{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33284517", "kind": "science-record", "revision": 8, "content_hash": "sha256:b3aee25cf1b771110823926e2d5ce1819ae05b79ccd0e507b9945771405ca449", "created_at": "2026-11-01T15:41:18Z", "updated_at": "2026-11-01T22:45:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "β-catenin regulates FOXP2 transcriptional activity via multiple binding sites.", "doi": "10.1111/febs.15656", "pmid": "33284517", "authors": ["Gesa Richter", "Tianshu Gui", "Benjamin Bourgeois", "Chintan N Koyani", "Peter Ulz", "Ellen Heitzer", "Dirk von Lewinski", "Boudewijn M T Burgering", "Ernst Malle", "Tobias Madl"], "journal": "The FEBS journal", "year": 2021, "abstract": "The transcription factor forkhead box protein P2 (FOXP2) is a highly conserved key regulator of embryonal development. The molecular mechanisms of how FOXP2 regulates embryonal development, however, remain elusive. Using RNA sequencing, we identified the Wnt signaling pathway as key target of FOXP2-dependent transcriptional regulation. Using cell-based assays, we show that FOXP2 transcriptional activity is regulated by the Wnt coregulator β-catenin and that β-catenin contacts multiple regions within FOXP2. Using nuclear magnetic resonance spectroscopy, we uncovered the molecular details of these interactions. β-catenin contacts a disordered FOXP2 region with α-helical propensity via its folded armadillo domain, whereas the intrinsically disordered β-catenin N terminus and C terminus bind to the conserved FOXP2 DNA-binding domain. Using RNA sequencing, we confirmed that β-catenin indeed regulates transcriptional activity of FOXP2 and that the FOXP2 α-helical motif acts as a key regulatory element of FOXP2 transcriptional activity. Taken together, our findings provide first insight into novel regulatory interactions and help to understand the intricate mechanisms of FOXP2 function and (mis)-regulation in embryonal development and human diseases. DATABASE: Expression data are available in the GEO database under the accession number GSE138938.", "claims": [{"id": "claim-method", "statement": "Gene read counts are generated using featurecounts [64], and differential expression was analyzed using deseq2 [65].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33284517", "locator": "sections[16] \"RNA isolation and RNA‐Seq\" paragraph 2", "quote": "Gene read counts are generated using featurecounts [64], and differential expression was analyzed using deseq2 [65]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Expression data are available in the GEO database under the accession number GSE138938.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33284517", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Expression data are available in the GEO database under the accession number GSE138938."}], "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:33284517"], "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:GSE138938"], "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:GSE138938"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33284517", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/febs.15656", "sha256": "sha256:01be49a915b3663a8ab30e192177f8d57aaaf8ab8ab26d6286dacbbf52239565", "bytes": 58029, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/febs.15656", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8246981", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE138938", "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=GSE138938", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE138938", "version": null, "note": "Expression data are available in the GEO database under the accession number GSE138938.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Expression data are available in the GEO database under the accession number GSE138938.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4123907", "GSM4123908", "GSM4123909", "GSM4123910", "GSM4123911", "GSM4123912", "GSM4123913", "GSM4123914", "GSM4123915", "GSM4123916", "GSM4123917", "GSM4123918", "GSM4123919", "GSM4123920", "GSM4123921", "GSM4123922", "GSM4123923", "GSM4123924", "GSM4123925", "GSM4123926", "GSM4123927", "GSM4123928", "GSM4123929", "GSM4123930", "GSM4123931", "GSM4123932", "GSM4123933", "GSM4123934", "GSM4123935", "GSM4123936"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "21697", "taxon": "Homo sapiens", "title": "β-catenin regulates FOXP2 transcriptional activity via multiple binding sites", "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:33284517:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b115d8b15f98041e20136737aa21f7fd4406f4e363f65e968371e70f4a74bac3", "bytes": 2302, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#febs15656-tbl-0001", "version": null, "note": "List of most significantly differentially expressed genes in all tested conditions and according to our RNA‐Seq data. The fold change is indicated in bracket.", "structure": {"pmcid": "PMC8246981", "section_index": 8, "section_title": "Deletion of the disordered β‐catenin‐binding site alters FOXP2 transcriptional activity in the presence and absence of β‐catenin", "row_count": 12, "column_count": 10}, "table": {"label": "Table 1", "caption": "List of most significantly differentially expressed genes in all tested conditions and according to our RNA‐Seq data. The fold change is indicated in bracket.", "rows": [["FOXP2", "CHIR", "FOXP2Δhelix", "FOXP2 + CHIR", "FOXP2Δhelix + CHIR"], ["FOXP2 (13)", "PRND (−10.5)", "GZMB (12)", "MYOCD (−9.2)", "FOXP2 (12.6)", "PRND (−9.7)", "FOXP2 (14)", "PRND (−10.5)", "FOXP2 (13.8)", "PRND (−9.2)"], ["MMP1 (11.3)", "KANK4 (−9.3)", "MUCL1 (11.4)", "FOXS1 (−8.8)", "MAL (11.4)", "PLP1 (−9.7)", "LPAR6 (13)", "SOSTDC1 (−10)", "MAL (12.7)", "SOSTDC1 (−8.7)"], ["LAPR6 (11.2)", "HTR2A (−9.2)", "CXCL6 (10.7)", "NWD1 (−8.5)", "LPAR6 (11.4)", "KANK4 (−9.1)", "MYCT1 (12.1)", "IGFBP5 (−9.1)", "LPAR6 (12.6)", "IGFBP5 (−8.7)"], ["CTD‐2532D 12.4 (9.4)", "SOSTDC1 (−8.9)", "MTHFD2P1 (10.7)", "GALNT15 (−8.3)", "MMP1 (10.9)", "ABCB5 (−8.3)", "SERPINB2 (12)", "PLP1 (−8.2)", "MYCT1 (11.9)", "ABCB5 (−8.3)"], ["MYCT1 (9.3)", "AC074289.1 (−8.5)", "C1orf168 (10.1)", "CD180 (−8.1)", "MUC5AC (9.7)", "CCDC67 (−8)", "RP11‐753N 8.1 (11.9)", "HTR2A (−8)", "RP11‐753N 8.1 (11.9)", "APOL4 (−8.2)"], ["IL24 (9)", "MYOCD (−8.1)", "LINC00161 (9.9)", "YPEL4 (−7.9)", "AGXT (9.5)", "CXCL14 (−7.8)", "SPRR2D (11.3)", "CXCL14 (−8)", "MUC5AC (11.6)", "GABRR1 (−7.7)"], ["ENAM (9)", "CXCL14 (−8.1)", "RP11‐415C 15.2 (9.8)", "SYT8 (−7.7)", "MYCT1 (9.4)", "RP11‐798L 4.1 (−7.7)", "CTD‐2532D 12.4 (11.2)", "SLC2A12 (−8)", "AGXT (11.5)", "RP1‐193H 18.2 (−7.7)"], ["AF121898.3 (9)", "FOXS1 (−8)", "RP11‐95P 13.1 (9.7)", "HRT2A (−7.2)", "CTD‐2532D 12.4 (9.1)", "GABRR1 (−7.7)", "MAL (11.2)", "AC074289.1 (−7.9)", "GZMB (11.5)", "CXCL14 (−7.7)"], ["SPRR2D (8.6)", "RP11‐798L 4.1 (−7.9)", "CST1 (9.6)", "TNFSF15 (−7.2)", "LINC00659 (9)", "AC074289.1 (−7.6)", "MMP1 (10.8)", "R3HDML (−7.8)", "SERPINB2 (11.1)", "GALNT15 (−7.6)"], ["MAL (8.6)", "ABCB5 (−7.9)", "FILIP1 (9.5)", "CTD‐2334D 19.1 (−6.8)", "SRL (8.9)", "MYOCD (−7.6)", "GZMB (10.8)", "GALNT15 (−7.6)", "SPRR2D (10.7)", "FABP7 (−7.6)"], ["MMP3 (8.4)", "GABRR1 (−7.9)", "IGFL2 (9.2)", "LINC00961 (−6.8)", "ENAM (8.9)", "HMGB3P18 (−7.5)", "AC006372.1 (10.7)", "MAP2K6 (−7.5)", "MUCL1 (10.5)", "KIAA1210 (−7.5)"]], "row_count": 12, "column_count": 10, "numeric_cells": 110, "header_rows": 1, "locator": "section[8]/table-wrap[1]#febs15656-tbl-0001"}}, {"id": "asset:table:pmid:33284517:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:03d22a3b9db6a7a5207c3e8a8f8c569ebbde642b89650fe4c05f3437e0eefbf2", "bytes": 872, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#febs15656-tbl-0002", "version": null, "note": "Primer sequences used for site‐directed mutagenesis.", "structure": {"pmcid": "PMC8246981", "section_index": 17, "section_title": "Quantitative real‐time PCR (qPCR)", "row_count": 6, "column_count": 4}, "table": {"label": "Table 2", "caption": "Primer sequences used for site‐directed mutagenesis.", "rows": [["Constructs", "Primer sequences (5′–3′)", "Optimized for", "Vectors"], ["FOXP2FH", "Fw1: CGTCCGCCGTTCACCTAC Rv1: GGATCCTTATTCCAGGTCTTCTG Fw2: CCCGACGCTGtaaAAAAACATTCC Rv2: GAGCCGGTAATTTTCTGAC", "E. coli cells", "pETM11"], ["FOXP2 Construct247–715", "Fw: GGCCAGGCAGCACTTCCT Rv: TTAGGTTTCACAAGTCTCGAGTCATTC", "Mammalian cells", "pCMV 3Tag"], ["FOXP2 Construct342–715", "Fw: TCTCTATGGCCATGGAGTTT Rv: AAGCCGAATTCCACCACA", "Mammalian cells", "pCMV 3Tag"], ["FOXP2 Construct504–715", "Fw: TCAGACCTCCATTTACTTATGC Rv: AGCCGAATTCCACCACAC", "Mammalian cells", "pCMV 3Tag"], ["FOXP2Δhelix", "Fw: GTGACTGGAGTTCACAGTATG Rv: AGGACTTAAGCCAGCTTG", "Mammalian cells", "pCMV 3Tag"]], "row_count": 6, "column_count": 4, "numeric_cells": 9, "header_rows": 1, "locator": "section[17]/table-wrap[1]#febs15656-tbl-0002"}}, {"id": "asset:table:pmid:33284517:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1124ae72070e393f31ecccb43a2896f38c716040db53ad627a3db538c6e8a6e7", "bytes": 669, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#febs15656-tbl-0003", "version": null, "note": "Primer sequences used for qPCR.", "structure": {"pmcid": "PMC8246981", "section_index": 17, "section_title": "Quantitative real‐time PCR (qPCR)", "row_count": 8, "column_count": 3}, "table": {"label": "Table 3", "caption": "Primer sequences used for qPCR.", "rows": [["Gene", "Forward primer (5′–3′)", "Reverse primer (5′–3′)"], ["BMP4", "ATGATTCCTGGTAACCGAATGC", "CCCCGTCTCAGGTATCAAACT"], ["CCND1", "GCTGCGAAGTGGAAACCATC", "CCTCCTTCTGCACACATTTGAA"], ["CD44", "CTGCCGCTTTGCAGGTGTA", "CATTGTGGGCAAGGTGCTATT"], ["HPRT1", "CCTGGCGTCGTGATTAGTGAT", "AGACGTTCAGTCCTGTCCATAA"], ["JUN", "TCCAAGTGCCGAAAAAGGAAG", "CGAGTTCTGAGCTTTCAAGGT"], ["LEF1", "TGCCAAATATGAATAACGACCCA", "GAGAAAAGTGCTCGTCACTGT"], ["TIAM1", "CCTGTGTCTTACACTGACTCTTC", "CATCCCCGTAAAGCCTGCTC"]], "row_count": 8, "column_count": 3, "numeric_cells": 3, "header_rows": 1, "locator": "section[17]/table-wrap[2]#febs15656-tbl-0003"}}], "gaps": ["asset:data:geo:GSE138938 not downloaded", "asset:data:geo:GSE138938 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": "Gene read counts are generated using featurecounts [64], and differential expression was analyzed using deseq2 [65]."}}], "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: deseq2."}, "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": ["GSE138938"], "resolved_accessions": ["GSE138938"], "statements": ["Expression data are available in the GEO database under the accession number GSE138938."], "basis": "The paper names GSE138938 in GEO database 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:33284517", "data:geo:GSE138938", "asset:table:pmid:33284517:1", "asset:table:pmid:33284517:2", "asset:table:pmid:33284517:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE138938"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:52Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 46308, "completion_tokens": 811, "cached_tokens": 776}}, "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:33284517", "type": "paper", "label": "pmid:33284517"}, {"id": "source:pmid:33284517", "type": "manuscript", "label": "PMID 33284517 full text"}, {"id": "data:geo:GSE138938", "type": "dataset", "label": "GEO GSE138938"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33284517", "type": "paper", "label": "pmid:33284517"}, {"id": "source:pmid:33284517", "type": "manuscript", "label": "PMID 33284517 full text"}, {"id": "data:geo:GSE138938", "type": "dataset", "label": "GEO GSE138938"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33284517", "type": "extraction", "used": ["source:pmid:33284517"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE138938", "type": "accession_resolution", "used": ["data:geo:GSE138938"], "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:33284517", "parent_hash": "sha256:c0a7b7715df53a89ba41a5c2c829ab97a1d8d68f9b1743cc4fa69836f218e50b", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE138938 licence not read", "asset:data:geo:GSE138938 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["development, however, remain elusive. Using RNA sequencing, we identified the Wnt signaling pathway as", "he conserved FOXP2 DNA-binding domain. Using RNA sequencing, we confirmed that β-catenin indeed regulate"], "order_basis": "paper_text_order:256", "id": "assay:1"}, {"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": ["Materials and methods Cell culture and transfection For the Co‐IP with endogenous FOXP2 and β‐ca", "plate, approx. 80% confluent U2OS cells were transfected with various FOXP2 construct plasmids (500 n", "IR 99021 was added in the medium 72 h before transfection with FOXP2 construct plasmids. For the qPCR", "986 for FOXP2; Qiagen, Vienna, Austria) were transfected to HEK293T cell with Lipofectamine RNAiMAX ("], "order_basis": "paper_text_order:1441", "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": ["or the qPCR experiments, HEK 293T cells were cultured in DMEM supplemented with 100 U·mL−1 penicillin", "−1 penicillin, and 100 µg·mL−1 streptomycin. U2OS cells were maintained at 37 °C under 5% CO2", ". In a six‐well plate, approx. 80% confluent U2OS cells were transfected with various FOXP2 co"], "order_basis": "paper_text_order:1675", "id": "assay:3"}, {"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": ["ction with FOXP2 construct plasmids. For the qPCR experiments, HEK 293T cells were cultured in", "ollected two days after transfection. For RT–qPCR, GSK inhibitor CHIR99021 (final concentratio"], "order_basis": "paper_text_order:2250", "id": "assay:4"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["CGACUAAACACAUCAA) was used as a control. For western blot, cells were collected two days after transfe"], "order_basis": "paper_text_order:2803", "id": "assay:5"}, {"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": ["Gene read counts are generated using featurecounts [64], and differential expression was analyzed using deseq2 [65]."], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T02:36:49+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}}}