{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23402308", "kind": "science-record", "revision": 6, "content_hash": "sha256:a981746c6dfc9e87c52716c57340406d74f404b64325975667cdc68c3c433eb8", "created_at": "2026-11-01T15:40:02Z", "updated_at": "2026-11-01T21:19:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Nuclear Factor I genomic binding associates with chromatin boundaries.", "doi": "10.1186/1471-2164-14-99", "pmid": "23402308", "authors": ["Milos Pjanic", "Christoph D Schmid", "Armelle Gaussin", "Giovanna Ambrosini", "Jozef Adamcik", "Petar Pjanic", "Genta Plasari", "Jan Kerschgens", "Giovani Dietler", "Philipp Bucher", "Nicolas Mermod"], "journal": "BMC genomics", "year": 2013, "abstract": "BACKGROUND: The Nuclear Factor I (NFI) family of DNA binding proteins (also called CCAAT box transcription factors or CTF) is involved in both DNA replication and gene expression regulation. Using chromatin immuno-precipitation and high throughput sequencing (ChIP-Seq), we performed a genome-wide mapping of NFI DNA binding sites in primary mouse embryonic fibroblasts.\nRESULTS: We found that in vivo and in vitro NFI DNA binding specificities are indistinguishable, as in vivo ChIP-Seq NFI binding sites matched predictions based on previously established position weight matrix models of its in vitro binding specificity. Combining ChIP-Seq with mRNA profiling data, we found that NFI preferentially associates with highly expressed genes that it up-regulates, while binding sites were under-represented at expressed but unregulated genes. Genomic binding also correlated with markers of transcribed genes such as histone modifications H3K4me3 and H3K36me3, even outside of annotated transcribed loci, implying NFI in the control of the deposition of these modifications. Positional correlation between + and - strand ChIP-Seq tags revealed that, in contrast to other transcription factors, NFI associates with a nucleosomal length of cleavage-resistant DNA, suggesting an interaction with positioned nucleosomes. In addition, NFI binding prominently occurred at boundaries displaying discontinuities in histone modifications specific of expressed and silent chromatin, such as loci submitted to parental allele-specific imprinted expression.\nCONCLUSIONS: Our data thus suggest that NFI nucleosomal interaction may contribute to the partitioning of distinct chromatin domains and to epigenetic gene expression regulation.NFI ChIP-Seq and input control DNA data were deposited at Gene Expression Omnibus (GEO) repository under accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts are on GEO accession number GSE15871.", "claims": [{"id": "claim-method", "statement": "NFI-bound genes showed a higher average transcription level than genes not associated to NFI (6.61 vs. 5.85, respectively, p=2.91E-31, two tailed t-test).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23402308", "locator": "sections[12] \"NFIC as an activator of gene transcription\" paragraph 2", "quote": "NFI-bound genes showed a higher average transcription level than genes not associated to NFI (6.61 vs. 5.85, respectively, p=2.91E-31, two tailed t-test)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23402308", "locator": "sections[21] \"Datasets repository\" paragraph 2", "quote": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using ChIP-Seq and the ChIP-Peak statistical peak-finding method, the study found that in vivo and in vitro NFI DNA-binding specificities are indistinguishable; the ChIP-Seq and input-control data are available through GEO under accession GSE15844.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:23402308", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We found that in vivo and in vitro NFI DNA binding specificities are indistinguishable, as in vivo ChIP-Seq NFI binding sites matched predictions based on previously established position weight matrix models of its in vitro binding specificity."}, {"asset": "source:pmid:23402308", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "NFI ChIP-Seq and input control DNA data were deposited at Gene Expression Omnibus (GEO) repository under accession number GSE15844."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using ChIP-Seq and the ChIP-Peak statistical peak-finding method, the study found that in vivo and in vitro NFI DNA-binding specificities are indistinguishable; the ChIP-Seq and input-control data are available through GEO under accession GSE15844.", "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:23402308"], "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:GSE12241"], "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:GSE12241"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:23402308", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/1471-2164-14-99", "sha256": "sha256:2a1acf18bbe6f611282875aa49cdea0cc0bcbdcd30260eff824e928a12d5be8c", "bytes": 83404, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/1471-2164-14-99", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3610271", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12241", "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=GSE12241", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12241", "version": null, "note": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM307605", "GSM307606", "GSM307607", "GSM307608", "GSM307609", "GSM307610", "GSM307611", "GSM307612", "GSM307613", "GSM307614", "GSM307615", "GSM307616", "GSM307617", "GSM307618", "GSM307619", "GSM307620", "GSM307621", "GSM307622", "GSM307623", "GSM307624", "GSM307625"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "9185", "taxon": "Mus musculus", "title": "Genome-wide maps of chromatin state in pluripotent and lineage-committed cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE15844", "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=GSE15844", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15844", "version": null, "note": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM398010", "GSM398011", "GSM398012"], "sample_count": 3, "group_sizes": null, "group_sizes_basis": null, "platform": "9185", "taxon": "Mus musculus", "title": "Genome-wide mapping of Nuclear Factor I binding sites using ChIP-Seq in WT and NFI-C knock-out MEFs", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE15871", "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=GSE15871", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15871", "version": null, "note": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM398437", "GSM398438", "GSM398439", "GSM398440", "GSM398441", "GSM398442", "GSM398443", "GSM398444", "GSM398445", "GSM398446", "GSM398447", "GSM398448", "GSM398449", "GSM398450", "GSM398451", "GSM398452", "GSM398453", "GSM398454"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Expression data from NFI-C knock out embryonic fibroblasts", "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:23402308:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5c78867c5e46bc4f7a968933d04d58bd61ef704250690eb122fd6798cc33e5d5", "bytes": 1167, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "Distribution of NFI-C-occupied sites at H3K27me3 and H3K36me3 boundaries", "structure": {"pmcid": "PMC3610271", "section_index": 10, "section_title": "NFI associates with open chromatin marks and chromatin domain boundaries", "row_count": 9, "column_count": 4}, "table": {"label": "Table 1", "caption": "Distribution of NFI-C-occupied sites at H3K27me3 and H3K36me3 boundaries", "rows": [["29,158 H3K27me3 boundaries, subdivided in:", "Matching NFI-occupied site", "Matching random genomic sites", "P-value (binomial)"], ["4,687 H3K27me3 boundaries co-localized with H3K36 boundaries", "148 (3.15%)", "45 (0.96%)", "1.51e-14"], ["2,032 H3K27me3 and H3K36me3 boundaries co-localized with TSS", "35 (1.72%)", "6 (0.29%)", "7.84e-07"], ["1,507 H3K27me3 and H3K36me3 boundaries co-localized with TES", "21 (1.39%)", "11 (0.72%)", "0.050"], ["1,148 H3K27me3 and H3K36me3 boundaries not co-localized with TES or TSS", "92 (8.01%)", "28 (2.43%)", "1.11e-09"], ["24,471 H3K27me3-only boundaries (not co-localized with H3K36 boundaries)", "284 (1.16%)", "253 (1.03%)", "0.167"], ["3,386 H3K27me3-only boundaries co-localized with TSS", "67 (0.19%)", "19 (0.05%)", "5.29e-08"], ["2,153 H3K27me3-only boundaries co-localized with TES", "20 (0.09%)", "13 (0.06%)", "0.162"], ["18,932 H3K27me3-only boundaries not co-localized with TES or TSS", "197 (1.04%)", "221(1.16%)", "0.889"]], "row_count": 9, "column_count": 4, "numeric_cells": 33, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:GSE12241 not downloaded", "asset:data:geo:GSE12241 licence not read", "asset:data:geo:GSE15844 not downloaded", "asset:data:geo:GSE15844 licence not read", "asset:data:geo:GSE15871 not downloaded", "asset:data:geo:GSE15871 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "two tailed t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "NFI-bound genes showed a higher average transcription level than genes not associated to NFI (6.61 vs. 5.85, respectively, p=2.91E-31, two tailed t-test)."}}], "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 (two tailed t-test), 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": ["GSE15844", "GSE15871", "GSE12241"], "resolved_accessions": ["GSE15844", "GSE15871", "GSE12241"], "statements": ["NFI ChIP-Seq data from wild type and NFI-C knock-out mouse embryonic fibroblasts, as well as sequenced input control DNA, were deposited at Gene Expression Omnibus (GEO) repository under the accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts were taken from GEO repository under the accession number GSE15871. ChIP-Seq data for histone modifications H3K4me3, H3K27me3, H3K36me3 in mouse embryonic fibroblasts were obtained from GEO repository under the accession number GSE12241."], "basis": "The paper names GSE15844, GSE15871, GSE12241 in 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:23402308", "data:geo:GSE12241", "asset:table:pmid:23402308:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12241"]}, "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": "2026-10-31T18:21:17Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 161039, "completion_tokens": 4683, "cached_tokens": 81695}}, "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:23402308", "type": "paper", "label": "pmid:23402308"}, {"id": "source:pmid:23402308", "type": "manuscript", "label": "PMID 23402308 full text"}, {"id": "data:geo:GSE12241", "type": "dataset", "label": "GEO GSE12241"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:23402308", "type": "paper", "label": "pmid:23402308"}, {"id": "source:pmid:23402308", "type": "manuscript", "label": "PMID 23402308 full text"}, {"id": "data:geo:GSE12241", "type": "dataset", "label": "GEO GSE12241"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-23402308", "type": "extraction", "used": ["source:pmid:23402308"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12241", "type": "accession_resolution", "used": ["data:geo:GSE12241"], "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:23402308", "parent_hash": "sha256:f1397ba3dda97e35f87b775d00b6cf2ac24e586897af32caf1a784ebe0309bda", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE12241 licence not read", "asset:data:geo:GSE12241 not downloaded", "asset:data:geo:GSE15844 licence not read", "asset:data:geo:GSE15844 not downloaded", "asset:data:geo:GSE15871 licence not read", "asset:data:geo:GSE15871 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "chip_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["recipitation and high throughput sequencing (ChIP-Seq), we performed a genome-wide mapping of NFI", "cificities are indistinguishable, as in vivo ChIP-Seq NFI binding sites matched predictions based", "its in vitro binding specificity. Combining ChIP-Seq with mRNA profiling data, we found that NFI", "ositional correlation between + and - strand ChIP-Seq tags revealed that, in contrast to other tra"], "order_basis": "paper_text_order:286", "id": "assay:1"}, {"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": ["mbryonic fibroblasts. RESULTS: We found that in vivo and in vitro NFI DNA binding specificities a", "ding specificities are indistinguishable, as in vivo ChIP-Seq NFI binding sites matched predictio", "mapping of NFI DNA binding sites in primary mouse embryonic fibroblasts. RESULTS: We found tha", "SE15844. Gene expression microarray data for mouse embryonic fibroblasts are on GEO accession n"], "order_basis": "paper_text_order:369", "id": "assay:2"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["r accession number GSE15844. Gene expression microarray data for mouse embryonic fibroblasts are on"], "order_basis": "paper_text_order:1898", "id": "assay:3"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["e (WT) and NFI-C knock-out (KO) embryos were cultured in DMEM medium under the following conditions:"], "order_basis": "paper_text_order:2151", "id": "assay:4"}]},"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":"2026-11-04T02:46:58+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}}}