{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:24349763", "kind": "science-record", "revision": 5, "content_hash": "sha256:624676cf27212ed789a32fb3b7b53ee2f9db54431d4e3032123109d360247195", "created_at": "2026-11-01T15:40:04Z", "updated_at": "2026-11-01T21:19:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Systems Biology Profiling of AMD on the Basis of Gene Expression.", "doi": "10.1155/2013/453934", "pmid": "24349763", "authors": ["Mones S Abu-Asab", "Jose Salazar", "Jingsheng Tuo", "Chi-Chao Chan"], "journal": "Journal of ophthalmology", "year": 2013, "abstract": "Genetic pathways underlying the initiation and progression of age-related macular degeneration (AMD) have not been yet sufficiently revealed, and the correlations of AMD's genotypes, phenotypes, and disease spectrum are still awaiting resolution. We are tackling both problems with systems biology phylogenetic parsimony analysis. Gene expression data (GSE29801: NCBI, Geo) of macular and extramacular specimens of the retinas and retinal pigment epithelium (RPE) choroid complexes representing dry AMD without geographic atrophy (GA), choroidal neovascularization (CNV), GA, as well as pre-AMD and subclinical pre-AMD were polarized against their respective normal specimens and then processed through the parsimony program MIX to produce phylogenetic cladograms. Gene lists from cladograms' nodes were processed in Genomatix GePS to reveal the affected signaling pathway networks. Cladograms exposed a highly heterogeneous transcriptomic profiles within all the conventional phenotypes. Moreover, clades and nodal synapomorphies did not support the classical AMD phenotypes as valid transcriptomal genotypes. Gene lists defined by cladogram nodes showed that the AMD-related deregulations occurring in the neural retina were different from those in RPE-choroidal tissue. Our analysis suggests a more complex transcriptional profile of the phenotypes than expected. Evaluation of the disease in much earlier stages is needed to elucidate the initial events of AMD.", "claims": [{"id": "claim-data-access", "statement": "Dataset GSE29801 was downloaded from Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24349763", "locator": "sections[2] \"2. Materials and Methods\" paragraph 3", "quote": "Dataset GSE29801 was downloaded from Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper used systems biology phylogenetic parsimony analysis with the MIX program to analyze gene-expression data obtained from GSE29801 at NCBI GEO, revealing heterogeneous transcriptomic profiles that did not support the classical AMD phenotypes as transcriptomal genotypes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:24349763", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Gene expression data (GSE29801: NCBI, Geo) of macular and extramacular specimens of the retinas and retinal pigment epithelium (RPE) choroid complexes representing dry AMD without geographic atrophy (GA), choroidal neovascularization (CNV), GA, as well as pre-AMD and subclinical pre-AMD were polarized against their respective normal specimens and then processed through the parsimony program MIX to produce phylogenetic cladograms."}, {"asset": "source:pmid:24349763", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Cladograms exposed a highly heterogeneous transcriptomic profiles within all the conventional phenotypes."}, {"asset": "source:pmid:24349763", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Moreover, clades and nodal synapomorphies did not support the classical AMD phenotypes as valid transcriptomal genotypes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper used systems biology phylogenetic parsimony analysis with the MIX program to analyze gene-expression data obtained from GSE29801 at NCBI GEO, revealing heterogeneous transcriptomic profiles that did not support the classical AMD phenotypes as transcriptomal genotypes.", "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:24349763"], "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:GSE29801"], "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:GSE29801"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:24349763", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2013/453934", "sha256": "sha256:0ea42bb648d6c5724c6ba8033c65384a8efdd649d92d814321387afcbfd56590", "bytes": 23595, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2013/453934", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3851728", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE29801", "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=GSE29801", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29801", "version": null, "note": "Dataset GSE29801 was downloaded from Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset GSE29801 was downloaded from Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM738433", "GSM738434", "GSM738435", "GSM738436", "GSM738437", "GSM738438", "GSM738439", "GSM738440", "GSM738441", "GSM738442", "GSM738443", "GSM738444", "GSM738445", "GSM738446", "GSM738447", "GSM738448", "GSM738449", "GSM738450", "GSM738451", "GSM738452", "GSM738453", "GSM738454", "GSM738455", "GSM738456", "GSM738457", "GSM738458", "GSM738459", "GSM738460", "GSM738461", "GSM738462", "GSM738463", "GSM738464", "GSM738465", "GSM738466", "GSM738467", "GSM738468", "GSM738469", "GSM738470", "GSM738471", "GSM738472", "GSM738473", "GSM738474", "GSM738475", "GSM738476", "GSM738477", "GSM738478", "GSM738479", "GSM738480", "GSM738481", "GSM738482", "GSM738483", "GSM738484", "GSM738485", "GSM738486", "GSM738487", "GSM738488", "GSM738489", "GSM738490", "GSM738491", "GSM738492", "GSM738493", "GSM738494", "GSM738495", "GSM738496", "GSM738497", "GSM738498", "GSM738499", "GSM738500", "GSM738501", "GSM738502", "GSM738503", "GSM738504", "GSM738505", "GSM738506", "GSM738507", "GSM738508", "GSM738509", "GSM738510", "GSM738511", "GSM738512", "GSM738513", "GSM738514", "GSM738515", "GSM738516", "GSM738517", "GSM738518", "GSM738519", "GSM738520", "GSM738521", "GSM738522", "GSM738523", "GSM738524", "GSM738525", "GSM738526", "GSM738527", "GSM738528", "GSM738529", "GSM738530", "GSM738531", "GSM738532", "GSM738533", "GSM738534", "GSM738535", "GSM738536", "GSM738537", "GSM738538", "GSM738539", "GSM738540", "GSM738541", "GSM738542", "GSM738543", "GSM738544", "GSM738545", "GSM738546", "GSM738547", "GSM738548", "GSM738549", "GSM738550", "GSM738551", "GSM738552", "GSM738553", "GSM738554", "GSM738555", "GSM738556", "GSM738557", "GSM738558", "GSM738559", "GSM738560", "GSM738561", "GSM738562", "GSM738563", "GSM738564", "GSM738565", "GSM738566", "GSM738567", "GSM738568", "GSM738569", "GSM738570", "GSM738571", "GSM738572", "GSM738573", "GSM738574", "GSM738575", "GSM738576", "GSM738577", "GSM738578", "GSM738579", "GSM738580", "GSM738581", "GSM738582", "GSM738583", "GSM738584", "GSM738585", "GSM738586", "GSM738587", "GSM738588", "GSM738589", "GSM738590", "GSM738591", "GSM738592", "GSM738593", "GSM738594", "GSM738595", "GSM738596", "GSM738597", "GSM738598", "GSM738599", "GSM738600", "GSM738601", "GSM738602", "GSM738603", "GSM738604", "GSM738605", "GSM738606", "GSM738607", "GSM738608", "GSM738609", "GSM738610", "GSM738611", "GSM738612", "GSM738613", "GSM738614", "GSM738615", "GSM738616", "GSM738617", "GSM738618", "GSM738619", "GSM738620", "GSM738621", "GSM738622", "GSM738623", "GSM738624", "GSM738625", "GSM738626", "GSM738627", "GSM738628", "GSM738629", "GSM738630", "GSM738631", "GSM738632", "GSM738633", "GSM738634", "GSM738635", "GSM738636", "GSM738637", "GSM738638", "GSM738639", "GSM738640", "GSM738641", "GSM738642", "GSM738643", "GSM738644", "GSM738645", "GSM738646", "GSM738647", "GSM738648", "GSM738649", "GSM738650", "GSM738651", "GSM738652", "GSM738653", "GSM738654", "GSM738655", "GSM738656", "GSM738657", "GSM738658", "GSM738659", "GSM738660", "GSM738661", "GSM738662", "GSM738663", "GSM738664", "GSM738665", "GSM738666", "GSM738667", "GSM738668", "GSM738669", "GSM738670", "GSM738671", "GSM738672", "GSM738673", "GSM738674", "GSM738675", "GSM738676", "GSM738677", "GSM738678", "GSM738679", "GSM738680", "GSM738681", "GSM738682", "GSM738683", "GSM738684", "GSM738685", "GSM738686", "GSM738687", "GSM738688", "GSM738689", "GSM738690", "GSM738691", "GSM738692", "GSM738693", "GSM738694", "GSM738695", "GSM738696", "GSM738697", "GSM738698", "GSM738699", "GSM738700", "GSM738701", "GSM738702", "GSM738703", "GSM738704", "GSM738705", "GSM738706", "GSM738707", "GSM738708", "GSM738709", "GSM738710", "GSM738711", "GSM738712", "GSM738713", "GSM738714", "GSM738715", "GSM738716", "GSM738717", "GSM738718", "GSM738719", "GSM738720", "GSM738721", "GSM738722", "GSM738723", "GSM738724", "GSM738725"], "sample_count": 293, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "Systems-level analysis of age-related macular degeneration reveals global and subtype-specific functional pathways", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:24349763:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:168dd896a308884d05d7220f78d25a5ddf2766cc7b4f84eab960f9f5c22f7073", "bytes": 1040, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#tab1", "version": null, "note": "Description of AMD phenotypic subtypes according to Newman et al. [1]. Abbreviated names in the first column are used in labeling the cladograms' legends in Figures 1 and 2.", "structure": {"pmcid": "PMC3851728", "section_index": 1, "section_title": "1. Introduction", "row_count": 12, "column_count": 3}, "table": {"label": "Table 1", "caption": "Description of AMD phenotypic subtypes according to Newman et al. [1]. Abbreviated names in the first column are used in labeling the cladograms' legends in Figures 1 and 2.", "rows": [["AMD phenotype", "Alternative name", "Description"], ["MD1", "Pre-AMD", "Hard macular drusen (<63 μm) only"], [""], ["MD2", "Subclinicalpre-AMD", "Soft, distinct macular drusen (>63 μm)Macular pigmentary irregularities without soft drusen"], [""], ["Dry AMD", "Dry AMD(non-GA)", "Soft, indistinct (>125 μm) or reticular macular drusenSoft distinct macular drusen (>63 μm) with pigmentary changes Soft indistinct macular drusen with pigmentary changes"], [""], ["GA", "Geographic atrophy", "Sharply demarcated area of apparent absence of the RPE (>175 μm) involving central macular region"], [""], ["CNV", "Wet AMD", "Subretinal choroidal neovascularization"], [""], ["GA/CNV", "", "Geographic atrophy with choroidal neovascularization"]], "row_count": 12, "column_count": 3, "numeric_cells": 4, "header_rows": 1, "locator": "section[1]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:24349763:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:314d460860ef4fc913449435495ebcf55a123fd0e79c61c6fbdf52f7c1e62e97", "bytes": 871, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tab2", "version": null, "note": "The study collection's clinical phenotypes and the number of their specimens. Data source: GSE29801 at Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801).", "structure": {"pmcid": "PMC3851728", "section_index": 2, "section_title": "2. Materials and Methods", "row_count": 24, "column_count": 3}, "table": {"label": "Table 2", "caption": "The study collection's clinical phenotypes and the number of their specimens. Data source: GSE29801 at Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801).", "rows": [["Dx", "Retina"], ["Macular", "Extramacular"], ["Normal (n = 55)", "28", "27"], [""], ["Pre-AMD (n = 13)", "MD1 = 4", "MD1 = 4"], ["MD2 = 3", "MD2 = 2"], [""], ["AMD (n = 47)", "Dry = 15", "Dry = 16"], ["CNV = 5", "CNV = 4"], ["GA = 1", "GA = 1"], ["GA/CNV = 3", "GA/CNV = 2"], [""], ["", "RPE-choroid"], [""], ["Normal (n = 96)", "48", "48"], [""], ["Pre-AMD (n = 21)", "MD1 = 6", "MD1 = 5"], ["MD2 = 4", "MD2 = 4"], [""], ["AMD (n = 60)", "Dry = 15", "Dry = 15"], ["CNV = 5", "CNV = 5"], ["GA = 2", "GA = 2"], ["GA/CNV = 2", "GA/CNV = 2"], ["Undetermined = 6", "Undetermined = 6"]], "row_count": 24, "column_count": 3, "numeric_cells": 36, "header_rows": 2, "locator": "section[2]/table-wrap[1]#tab2"}}, {"id": "asset:table:pmid:24349763:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a296da508869b83b313f59e13335f0cd40237fb57d73817aec330172ff51938e", "bytes": 1222, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tab3", "version": null, "note": "Affected retinal signaling pathways at different locations of cladogram in Figure 1. Sample identification follows http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801.", "structure": {"pmcid": "PMC3851728", "section_index": 3, "section_title": "3. Results", "row_count": 2, "column_count": 4}, "table": {"label": "Table 3", "caption": "Affected retinal signaling pathways at different locations of cladogram in Figure 1. Sample identification follows http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801.", "rows": [["First nodeShared by all retinal specimens", "RetMD1-106(Sample GSM738713)Lower part of the cladogram", "Specimen: RetDRY98(Sample GSM738705)Middle part of the cladogram", "Specimen: RetDRY70(Sample GSM738677)Upper part of the cladogram"], ["(1) Apoptosis(2) Cell cycle(3) Cytoskeleton(4) Differentiation(5) Growth(6) Insulin metabolism", "(1) Apoptosis(2) Cell cycle(3) Development(4) Growth(5) Neurotransmission(6) Transcription activation(7) Tumor suppression", "(1) Cytokine receptor degradation signaling(2) Cytosolic calcium ion concentration elevation (through IP3 receptor) (GPCR signaling (G alpha q))(3) EGFR1(4) ERK cascade GPCR signaling (G alpha s, PKA, and ERK)(5) Protein binding(6) Proteolysis", "(1) Amyloid metabolism(2) Apoptosis(3) Cell cycle(4) Cytoskeleton(5) Immunoregulation(6) Inflammation(7) Lipid metabolism(8) Retinoid metabolism(9) Ribosomal proteins(10) Telomere metabolism"]], "row_count": 2, "column_count": 4, "numeric_cells": 7, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tab3"}}, {"id": "asset:table:pmid:24349763:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:18dfff90f543722a1a1c808a0fe07e33aaafd932722d7961fc6c3704e50676d1", "bytes": 1704, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#tab4", "version": null, "note": "Affected RPE-choroidal signaling pathways at different locations of cladogram in Figure 2. Sample identification follows http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801. Updates on genes' functions can be obtained from http://www.ncbi.nlm.nih.gov/gene/.", "structure": {"pmcid": "PMC3851728", "section_index": 3, "section_title": "3. Results", "row_count": 2, "column_count": 3}, "table": {"label": "Table 4", "caption": "Affected RPE-choroidal signaling pathways at different locations of cladogram in Figure 2. Sample identification follows http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801. Updates on genes' functions can be obtained from http://www.ncbi.nlm.nih.gov/gene/.", "rows": [["Dry 135(Sample GSM738566)Lower part of the cladogram", "Dry 145(Sample GSM738575)Middle part of the cladogram", "Dry 136(Sample GSM738567)Upper part of the cladogram"], ["(1) CXCL12: activates lymphocytes(2) GDNF: promotes the survival and differentiation of dopaminergic neurons(3) MAPK1: proliferation, differentiation, transcription regulation, and development(4) PIK3CA: oncogenic(5) SFRP1: soluble modulator of Wnt signaling(6) SOD1 superoxide dismutase 1", "(1) ABL1 protooncogene implicated in cell differentiation, division, adhesion, and stress response(2) CAV1: cell cycle(3) CCL20: inflammation(4) CREB1: a transcription factor, cAMP pathway(5) CRY2: insulin metabolism(6) ERCC1: DNA repair(7) ESR1: hormone binding, DNA binding, and activation of transcription(8) IL8: inflammatory response(9) INS: insulin(10) MSN: cytoskeleton(11) MT1A: cytoskeleton, and so forth(12) PML: tumor suppressor(13) SERPINE1: inhibitor of fibrinolysis(14) TBP: assembly of transcription complex, and acts as a channel for regulatory signals(15) TMSB4X: cytoskeleton, proliferation, migration, and differentiation", "(1) CAV1: cell cycle(2) CCL5: inflammation(3) CXCL12: activates lymphocytes(4) EGF: growth, proliferation, and differentiation(5) PPARA peroxisome proliferator-activated receptor alpha"]], "row_count": 2, "column_count": 3, "numeric_cells": 6, "header_rows": 1, "locator": "section[3]/table-wrap[2]#tab4"}}], "gaps": ["asset:data:geo:GSE29801 not downloaded", "asset:data:geo:GSE29801 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Phylogenetic parsimony analysis using the MIX parsimony program", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“Dataset GSE29801 was downloaded from Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801).” “Pre-AMD and AMD gene expression values of retinal and RPE-choroidal specimens were polarized separately against their respective normal specimens (e.g., RPE-choroid data was polarized using normal RPE-choroid specimens data), and the new polarized data matrices were processed separately through MIX [12], a parsimony program of the PHYLIP package (http://evolution.genetics.washington.edu/phylip.html) to produce phylogenetic cladograms for both datasets (for details of this process see [7, 13]).”"}}], "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": "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 (Phylogenetic parsimony analysis using the MIX parsimony program), 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": ["GSE29801"], "resolved_accessions": ["GSE29801"], "statements": ["Dataset GSE29801 was downloaded from Geo Datasets of NCBI (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE29801)."], "basis": "The paper names GSE29801 in Geo Datasets of NCBI and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:24349763", "data:geo:GSE29801", "asset:table:pmid:24349763:1", "asset:table:pmid:24349763:2", "asset:table:pmid:24349763:3", "asset:table:pmid:24349763:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE29801"]}, "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": "2026-10-31T18:21:54Z", "independence": "same_provider"}, "evidence_check": {"method": "reordered", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 45944, "completion_tokens": 3052, "cached_tokens": 28168}}, "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:24349763", "type": "paper", "label": "pmid:24349763"}, {"id": "source:pmid:24349763", "type": "manuscript", "label": "PMID 24349763 full text"}, {"id": "data:geo:GSE29801", "type": "dataset", "label": "GEO GSE29801"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:24349763", "type": "paper", "label": "pmid:24349763"}, {"id": "source:pmid:24349763", "type": "manuscript", "label": "PMID 24349763 full text"}, {"id": "data:geo:GSE29801", "type": "dataset", "label": "GEO GSE29801"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-24349763", "type": "extraction", "used": ["source:pmid:24349763"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE29801", "type": "accession_resolution", "used": ["data:geo:GSE29801"], "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:24349763", "parent_hash": "sha256:bf4381277950626d1ac4b4597209741258d611bcb707688091308336a4f3ff66", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE29801 licence not read", "asset:data:geo:GSE29801 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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":"2026-11-04T02:45:45+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}}}