{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29348872", "kind": "science-record", "revision": 6, "content_hash": "sha256:14e3bd351e0f0c8e84af72bf3e52e6185a1e6bc96e6863a249615e393a72f60b", "created_at": "2026-11-01T15:40:31Z", "updated_at": "2026-11-01T21:21:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene expression profiling reveals U1 snRNA regulates cancer gene expression.", "doi": "10.18632/oncotarget.22842", "pmid": "29348872", "authors": ["Zhi Cheng", "Yu Sun", "Xiaoran Niu", "Yingchun Shang", "Jishou Ruan", "Ze Chen", "Shan Gao", "Tao Zhang"], "journal": "Oncotarget", "year": 2017, "abstract": "U1 small nuclear RNA (U1 snRNA), as one of the most abundant ncRNAs in human cells, plays an important role in splicing of pre-mRNAs. Compared to previous studies which have focused on the primary function of U1 snRNA and the neurodegenerative diseases caused by abnormalities of U1 snRNA, this study is to investigate how U1 snRNA over-expression affects the expression of mammal genes on a genome-wide scale. By comparing the gene expression profiles of U1 snRNA over-expressed cells with those of their controls using microarray experiments, 916 genes or loci were identified significantly Differentially Expressed (DE). These 595 up-regulated DE genes and 321 down-regulated DE genes were analyzed using annotations from GO categories and pathways from the KEGG database. As a result, three of 12 enriched pathways were well-known cancer pathways, while the other nine pathways were associated to cancers in previous studies. The further analysis of 73 genes involved in 12 pathways suggested that U1 snRNA could regulate cancer gene expression. The microarray data under the GEO Series accession number GSE84304 is available in the NCBI GEO database.", "claims": [{"id": "claim-method", "statement": "The annotations and enrichment analyses by GO terms and KEGG pathways were performed using Gene Set Enrichment Analysis (GSEA) (http://software.broadinstitute.org/gsea/index.jsp).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29348872", "locator": "sections[12] \"Data analysis\" paragraph 2", "quote": "The annotations and enrichment analyses by GO terms and KEGG pathways were performed using Gene Set Enrichment Analysis (GSEA) (http://software.broadinstitute.org/gsea/index.jsp)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The microarray data under the GEO Series accession number GSE84304 is available in the NCBI GEO database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29348872", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The microarray data under the GEO Series accession number GSE84304 is available in the NCBI GEO database."}], "state": "complete"}, {"id": "claim-target-result", "statement": "U1 snRNA over-expression significantly changed the expression of 916 genes or loci in PC-12 cells (595 up-regulated and 321 down-regulated); enrichment was assessed by Gene Set Enrichment Analysis, and the underlying microarray data are available under GEO accession GSE84304.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29348872", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "By comparing the gene expression profiles of U1 snRNA over-expressed cells with those of their controls using microarray experiments, 916 genes or loci were identified significantly Differentially Expressed (DE). These 595 up-regulated DE genes and 321 down-regulated DE genes were analyzed using annotations from GO categories and pathways from the KEGG database."}, {"asset": "source:pmid:29348872", "locator": "sections[12] \"Data analysis\" paragraph 2", "quote": "The annotations and enrichment analyses by GO terms and KEGG pathways were performed using Gene Set Enrichment Analysis (GSEA) (http://software.broadinstitute.org/gsea/index.jsp)."}, {"asset": "source:pmid:29348872", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The microarray data under the GEO Series accession number GSE84304 is available in the NCBI GEO database."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "U1 snRNA over-expression significantly changed the expression of 916 genes or loci in PC-12 cells (595 up-regulated and 321 down-regulated); enrichment was assessed by Gene Set Enrichment Analysis, and the underlying microarray data are available under GEO accession GSE84304.", "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:29348872"], "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:GSE84304"], "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:GSE84304"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29348872", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/oncotarget.22842", "sha256": "sha256:e3f5cc6a5575f375f26243d93eee767ee5b3d71d3d059b44dea94fc84d694426", "bytes": 21661, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/oncotarget.22842", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5762557", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE84304", "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=GSE84304", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE84304", "version": null, "note": "The microarray data under the GEO Series accession number GSE84304 is available in the NCBI GEO database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The microarray data under the GEO Series accession number GSE84304 is available in the NCBI GEO database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2231238", "GSM2231239", "GSM2231240", "GSM2231241", "GSM2231242", "GSM2231243"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "20566", "taxon": "Rattus norvegicus", "title": "Gene expression profiling reveals cytoplasmic U1 snRNA accumulation may cause cancers", "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:29348872:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:623544240e3dba21aa2dc35107d61461b686bee8a4026d9692981d27ea0e6be0", "bytes": 1792, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T1", "version": null, "note": "Enriched pathways induced by U1 snRNA over-expression", "structure": {"pmcid": "PMC5762557", "section_index": 5, "section_title": "Pathway analysis of DE genes", "row_count": 13, "column_count": 3}, "table": {"label": "Table 1", "caption": "Enriched pathways induced by U1 snRNA over-expression", "rows": [["Pathway", "Up-regulated", "Down-regulated"], ["rno04010:MAPK signaling pathway", "Pak1, Nf1, Il1r2, Rras2, Dusp8, Nfkb1, Rapgef2, Fos, Traf2, Dusp5, Myc, Ddit3, Tgfb2, Tnf, Gadd45a, Gadd45g, Dusp1, Gadd45b", "Pla2g2a, Tgfb1, Cd14, Map4k2, Cdc25b, Ntf4, Pla2g6, Fgf2, Ntrk2"], ["rno04110:Cell cycle", "Wee2, Cdkn1a, Smc1b, Mdm2, Cdk6, Cdkn2a, Myc, Tgfb2, Gadd45a, Gadd45g, Gadd45b", "Tgfb1, Rbl2, Cdc6, Cdc25b, Ccne1"], ["rno04060:Cytokine-cytokine receptor interaction", "Il1r2, Tnfsf15, Il9r, Ccl5, Ifnb1, Cxcl2, Tnf, Il22ra2, Csf1, Cx3cl1, Cxcl10, Ltb, Tnfsf18, Il23r, Il6, Ccl4, Cxcl11", "Tnfsf9, Il23a, Csf3"], ["rno04621:NOD-like receptor signaling pathway", "Ripk2, Cxcl1, Nfkb1, Birc3, Ccl5, Tnfaip3, Cxcl2, Tnf, Il6", "Pycard"], ["rno04115:p53 signaling pathway", "Bid, Cdkn1a, Mdm2, Cdk6, Cdkn2a, Gadd45a, Gadd45g, Bbc3, Gadd45b", "Ccne1"], ["rno04623:Cytosolic DNA-sensing pathway", "Nfkb1, Ccl5, Ifnb1, Cxcl10, Il6, Ccl4", "Pycard"], ["rno04622:RIG-I-like receptor signaling pathway", "Ifih1, Nfkb1, Traf2, Ifnb1, Tnf, Dhx58, Isg15, Cxcl10", ""], ["rno04620:Toll-like receptor signaling pathway", "Nfkb1, Fos, Tlr5, Ccl5, Ifnb1, Tnf, Cxcl10, Il6, Cxcl11", "Cd14"], ["rno05220:Chronic myeloid leukemia", "Cdkn1a, Nfkb1, Mdm2, Runx1, Cdk6, Cdkn2a, Myc, Tgfb2", "Tgfb1"], ["rno04640:Hematopoietic cell lineage", "Il1r2, Cd22, Il9r, Tnf, Csf1, Il6", "Cd14, Csf3, Cd37"], ["rno05219:Bladder cancer", "Cdkn1a, Cdh1, Mdm2, Rassf1, Cdkn2a, Myc", ""], ["rno05200:Pathways in cancer", "Bid, Cdkn1a, Cdh1, Nfkb1, Fos, Mdm2, Runx1, Hhip, Traf2, Rassf1, Cdk6, Birc3, Cdkn2a, Myc, Traf1, Tgfb2, Lamc2, Il6", "Tgfb1, Ccne1, Fgf2"]], "row_count": 13, "column_count": 3, "numeric_cells": 25, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:GSE84304 not downloaded", "asset:data:geo:GSE84304 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Gene Set Enrichment Analysis (GSEA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The annotations and enrichment analyses by GO terms and KEGG pathways were performed using Gene Set Enrichment Analysis (GSEA) (http://software.broadinstitute.org/gsea/index.jsp)."}}], "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 (Gene Set Enrichment Analysis (GSEA)), 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": ["GSE84304"], "resolved_accessions": ["GSE84304"], "statements": ["The microarray data under the GEO Series accession number GSE84304 is available in the NCBI GEO database."], "basis": "The paper names GSE84304 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": [], "assets": ["source:pmid:29348872", "data:geo:GSE84304", "asset:table:pmid:29348872:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE84304"]}, "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": "2026-10-31T18:33:36Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 47435, "completion_tokens": 3076, "cached_tokens": 12808}}, "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:29348872", "type": "paper", "label": "pmid:29348872"}, {"id": "source:pmid:29348872", "type": "manuscript", "label": "PMID 29348872 full text"}, {"id": "data:geo:GSE84304", "type": "dataset", "label": "GEO GSE84304"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29348872", "type": "paper", "label": "pmid:29348872"}, {"id": "source:pmid:29348872", "type": "manuscript", "label": "PMID 29348872 full text"}, {"id": "data:geo:GSE84304", "type": "dataset", "label": "GEO GSE84304"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29348872", "type": "extraction", "used": ["source:pmid:29348872"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE84304", "type": "accession_resolution", "used": ["data:geo:GSE84304"], "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:29348872", "parent_hash": "sha256:28f9205deb62547ff64c302920b62ceb2d9fa7672a4ea41385840b1d24335b18", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE84304 licence not read", "asset:data:geo:GSE84304 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["sed cells with those of their controls using microarray experiments, 916 genes or loci were identifi", "A could regulate cancer gene expression. The microarray data under the GEO Series accession number G", "urther analysis To validate results from the microarray data analysis, the expression levels of six", "which were consistent with results from the microarray data analysis (Figure 3). Pathways in cancer"], "order_basis": "paper_text_order:553", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["in cancer (KEGG: rno05200) were measured by qPCR assays using human cell line (Hela), rat cel", "ession levels of six genes were confirmed by qPCR. Confirmation of microarray results by qPCRT", "(Ccne1, Fgf2 and Tgfb1) were measured using qPCR. (A) Fold changes represent the average expr", "enes (Pcna, Mcm2 and Ki-67) were measured by qPCR assays using human cell line (Hela), rat cel"], "order_basis": "paper_text_order:2692", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["asured by qPCR assays using human cell line (Hela), rat cell line (PC-12) and mouse tissues (t", "Ki-67) by qPCR assays using human cell line (Hela), rat cell line (PC-12) and mouse tissues (t", "When it comes to the experimental results in Hela cells, the Bax/Bcl2 ratio reached 1.003, whi", "i-67 by 10.44, 12.8 and 2.13 fold changes in Hela cells, which suggested that U1 snRNA over-ex"], "order_basis": "paper_text_order:2726", "id": "assay:3"}, {"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": ["t for one week, six 9-week-old C57BL/6J male mice were randomly divided into the treatment group (n", "oup (n=3) and the control group (n=3). These mice were weighed and then anesthetized (0.6 g/kg body", "t was slowly withdrawn. Two month later, six mice were decapitated to obtain their hippocampus tiss", "cell line (Hela), rat cell line (PC-12) and mouse tissues (the hippocampus) from animal experi"], "order_basis": "paper_text_order:2760", "id": "assay:4"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["x genes. (B) Expression levels of three cell-apoptosis marker genes (Bax, Bcl2 and Casp3) and three", "we measured expression levels of three cell-apoptosis marker genes (Bax, Bcl2 and Casp3) and three", "eriments (Supplementary Table 4). Both three apoptosis markers and three proliferation markers were", "t a low Bax/Bcl2 ratio (< 1) is against cell apoptosis, while a high Bax/Bcl2 ratio (>1) is in favo"], "order_basis": "paper_text_order:3964", "id": "assay:5"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["l-proliferation marker genes (Pcna, Mcm2 and Ki-67) were measured by qPCR assays using human ce", "l-proliferation marker genes (Pcna, Mcm2 and Ki-67) by qPCR assays using human cell line (Hela)", "antly increased expression of Pcna, Mcm2 and Ki-67 by 2.95, 4.11 and 1.65 fold changes in PC-12", "antly increased expression of Pcna, Mcm2 and Ki-67 by 10.44, 12.8 and 2.13 fold changes in Hela"], "order_basis": "paper_text_order:4067", "id": "assay:6"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["In-fusion HD Cloning Kit (Clontech, USA) and transfected into E. coli JM109 competent cells (TaKaRa,", "JM109 competent cells (TaKaRa, Japan). After transfection, E. coli cells were being shaken at 150 rpm", "in PC-12 cells. Then, we performed U1 snRNA knockdown experiments using RNAi following the procedu", "io (~ 0.3) in PC-12 cells caused by U1 snRNA knockdown. It is well known that a low Bax/Bcl2 ratio"], "order_basis": "paper_text_order:4759", "id": "assay:7"}]},"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":"2026-11-04T01:43:03+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}