{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28440393", "kind": "science-record", "revision": 9, "content_hash": "sha256:015248160744d449deae114df9778012f87a95a8b1f23c0590f32b68b3c07d5e", "created_at": "2026-11-01T15:40:25Z", "updated_at": "2026-11-01T22:42:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key genes associated with Schmid-type metaphyseal chondrodysplasia based on microarray data.", "doi": "10.3892/ijmm.2017.2954", "pmid": "28440393", "authors": ["Bing Wang", "Li He", "Wusheng Miao", "Ge Wu", "Hai Jiang", "Yongtao Wu", "Jining Qu", "Min Li"], "journal": "International journal of molecular medicine", "year": 2017, "abstract": "This study aimed to gain a better understanding of the molecular circuitry of Schmid-type metaphyseal chondrodysplasia (SMCD), and to identify more potential genes associated with the pathogenesis of SMCD. Microarray data from GSE72261 were downloaded from the NCBI GEO database, including collagen X p.Asn617Lys knock-in mutation (ColXN617K), ablated XBP1 activity (Xbp1CartΔEx2), compound mutant (C/X), and wild-type (WT) specimens. Differentially expressed genes (DEGs) were screened in Xbp1 vs. WT, Col vs. WT and CX vs. WT, respectively. Pathway enrichment analysis of these DEGs was performed. Transcription factors (TFs) of the overlapping DEGs were identified. Weighted correlation network analysis (WGCNA) was performed to find modules of DEGs with high correlations, followed by gene function analysis and a protein-protein interaction network construction. In total, 481, 1,530 and 1,214 DEGs were identified in Xbp1 vs. WT, Col vs. WT and CX vs. WT, respectively. These DEGs were enriched in different pathways, such as extracellular matrix (ECM)-receptor interaction and metabolism-related pathways. A total of 7 TFs were found to regulate 19 common upregulated genes, and 4 TFs were identified to regulate 21 common downregulated genes. Two significant gene co-expression modules were enriched and DEGs in the 2 modules were mainly enriched in different biological processes, such as ribosome biogenesis. Moreover, Kras (downregulated), Col5a1 (upregulated) and Furin (upregulated) were both identified in the regulatory networks and protein-protein interaction (PPI) network. On the whole, our findings indicate that the Kras, Col5a1 and Furin genes may play essential roles in the molecular mechanisms of SMCD, which warrants further investigation.", "claims": [{"id": "claim-method", "statement": "|log2fold change (FC)| and p-values from an unpaired t-test implemented in the limma package (15) were used to select the DEGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28440393", "locator": "sections[4] \"Screening of DEGs\" paragraph 2", "quote": "|log2fold change (FC)| and p-values from an unpaired t-test implemented in the limma package (15) were used to select the DEGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data of GSE72261, deposited by Cameron et al (11), were downloaded from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) database (http://www.nibi.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28440393", "locator": "sections[3] \"Microarray data and data preprocessing\" paragraph 2", "quote": "The microarray data of GSE72261, deposited by Cameron et al (11), were downloaded from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) database (http://www.nibi.nih.gov/geo/)."}], "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:28440393"], "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:GSE72261"], "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:GSE72261"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28440393", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ijmm.2017.2954", "sha256": "sha256:f3ea00e2958fd8a8f0afcc49e0c079fd47791f0093e97339cbfa2e09ccd22768", "bytes": 34210, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ijmm.2017.2954", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5428963", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE72261", "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=GSE72261", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE72261", "version": null, "note": "The microarray data of GSE72261, deposited by Cameron et al (11), were downloaded from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) database (http://www.nibi.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data of GSE72261, deposited by Cameron et al (11), were downloaded from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) database (http://www.nibi.nih.gov/geo/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1858964", "GSM1858965", "GSM1858966", "GSM1858967", "GSM1858968", "GSM1858969", "GSM1858970", "GSM1858971", "GSM1858972", "GSM1858973", "GSM1858974", "GSM1858975"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "6887", "taxon": "Mus musculus", "title": "Analysis of the IRE1/XBP1 unfolded protein response (UPR) pathway in Schmid metaphyseal chondrodysplasia hypertrophic chondrocyte endoplasmic reticulum (ER) stress", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28440393:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6876703acd8069b772c6ed280c59ad76d53639c40d7afce90a3dc0341c27f4ec", "bytes": 2409, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tI-ijmm-39-06-1428", "version": null, "note": "The pathways enriched in the Xbp1 group, and the top 10 pathways and top 5 pathways enriched in the Col group and CX group, respectively.", "structure": {"pmcid": "PMC5428963", "section_index": 12, "section_title": "KEGG pathway enrichment analysis of the DEGs identified", "row_count": 40, "column_count": 4}, "table": {"label": "Table I", "caption": "The pathways enriched in the Xbp1 group, and the top 10 pathways and top 5 pathways enriched in the Col group and CX group, respectively.", "rows": [["Gene change", "KEGG term", "Count", "p-value"], ["In Xbp1 group", "", "", ""], ["Upregulated", "mmu04512:ECM-receptor interaction", "8", "5.23E-04"], ["mmu04510:Focal adhesion", "11", "0.0020"], ["mmu04142:Lysosome", "8", "0.0043"], ["mmu00561:Glycerolipid metabolism", "4", "0.0468"], ["Downregulated", "mmu03010:Ribosome", "8", "2.69E-05"], ["mmu00860:Porphyrin and chlorophyll metabolism", "3", "0.0364"], ["In Col group", "", "", ""], ["Upregulated", "mmu00970:Aminoacyl-tRNA biosynthesis", "8", "0.0011"], ["mmu00051:Fructose and mannose metabolism", "7", "0.0030"], ["mmu00600:Sphingolipid metabolism", "7", "0.0057"], ["mmu00250:Alanine, aspartate and glutamate metabolism", "6", "0.00594"], ["mmu04142:Lysosome", "12", "0.0071"], ["mmu00290:Valine, leucine and isoleucine biosynthesis", "4", "0.00796"], ["mmu00510:N-Glycan biosynthesis", "7", "0.00893"], ["mmu03018:RNA degradation", "8", "0.00895"], ["mmu00480:Glutathione metabolism", "7", "0.0160"], ["mmu00010:Glycolysis/gluconeogenesis", "8", "0.0172"], ["Downregulated", "mmu04510:Focal adhesion", "24", "1.18E-05"], ["mmu04070:Phosphatidylinositol signaling system", "14", "1.55E-05"], ["mmu04142:Lysosome", "15", "5.58E-04"], ["mmu04270:Vascular smooth muscle contraction", "15", "6.08E-04"], ["mmu04512:ECM-receptor interaction", "12", "8.03E-04"], ["mmu04912:GnRH signaling pathway", "13", "8.79E-04"], ["mmu05210:Colorectal cancer", "12", "0.00108"], ["mmu04540:Gap junction", "12", "0.00108"], ["mmu05213:Endometrial cancer", "9", "0.00157"], ["mmu04670:Leukocyte transendothelial migration", "14", "0.00175"], ["In CX group", "", "", ""], ["Upregulated", "mmu00010:Glycolysis/gluconeogenesis", "9", "0.0012"], ["mmu00051:Fructose and mannose metabolism", "6", "0.0055"], ["mmu00030:Pentose phosphate pathway", "5", "0.0082"], ["mmu00520:Amino sugar and nucleotide sugar metabolism", "6", "0.0116"], ["mmu00750:Vitamin B6 metabolism", "3", "0.0135"], ["Downregulated", "mmu04670:Leukocyte transendothelial migration", "16", "1.83E-05"], ["mmu04510:Focal adhesion", "20", "7.17E-05"], ["mmu05210:Colorectal cancer", "12", "2.15E-04"], ["mmu04664:Fc epsilon RI signaling pathway", "11", "6.15E-04"], ["mmu04270:Vascular smooth muscle contraction", "13", "0.0011"]], "row_count": 40, "column_count": 4, "numeric_cells": 108, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tI-ijmm-39-06-1428"}}, {"id": "asset:table:pmid:28440393:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:433b24c45f296b6bcd8bb7d7e9edc147305e15dcde5409ddc3b086f796791ce3", "bytes": 715, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#tII-ijmm-39-06-1428", "version": null, "note": "Results of gene co-expression module analysis.", "structure": {"pmcid": "PMC5428963", "section_index": 14, "section_title": "Gene co-expression modules and functional enrichment analysis of genes in these modules", "row_count": 12, "column_count": 4}, "table": {"label": "Table II", "caption": "Results of gene co-expression module analysis.", "rows": [["Module", "Correlation", "Gene count", "p-value"], ["Turquoise", "−0.6", "503", "0.03850043"], ["Dark orange", "0.17", "40", "0.590624"], ["Dark red", "0.37", "28", "0.2373936"], ["Dark olive green", "0.024", "24", "0.9413225"], ["Dark green", "0.94", "378", "4.28E-06"], ["Pale turquoise", "0.69", "31", "0.01377187"], ["Black", "0.62", "896", "0.03280841"], ["Dark magenta", "−0.78", "10", "0.002588195"], ["Green", "−0.89", "267", "8.83E-05"], ["Royal blue", "−0.73", "66", "0.006466701"], ["Saddle brown", "−0.35", "15", "0.2660367"]], "row_count": 12, "column_count": 4, "numeric_cells": 33, "header_rows": 1, "locator": "section[14]/table-wrap[1]#tII-ijmm-39-06-1428"}}, {"id": "asset:table:pmid:28440393:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:108d149f1e247a7502eadf340cfdf156cc6799549352ec087bffe2839a3b9abc", "bytes": 1313, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#tIII-ijmm-39-06-1428", "version": null, "note": "The most significant GO terms of DEGs identified in darkgreen and green modules.", "structure": {"pmcid": "PMC5428963", "section_index": 14, "section_title": "Gene co-expression modules and functional enrichment analysis of genes in these modules", "row_count": 19, "column_count": 4}, "table": {"label": "Table III", "caption": "The most significant GO terms of DEGs identified in darkgreen and green modules.", "rows": [["Module", "Term", "p-value", "Gene"], ["Darkgreen", "GO:0022613 - ribonucleoprotein complex biogenesis", "10", "8.91E-04"], ["GO:0042254 - ribosome biogenesis", "9", "9.96E-04"], ["GO:0007050 - cell cycle arrest", "6", "0.0037"], ["GO:0042364 - water-soluble vitamin biosynthetic process", "4", "0.0071"], ["GO:0034470 - ncRNA processing", "9", "0.0083"], ["GO:0000041 - transition metal ion transport", "6", "0.0088"], ["GO:0055114 - oxidation reduction", "22", "0.0109"], ["GO:0034660 - ncRNA metabolic process", "10", "0.0116"], ["GO:0016053 - organic acid biosynthetic process", "8", "0.0146"], ["GO:0046394 - carboxylic acid biosynthetic process", "8", "0.0146"], ["Green", "GO:0007155 - cell adhesion", "14", "0.0126"], ["GO:0022610 - biological adhesion", "14", "0.0128"], ["GO:0006928 - cell motion", "10", "0.0258"], ["GO:0006695 - cholesterol biosynthetic process", "3", "0.0283"], ["GO:0055114 - oxidation reduction", "14", "0.0456"], ["GO:0016126 - sterol biosynthetic process", "3", "0.0462"], ["GO:0006865 - amino acid transport", "4", "0.0482"], ["GO:0006694 - steroid biosynthetic process", "4", "0.0482"]], "row_count": 19, "column_count": 4, "numeric_cells": 54, "header_rows": 1, "locator": "section[14]/table-wrap[2]#tIII-ijmm-39-06-1428"}}], "gaps": ["asset:data:geo:GSE72261 not downloaded", "asset:data:geo:GSE72261 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "|log2fold change (FC)| and p-values from an unpaired t-test implemented in the limma package (15) were used to select the DEGs."}}, {"id": "method-2", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "dendrogram"}}, {"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": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Pathway enrichment"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE72261"], "resolved_accessions": ["GSE72261"], "statements": ["The microarray data of GSE72261, deposited by Cameron et al (11), were downloaded from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) database (http://www.nibi.nih.gov/geo/)."], "basis": "The paper names GSE72261 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:28440393", "data:geo:GSE72261", "asset:table:pmid:28440393:1", "asset:table:pmid:28440393:2", "asset:table:pmid:28440393:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE72261"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 0, "usage": {}}, "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:28440393", "type": "paper", "label": "pmid:28440393"}, {"id": "source:pmid:28440393", "type": "manuscript", "label": "PMID 28440393 full text"}, {"id": "data:geo:GSE72261", "type": "dataset", "label": "GEO GSE72261"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28440393", "type": "paper", "label": "pmid:28440393"}, {"id": "source:pmid:28440393", "type": "manuscript", "label": "PMID 28440393 full text"}, {"id": "data:geo:GSE72261", "type": "dataset", "label": "GEO GSE72261"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28440393", "type": "extraction", "used": ["source:pmid:28440393"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE72261", "type": "accession_resolution", "used": ["data:geo:GSE72261"], "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:28440393", "parent_hash": "sha256:fdb5a04bf8343d0f3e42fbb8fcd2c9c73505bac4ea16795f9afc2d8378c7b52c", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE72261 licence not read", "asset:data:geo:GSE72261 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["d-type metaphyseal chondrodysplasia based on microarray data.", "es associated with the pathogenesis of SMCD. Microarray data from GSE72261 were downloaded from the"], "order_basis": "paper_text_order:49", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["|log2fold change (FC)| and p-values from an unpaired t-test implemented in the limma package (15) were used to select the DEGs."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T03:17:23+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}}}