{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:24312219", "kind": "science-record", "revision": 7, "content_hash": "sha256:8effca99a5c764f796c0bbfd74a48d573e5028c70b31192beef4cd5c35715f70", "created_at": "2026-11-01T15:40:04Z", "updated_at": "2026-11-01T21:58:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dynamic impacts of the inhibition of the molecular chaperone Hsp90 on the T-cell proteome have implications for anti-cancer therapy.", "doi": "10.1371/journal.pone.0080425", "pmid": "24312219", "authors": ["Ivo Fierro-Monti", "Pablo Echeverria", "Julien Racle", "Celine Hernandez", "Didier Picard", "Manfredo Quadroni"], "journal": "PloS one", "year": 2013, "abstract": "The molecular chaperone Hsp90-dependent proteome represents a complex protein network of critical biological and medical relevance. Known to associate with proteins with a broad variety of functions termed clients, Hsp90 maintains key essential and oncogenic signalling pathways. Consequently, Hsp90 inhibitors are being tested as anti-cancer drugs. Using an integrated systematic approach to analyse the effects of Hsp90 inhibition in T-cells, we quantified differential changes in the Hsp90-dependent proteome, Hsp90 interactome, and a selection of the transcriptome. Kinetic behaviours in the Hsp90-dependent proteome were assessed using a novel pulse-chase strategy (Fierro-Monti et al., accompanying article), detecting effects on both protein stability and synthesis. Global and specific dynamic impacts, including proteostatic responses, are due to direct inhibition of Hsp90 as well as indirect effects. As a result, a decrease was detected in most proteins that changed their levels, including known Hsp90 clients. Most likely, consequences of the role of Hsp90 in gene expression determined a global reduction in net de novo protein synthesis. This decrease appeared to be greater in magnitude than a concomitantly observed global increase in protein decay rates. Several novel putative Hsp90 clients were validated, and interestingly, protein families with critical functions, particularly the Hsp90 family and cofactors themselves as well as protein kinases, displayed strongly increased decay rates due to Hsp90 inhibitor treatment. Remarkably, an upsurge in survival pathways, involving molecular chaperones and several oncoproteins, and decreased levels of some tumour suppressors, have implications for anti-cancer therapy with Hsp90 inhibitors. The diversity of global effects may represent a paradigm of mechanisms that are operating to shield cells from proteotoxic stress, by promoting pro-survival and anti-proliferative functions. Data are available via ProteomeXchange with identifier PXD000537.", "claims": [{"id": "claim-method", "statement": "For each time point, log2 of quantified ratios were subjected to a two-tailed Welch t-test for one sample (null hypothesis H0: µ = 0) followed by correction for multiple testing (Benjamini-Hochberg). The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository [26] with the dataset identifier PXD000537.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24312219", "locator": "sections[7] \"T-test and clustering\" paragraph 2", "quote": "For each time point, log2 of quantified ratios were subjected to a two-tailed Welch t-test for one sample (null hypothesis H0: µ = 0) followed by correction for multiple testing (Benjamini-Hochberg)."}, {"asset": "source:pmid:24312219", "locator": "sections[4] \"stSILAC experiments\" paragraph 3", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository [26] with the dataset identifier PXD000537."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with identifier PXD000537.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:24312219", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD000537."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Hsp90 inhibition broadly perturbs the T-cell proteome, with most changed proteins decreasing; the mass-spectrometry source data are available through ProteomeXchange under identifier PXD000537.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:24312219", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "As a result, a decrease was detected in most proteins that changed their levels, including known Hsp90 clients."}, {"asset": "source:pmid:24312219", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD000537."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Hsp90 inhibition broadly perturbs the T-cell proteome, with most changed proteins decreasing; the mass-spectrometry source data are available through ProteomeXchange under identifier PXD000537.", "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:24312219"], "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:PXD000537"], "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:PXD000537"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:24312219", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0080425", "sha256": "sha256:8980d246615b02f531ae05e87fe4b2ed35d07c00496172c88645b5996e5b6e30", "bytes": 90945, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0080425", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3842317", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD000537", "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=PXD000537", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000537", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD000537.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD000537.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Dynamic impacts of the inhibition of the molecular chaperone Hsp90 on the T-cell proteome have implications for anti-cancer therapy.", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:24312219:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ee72baadc3abf5753c92dd98de67eaa8613eec7a0f294a6113400fd18ab85574", "bytes": 3346, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#pone-0080425-t001", "version": null, "note": "Selected GO terms associated with clusters with the largest number of proteins (stSILAC dataset).", "structure": {"pmcid": "PMC3842317", "section_index": 19, "section_title": "Effects of Hsp90 inhibition based on GO terms enriched in the clusters and on additional experiments", "row_count": 25, "column_count": 9}, "table": {"label": "Table 1", "caption": "Selected GO terms associated with clusters with the largest number of proteins (stSILAC dataset).", "rows": [["Cluster", "Model", "Class", "GO term", "Description", "FDR q-value", "Enrichment", "#genes", "Examples"], ["2", "[0,1,2]", "GOBP", "0006986", "response to unfolded protein", "5.21E-004", "7.59", "11", "Hsp70, Grp94, Hsp40 (DNAJB1)"], ["2", "[0,1,2]", "GOBP", "0006457", "protein folding", "1.97E-003", "4.62", "14", "PDIA's, BAG2, Hsp70, Grp94, Hsp40 (DNAJB1)"], ["2", "[0,1,2]", "GOCC", "0005788", "endoplasmic reticulum lumen", "6.76E-008", "11.64", "12", "PDIA's, PPI's, CANX, CALU, SERPINH1"], ["2", "[0,1,2]", "GOCC", "0031982", "vesicle", "3.24E-005", "3.69", "20", "GABARAPL2, MAP1LC3B, PDI's, CANX, SEC's"], ["6", "[0,0,1]", "GOBP", "0006457", "protein folding", "4.48E-004", "3.09", "22", "CCT chaperonins, Hsp90 & cofactors, HSPD1"], ["6", "[0,0,1]", "GOBP", "0051493", "regulation of cytoskeleton organization", "4.70E-004", "3.6", "18", "Arp2/3 subunits, AURKA, RAC1"], ["6", "[0,0,1]", "GOBP", "0016192", "vesicle-mediated transport", "1.43E-003", "2.33", "31", "RAB's, Sec proteins, vacuolar proteins, coatomer"], ["6", "[0,0,1]", "GOBP", "0019882", "antigen processing and presentation", "4.78E-003", "2.9", "18", "Proteasome subunits"], ["6", "[0,0,1]", "GOBP", "0007264", "small GTPase mediated signal transduction", "6.00E-003", "2.83", "18", "RAB's, RAC1, NRAS"], ["6", "[0,0,1]", "GOBP", "0006986", "response to unfolded protein", "3.74E-002", "3.23", "11", "Hsp70, Hsp90 families,"], ["6", "[0,0,1]", "GOBP", "0043069", "negative regulation of programmed cell death", "4.25E-002", "2.11", "22", "Hsp60, Hsp90, Proteasome, PRDX's, NRAS, USP47"], ["6", "[0,0,1]", "GOMF", "0008092", "cytoskeletal protein binding", "3.19E-003", "2.64", "25", "CAPG, CAPZ, ARL3, Arp2/3 proteins, spindle-associated proteins"], ["6", "[0,0,1]", "GOCC", "0000139", "Golgi membrane", "1.68E-005", "3.6", "21", "ARL3,Sec proteins, GOLGB1, coatomer, RAB's"], ["6", "[0,0,1]", "GOCC", "0005839", "proteasome core complex", "3.67E-003", "5.78", "7", "Proteasome"], ["7", "[0,0, –1]", "GOBP", "0016072", "rRNA metabolic process", "7.69E-004", "3.87", "17", "BOP1, processome, ribosomal proteins, DDX56"], ["7", "[0,0, –1]", "GOBP", "0006364", "rRNA processing", "1.64E-003", "3.74", "16", "BOP1, DDX56, processome, RRP1"], ["7", "[0,0, –1]", "GOBP", "0000723", "telomere maintenance", "2.68E-003", "6.31", "9", "RFC5, XRCC5, POLD1,POLD2, POLA1, PRIM1"], ["7", "[0,0, –1]", "GOBP", "0006271", "DNA strand elongation involved in DNA replication", "4.68E-002", "5.58", "7", "RFC5, XRCC5,POLD1,POLD2, POLA1, MCM4"], ["7", "[0,0, –1]", "GOCC", "0005730", "nucleolus", "1.52E-009", "3.08", "43", "RNA Helicases, processome subunits"], ["7", "[0,0, –1]", "GOCC", "0030684", "preribosome", "4.86E-002", "7.3", "5", "Small subunit processome"], ["11", "[0, –1, –2]", "GOBP", "0006998", "nuclear envelope organization", "2.56E-002", "6.57", "8", "Nucleoporins, CDK1"], ["11", "[0, –1, –2]", "GOMF", "0004672", "protein kinase activity", "1.29E-002", "3.86", "11", "CDK1, PRKDC,ILK, LCK, CHEK1"], ["11", "[0, –1, –2]", "GOMF", "0004674", "protein serine/threonine kinase activity", "1.30E-002", "4.24", "10", "MAP4K4 ; PRKDC ; CDK11B ; ILK ; CDK1 ; TAOK3 ; MAP2K4 ; CHEK1 ; NEK9 ; ADRBK1"], ["11", "[0, –1, –2]", "GOMF", "0005524", "ATP binding", "2.06E-002", "2.16", "31", "Helicases, Kinases"]], "row_count": 25, "column_count": 9, "numeric_cells": 154, "header_rows": 1, "locator": "section[19]/table-wrap[1]#pone-0080425-t001"}}], "gaps": ["asset:data:geo:PXD000537 not downloaded", "asset:data:geo:PXD000537 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "welch_t_test", "label": "Group comparison", "dsl_operations": ["welch_t"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "reordered", "quote": "For each time point, log2 of quantified ratios were subjected to a two-tailed Welch t-test for one sample (null hypothesis H0: µ = 0) followed by correction for multiple testing (Benjamini-Hochberg). The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository [26] with the dataset identifier PXD000537."}}, {"id": "method-2", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "PPI"}}], "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": ["welch_t"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: welch_t_test."}, "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": ["PXD000537"], "resolved_accessions": ["PXD000537"], "statements": ["Data are available via ProteomeXchange with identifier PXD000537."], "basis": "The paper names PXD000537 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["welch_t"], "assets": ["source:pmid:24312219", "data:geo:PXD000537", "asset:table:pmid:24312219:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD000537"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:54Z", "independence": "same_provider"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 182593, "completion_tokens": 3260, "cached_tokens": 136972}}, "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:24312219", "type": "paper", "label": "pmid:24312219"}, {"id": "source:pmid:24312219", "type": "manuscript", "label": "PMID 24312219 full text"}, {"id": "data:geo:PXD000537", "type": "dataset", "label": "GEO PXD000537"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:24312219", "type": "paper", "label": "pmid:24312219"}, {"id": "source:pmid:24312219", "type": "manuscript", "label": "PMID 24312219 full text"}, {"id": "data:geo:PXD000537", "type": "dataset", "label": "GEO PXD000537"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-24312219", "type": "extraction", "used": ["source:pmid:24312219"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD000537", "type": "accession_resolution", "used": ["data:geo:PXD000537"], "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:24312219", "parent_hash": "sha256:88209cd6830a3e536d75e76b1ca4ecd279ce786cac19ffa62b9918d9cd782ce1", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD000537 licence not read", "asset:data:geo:PXD000537 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["a cell cycle arrest, which was detected by a flow cytometry analysis as an enrichment of cells blocked e", "24h with 1 µM geldanamycin (GA) assessed by flow cytometry and western blot analysis. A) Staining of li"], "order_basis": "paper_text_order:3306", "id": "assay:1"}, {"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": ["lls in S phase. We assessed the induction of apoptosis by immunoblotting, detecting cleavage of the", "(PARP1), but observed no strong induction of apoptosis under the assay conditions (Fig. S1C). The d", "ntary Materials Figure S1 Cell viability and apoptosis of Jurkat cells treated for 24h with 1 µM ge", "by immunoblotting, detecting cleavage of the caspase substrate poly (ADP-ribose) polymerase (PARP"], "order_basis": "paper_text_order:3494", "id": "assay:2"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["anamycin (GA) assessed by flow cytometry and western blot analysis. A) Staining of live cells with 7-a", "ic cells was visible (n = 2). C) Anti-PARP-1 western blot analysis. PARP-1 (110 kDa) is cleaved by Cas", "e. We assessed the induction of apoptosis by immunoblotting, detecting cleavage of the caspase substrate"], "order_basis": "paper_text_order:3507", "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": 0.99, "evidence": ["axis) was compared with the one obtained for HeLa cells (1), with the one obtained for erythro", "e one obtained for erythroleukemia cell line K562, for the breast cancer line MD-MBA231, and f"], "order_basis": "paper_text_order:13755", "id": "assay:4"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["welch_t"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["For each time point, log2 of quantified ratios were subjected to a two-tailed Welch t-test for one sample (null hypothesis H0: µ = 0) followed by correction for multiple testing (Benjamini-Hochberg). The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository [26] with the dataset identifier PXD000537."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:34:24+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}}}