{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26697359", "kind": "science-record", "revision": 4, "content_hash": "sha256:b2f9a03f77487036177bd680e3f5857023016d2001709e4d29de7ca3547d20d8", "created_at": "2026-11-01T15:40:15Z", "updated_at": "2026-11-01T21:20:21Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptome analysis of Streptococcus pneumoniae D39 in the presence of cobalt.", "doi": "10.1016/j.gdata.2015.08.033", "pmid": "26697359", "authors": ["Irfan Manzoor", "Sulman Shafeeq", "Oscar P Kuipers"], "journal": "Genomics data", "year": 2015, "abstract": "Cobalt (Co(2 +)) is an important transition metal ion that plays a vital role in cellular physiology of bacteria. The role of Co(2 +) in the regulation of several genes/operons in Streptococcus pneumoniae has recently been reported [1]. The data described in this article relate to the genome-wide transcriptional profiling of Streptococcus pneumoniae D39, either in the presence or absence of 0.5 mM Co(2 +) in chemically defined medium (CDM) using DNA microarray analysis. Genes belonging to a broad range of cellular processes such as virulence, transport and efflux systems, stress response and surface attachment were differentially expressed in the presence of Co(2 +). We used transcriptional lacZ assays and electrophoretic mobility shift assays (EMSAs) to confirm our results [1]. The dataset is publicly available at the Gene Expression Omnibus (GEO) repository (http://www.ncbi.nlm.nih.gov/geo/) with accession number GSE57696.", "claims": [{"id": "claim-method", "statement": "Finally, Cyber-T was used to analyze the data generated using Microprep for the identification of statistically significant differentially expressed genes.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697359", "locator": "sections[8] \"Microarray data analysis\" paragraph 2", "quote": "Finally, Cyber-T was used to analyze the data generated using Microprep for the identification of statistically significant differentially expressed genes."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw and processed DNA microarray dataset has been deposited in the Gene Expression Omnibus (GEO) database and can be accessed under following link: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE57696.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26697359", "locator": "sections[2] \"Direct link to deposited data\" paragraph 2", "quote": "The raw and processed DNA microarray dataset has been deposited in the Gene Expression Omnibus (GEO) database and can be accessed under following link: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE57696."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:26697359"], "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:GSE57696"], "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:GSE57696"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26697359", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2015.08.033", "sha256": "sha256:308559efec88a0ba58b46b07234ef9fcb3d650622cb0ab9ddb1b3adf6561e240", "bytes": 10899, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2015.08.033", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4664747", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE57696", "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=GSE57696", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57696", "version": null, "note": "The raw and processed DNA microarray dataset has been deposited in the Gene Expression Omnibus (GEO) database and can be accessed under following link: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE57696.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw and processed DNA microarray dataset has been deposited in the Gene Expression Omnibus (GEO) database and can be accessed under following link: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE57696.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1386903", "GSM1386904"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "11484", "taxon": "Streptococcus pneumoniae D39", "title": "Low Co vs high Co in CDM", "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:26697359:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6f4909ada47dc6a57450399bbf95ebac1540a40b9ef3d6fb3812d920cf04a93f", "bytes": 648, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0020", "version": null, "note": null, "structure": {"pmcid": "PMC4664747", "section_index": 1, "section_title": "Specifications", "row_count": 8, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Organism/cell line/tissue", "Streptococcus pneumoniae strain D39"], ["Sex", "N/A"], ["Sequencer or array type", "Oligo-based DNA microarray"], ["Data format", "Raw and processed"], ["Experimental factors", "0 mM Co2 + versus 0.5 mM Co2 +"], ["Experimental features", "Differentially expressed genes were identified by microarray comparison of D39 wild-type grown in CDM + 0 mM Co2 + to D39 wild-type grown in CDM + 0.5 mM Co2 + in CDM"], ["Consent", "N/A"], ["Sample source location", "Groningen, The Netherlands"]], "row_count": 8, "column_count": 2, "numeric_cells": 3, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0020"}}, {"id": "asset:table:pmid:26697359:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d3c5f42c2aa952841d33b02adb207b8edfcc7ef38b9b2a6964603094b36b8d66", "bytes": 1042, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#t0005", "version": null, "note": "Summary of computational tools used to analyze DNA microarray data.", "structure": {"pmcid": "PMC4664747", "section_index": 8, "section_title": "Microarray data analysis", "row_count": 7, "column_count": 3}, "table": {"label": "Table 1", "caption": "Summary of computational tools used to analyze DNA microarray data.", "rows": [["Software", "Purpose", "URL"], ["Microprep[8]", "A cDNA microarray data pre-processing framework", "http://www.molgenrug.nl/index.php/molgensoftware"], ["CyberT", "Amplementation of a variant of t-test", "http://bioinformatics.biol.rug.nl/cybert/index.shtml"], ["Genome2D [9]", "A visualization tool for the rapid analysis of bacterial transcriptome data", "http://genome2d.molgenrug.nl/"], ["FIVA [10]", "Functional Information Viewer and Analyzer extracting biological knowledge from transcriptome data of prokaryotes", "http://bioinformatics.biol.rug.nl/standalone/fiva/"], ["Projector [11]", "Automatic contig mapping for gap closure purposes", "http://bamics2.cmbi.ru.nl/websoftware/projector2/projector2_start.php"], ["PePPER [12]", "A webserver for prediction of prokaryote promoter elements and regulons", "http://pepper.molgenrug.nl/"]], "row_count": 7, "column_count": 3, "numeric_cells": 5, "header_rows": 1, "locator": "section[8]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:26697359:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:21482a1922b1df3b23f0812b14bb70a6bcbf94c1c5803098c24ebd20e68ae011", "bytes": 2108, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t0010", "version": null, "note": "Summary of downregulated genes in transcriptome comparison of S. pneumoniae D39 wild-type grown in CDM plus 0 mM Co2 + and CDM plus 0.5 mM Co2 +.", "structure": {"pmcid": "PMC4664747", "section_index": 9, "section_title": "Discussion", "row_count": 25, "column_count": 4}, "table": {"label": "Table 2", "caption": "Summary of downregulated genes in transcriptome comparison of S. pneumoniae D39 wild-type grown in CDM plus 0 mM Co2 + and CDM plus 0.5 mM Co2 +.", "rows": [["Gene taga", "Functionb", "Ratioc", "P-value"], ["SPD0053", "Amidophosphoribosyltransferase", "− 2.0", "2.09E-06"], ["SPD0054", "Phosphoribosylformylglycinamidine cyclo-ligase", "− 2.0", "5.29E-08"], ["SPD0055", "Phosphoribosylglycinamide formyltransferase", "− 2.2", "1.12E-05"], ["SPD0056", "VanZ protein", "− 2.4", "6.93E-05"], ["SPD0057", "Bifunctional purine biosynthesis protein, PurH", "− 2.5", "1.28E-07"], ["SPD0187", "Anaerobic ribonucleoside-triphosphate reductase, NrdD", "− 11.2", "2.93E-14"], ["SPD0188", "Hypothetical protein", "− 4.3", "2.47E-10"], ["SPD0189", "Acetyltransferase, GNAT family protein", "− 11.0", "5.44E-10"], ["SPD0190", "Anaerobic ribonucleoside-triphosphate reductase, NrdG", "− 10.5", "1.22E-15"], ["SPD0191", "Hypothetical protein", "− 8.3", "1.34E-07"], ["SPD0458", "Heat-inducible transcription repressor, HrcA", "− 2.5", "1.09E-10"], ["SPD0459", "Heat shock protein, GrpE", "− 2.1", "4.82E-09"], ["SPD0558", "Cell wall-associated serine protease, PrtA", "− 16.6", "3.89E-14"], ["SPD1461", "Mn2 + ABC transporter, ATP binding protein, PsaB", "− 8.7", "2.18E-14"], ["SPD1462", "Manganese ABC transporter, permease protein, PsaC", "− 8.7", "2.18E-14"], ["SPD1594", "XRE family Transcriptional regulator", "− 3.1", "7.14E-09"], ["SPD1636", "Zn2 +-containing alcohol dehydrogenase", "− 8.4", "2.05E-14"], ["SPD1637", "MerR family transcriptional regulator", "− 11.0", "1.41E-10"], ["SPD1638", "Cation efflux system, CzcD", "− 20.8", "0"], ["SPD1965", "Choline binding protein, PcpA", "− 5.0", "5.48E-06"], ["SPD2044", "Rod shape-determining protein, MreD", "− 3.0", "8.75E-11"], ["SPD2046", "Co2 + ABC transporter, permease protein, CbiQ", "− 2.0", "1.22E-09"], ["SPD2049", "CDP-diacylglycerol-glycerol-3-phosphate 3-phosphatidyltransferase PgsA", "− 2.0", "1.13E-06"], ["SPD2052", "Hypothetical protein", "− 2.0", "6.84E-09"]], "row_count": 25, "column_count": 4, "numeric_cells": 73, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:26697359:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b6ad06e9d652dee7b254ea020c4418dfa0f9333c14630d4acd4b97b32f686ba1", "bytes": 1140, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#t0015", "version": null, "note": "Summary of upregulated genes in transcriptome comparison of S. pneumoniae D39 wild-type grown in CDM plus 0 mM Co2 + and CDM plus 0.5 mM Co2 +.", "structure": {"pmcid": "PMC4664747", "section_index": 9, "section_title": "Discussion", "row_count": 14, "column_count": 4}, "table": {"label": "Table 3", "caption": "Summary of upregulated genes in transcriptome comparison of S. pneumoniae D39 wild-type grown in CDM plus 0 mM Co2 + and CDM plus 0.5 mM Co2 +.", "rows": [["Gene taga", "Functionb", "Ratioc", "P-value"], ["SPD0801", "Hypothetical protein", "2.01", "1.29E-05"], ["SPD0910", "Serine hydroxymethyltransferase", "2.17", "1.69E-11"], ["SPD1018", "Immunoglobulin A1 protease precursor", "2.08", "2.29E-06"], ["SPD1039", "Phosphoenolpyruvate-protein phosphotransferase", "2.05", "5.54E-11"], ["SPD1053", "Galactose-6-phosphate isomerase, LacA subunit", "2.45", "5.83E-07"], ["SPD1294", "Hypothetical protein", "2.65", "1.98E-11"], ["SPD1355", "Hypothetical protein", "2.10", "7.71E-01"], ["SPD1466", "ABC transporter, ATP-binding protein", "2.02", "4.65E-09"], ["SPD1588", "Hypothetical protein", "2.29", "3.09E-07"], ["SPD 1598", "Hypothetical protein", "2.16", "2.62E-08"], ["SPD 1596", "Tryptophan synthase, alpha subunit", "2.24", "2.36E-08"], ["SPD 1727", "Hypothetical protein", "2.39", "2.61E-07"], ["SPD 1728", "Hypothetical protein", "2.26", "1.25E-10"]], "row_count": 14, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[9]/table-wrap[2]#t0015"}}], "gaps": ["asset:data:geo:GSE57696 not downloaded", "asset:data:geo:GSE57696 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Cyber-T with false discovery rate (FDR) correction", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Finally, Cyber-T was used to analyze the data generated using Microprep for the identification of statistically significant differentially expressed genes."}}], "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 (Cyber-T with false discovery rate (FDR) correction), 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": ["GSE57696"], "resolved_accessions": ["GSE57696"], "statements": ["The raw and processed DNA microarray dataset has been deposited in the Gene Expression Omnibus (GEO) database and can be accessed under following link: http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE57696."], "basis": "The paper names GSE57696 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:26697359", "data:geo:GSE57696", "asset:table:pmid:26697359:1", "asset:table:pmid:26697359:2", "asset:table:pmid:26697359:3", "asset:table:pmid:26697359:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE57696"]}, "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": "2026-10-31T18:26:47Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 28218, "completion_tokens": 3366, "cached_tokens": 2072}}, "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:26697359", "type": "paper", "label": "pmid:26697359"}, {"id": "source:pmid:26697359", "type": "manuscript", "label": "PMID 26697359 full text"}, {"id": "data:geo:GSE57696", "type": "dataset", "label": "GEO GSE57696"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26697359", "type": "paper", "label": "pmid:26697359"}, {"id": "source:pmid:26697359", "type": "manuscript", "label": "PMID 26697359 full text"}, {"id": "data:geo:GSE57696", "type": "dataset", "label": "GEO GSE57696"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26697359", "type": "extraction", "used": ["source:pmid:26697359"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE57696", "type": "accession_resolution", "used": ["data:geo:GSE57696"], "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:26697359", "parent_hash": "sha256:0466228f209ab281a73983b128b840b017dfde4abd1058f9c2bbac7ca1fd9912", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE57696 licence not read", "asset:data:geo:GSE57696 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["in chemically defined medium (CDM) using DNA microarray analysis. Genes belonging to a broad range o"], "order_basis": "paper_text_order:491", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:19:32+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}}}