "M, N"], ["Q91VA7", "Idh3b", "Isocitrate dehydrogenase [NAD] subunit, mitochondrial", "0.6", "0.0105", "M"], ["O88712", "Ctbp1", "C-terminal-binding protein 1", "0.6", "0.00177", "N"], ["Q8C3L6", "Atp6v1b1", "Putative uncharacterized protein", "0.6", "0.04137", "PM"], ["P70333", "Hnrnph2", "Heterogeneous nuclear ribonucleoprotein H2", "0.6", "0.00158", "N"], ["P14094", "Atp1b1", "Sodium/potassium-transporting ATPase subunit beta-1", "0.7", "0.00001", "PM"], ["O55100", "Syngr1", "Synaptogyrin-1", "0.7", "0.03643", "PM"], ["Q9R0P9", "Uchl1", "Ubiquitin carboxyl-terminal hydrolase isozyme L1", "0.7", "0.00142", "C, ER, PM"], ["P05063", "Aldoc", "Fructose-bisphosphate aldolase C", "0.7", "0.00002", "C, M"], ["Q61990", "Pcbp2", "Poly(rC)-binding protein 2", "0.8", "0.03331", "C, N"], ["Q8R464", "Cadm4", "Cell adhesion molecule 4", "0.8", "0.01837", "PM"], ["P21279", "Gnaq", "Guanine nucleotide-binding protein G(q) subunit alpha", "0.9", "0.04159", "C, N, PM"], ["Q00898", "Serpina1", "Alpha-1-antitrypsin 1-5", "1.2", "0.04259", "ER, ERS, GA"], ["P63330", "Ppp2ca", "Serine/threonine-protein phosphatase 2A catalytic subunit alpha isoform", "1.4", "0.00163", "CK, C, N, PM"], ["P03995", "Gfap", "Glial fibrillary acidic protein", "1.4", "0.00001", "CK, Ly"]], "row_count": 205, "column_count": 6, "numeric_cells": 653, "header_rows": 1, "locator": "section[12]/table-wrap[1]#biomolecules-10-00355-t001"}}, {"id": "asset:table:pmid:32111039:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:de43767742063922c0004fc46ba280c76acad04aa94ab39fc90ca44db5f8f3f5", "bytes": 4956, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#biomolecules-10-00355-t002", "version": null, "note": "REACTOME pathway classification of murine NAGLU−/− brain tissue proteome.", "structure": {"pmcid": "PMC7175334", "section_index": 13, "section_title": "3.3. Bioinformatic Analysis of Differentially Abundant Proteins", "row_count": 56, "column_count": 4}, "table": {"label": "Table 2", "caption": "REACTOME pathway classification of murine NAGLU−/− brain tissue proteome.", "rows": [["REACTOME Pathways", "Mus musculus REFLIST", "Client Input", "Client Input (Raw p-Value)"], ["Microtubule-dependent trafficking of connexons from Golgi to the plasma membrane (R-MMU-190840)", "14", "7", "1.45 × 10−11"], ["Citric acid cycle (TCA cycle) (R-MMU-71403)", "22", "8", "3.68 × 10−12"], ["RHO GTPases activate IQGAPs (R-MMU-5626467)", "25", "8", "8.61 × 10−12"], ["Carboxyterminal post-translational modifications of tubulin (R-MMU-8955332)", "25", "7", "4.00 × 10−10"], ["Recycling pathway of L1 (R-MMU-437239)", "34", "9", "1.74 × 10−12"], ["Lysine catabolism (R-MMU-71064)", "12", "3", "7.16 × 10−05"], ["HSP90 chaperone cycle for steroid hormone receptors (SHR) (R-MMU-3371497)", "51", "12", "1.00 × 10−15"], ["COPI-independent Golgi-to-ER retrograde traffic (R-MMU-6811436)", "47", "10", "6.42 × 10−13"], ["Gluconeogenesis (R-MMU-70263)", "35", "7", "3.07 × 10−09"], ["Serotonin Neurotransmitter Release Cycle (R-MMU-181429)", "17", "3", "1.76 × 10−04"], ["Pyruvate metabolism and Citric Acid (TCA) cycle (R-MMU-71406)", "51", "9", "4.21 × 10−11"], ["GABA synthesis, release, reuptake and degradation (R-MMU-888590)", "19", "3", "2.35 × 10−04"], ["Dopamine Neurotransmitter Release Cycle (R-MMU-212676)", "22", "3", "3.47 × 10−04"], ["Glyoxylate metabolism and glycine degradation (R-MMU-389661)", "30", "4", "3.64 × 10−05"], ["Kinesins (R-MMU-983189)", "54", "7", "4.54 × 10−08"], ["Intraflagellar transport (R-MMU-5620924)", "54", "7", "4.54 × 10−08"], ["Recruitment of NuMA to mitotic centrosomes (R-MMU-380320)", "86", "11", "6.28 × 10−12"], ["RAF activation (R-MMU-5673000)", "25", "3", "4.89 × 10−04"], ["COPI-mediated anterograde transport (R-MMU-6807878)", "98", "11", "2.29 × 10−11"], ["The role of GTSE1 in G2/M progression after G2 checkpoint (R-MMU-8852276)", "72", "8", "1.45 × 10−08"], ["Loss of Nlp from mitotic centrosomes (R-MMU-380259)", "67", "7", "1.77 × 10−07"], ["AURKA Activation by TPX2 (R-MMU-8854518)", "70", "7", "2.33 × 10−07"], ["MHC class II antigen presentation (R-MMU-2132295)", "120", "12", "9.50 × 10−12"], ["Recruitment of mitotic centrosome proteins and complexes (R-MMU-380270)", "76", "7", "3.91 × 10−07"], ["Regulation of PLK1 Activity at G2/M Transition (R-MMU-2565942)", "85", "7", "7.92 × 10−07"], ["Hedgehog “on” state (R-MMU-5632684)", "103", "8", "1.91 × 10−07"], ["ER to Golgi Anterograde Transport (R-MMU-199977)", "155", "12", "1.52 × 10−10"], ["COPI-dependent Golgi-to-ER retrograde traffic (R-MMU-6811434)", "92", "7", "1.30 × 10−06"], ["Anchoring of the basal body to the plasma membrane (R-MMU-5620912)", "93", "7", "1.40 × 10−06"], ["RHO GTPases Activate Formins (R-MMU-5663220)", "133", "10", "7.13 × 10−09"], ["Resolution of Sister Chromatid Cohesion (R-MMU-2500257)", "121", "9", "4.53 × 10−08"], ["Hedgehog “off” state (R-MMU-5610787)", "109", "8", "2.87 × 10−07"], ["Glycolysis (R-MMU-70171)", "63", "4", "5.22 × 10−04"], ["Separation of Sister Chromatids (R-MMU-2467813)", "185", "10", "1.36 × 10−07"], ["Mitotic Anaphase (R-MMU-68882)", "188", "10", "1.57 × 10−07"], ["Neutrophil degranulation (R-MMU-6798695)", "553", "14", "3.17 × 10−06"], ["Microtubule-dependent trafficking of connexons from Golgi to the plasma membrane (R-MMU-190840)", "14", "7", "1.45 × 10−11"], ["Citric acid cycle (TCA cycle) (R-MMU-71403)", "22", "8", "3.68 × 10−12"], ["RHO GTPases activate IQGAPs (R-MMU-5626467)", "25", "8", "8.61 × 10−12"], ["Carboxyterminal post-translational modifications of tubulin (R-MMU-8955332)", "25", "7", "4.00 × 10−10"], ["Recycling pathway of L1 (R-MMU-437239)", "34", "9", "1.74 × 10−12"], ["Lysine catabolism (R-MMU-71064)", "12", "3", "7.16 × 10−05"], ["Fatty Acids bound to GPR40 (FFAR1) regulate insulin secretion (R-MMU-434316)", "8", "2", "1.33 × 10−03"], ["HSP90 chaperone cycle for steroid hormone receptors (SHR) (R-MMU-3371497)", "51", "12", "1.00 × 10−15"], ["COPI-independent Golgi-to-ER retrograde traffic (R-MMU-6811436)", "47", "10", "6.42 × 10−13"], ["Gluconeogenesis (R-MMU-70263)", "35", "7", "3.07 × 10−09"], ["Serotonin Neurotransmitter Release Cycle (R-MMU-181429)", "17", "3", "1.76 × 10−04"], ["Pyruvate metabolism and Citric Acid (TCA) cycle (R-MMU-71406)", "51", "9", "4.21 × 10−11"], ["GABA synthesis, release, reuptake and degradation (R-MMU-888590)", "19", "3", "2.35 × 10−04"], ["Dopamine Neurotransmitter Release Cycle (R-MMU-212676)", "22", "3", "3.47 × 10−04"], ["Glyoxylate metabolism and glycine degradation (R-MMU-389661)", "30", "4", "3.64 × 10−05"], ["Kinesins (R-MMU-983189)", "54", "7", "4.54 × 10−08"], ["Intraflagellar transport (R-MMU-5620924)", "54", "7", "4.54 × 10−08"], ["Recruitment of NuMA to mitotic centrosomes (R-MMU-380320)", "86", "11", "6.28 × 10−12"], ["RAF activation (R-MMU-5673000)", "25", "3", "4.89 × 10−04"]], "row_count": 56, "column_count": 4, "numeric_cells": 220, "header_rows": 1, "locator": "section[13]/table-wrap[1]#biomolecules-10-00355-t002"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-2", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "linear regression"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-4", "family": null, "specific": null, "label": "Two-tailed Student’s t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A Student’s t test was used to select proteins showing significant changes between the analyzed datasets, resulting in two-tailed p values."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Data are available via ProteomeXchange with the identifier PXD017363."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:32111039", "asset:table:pmid:32111039:1", "asset:table:pmid:32111039:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:57:45Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 56140, "completion_tokens": 1008, "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:32111039", "type": "paper", "label": "pmid:32111039"}, {"id": "source:pmid:32111039", "type": "manuscript", "label": "PMID 32111039 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32111039", "type": "paper", "label": "pmid:32111039"}, {"id": "source:pmid:32111039", "type": "manuscript", "label": "PMID 32111039 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32111039", "type": "extraction", "used": ["source:pmid:32111039"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:32111039", "parent_hash": "sha256:472d7be1242cc725b01e6b201dc508576b943fc1bb6538213dba810f26e7b42d", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": ["eomic Analysis of Mucopolysaccharidosis IIIB Mouse Brain.", "resented and 74 over-represented in MPS IIIB mouse brains compared to wild type (WT). Multiple", "metabolism. The proteome profile of NAGLU-/- mouse brain could pave the way for further studies", "the C57/BL6 background [30]. NAGLU−/− and WT mice were genotyped by PCR [31]. Mice were housed with"], "order_basis": "paper_text_order:4", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["P03995) differential abundance was proved by Western blotting analysis using an independent set of brain s", "een NAGLU−/− and WT. Supplemental Figure S4: Western blotting of GFAP protein levels in NAGLU−/− and WT br"], "order_basis": "paper_text_order:7707", "id": "assay:2"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["PCA"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:47:31+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}}}