{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33318985", "kind": "science-record", "revision": 8, "content_hash": "sha256:58fd2dac7ed886627ee3ea4009896688a0ee7ff2e40051085210c6ec4eb244e9", "created_at": "2026-11-01T15:41:19Z", "updated_at": "2026-11-01T22:45:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "RNA-Seq transcriptome data of human cells infected with influenza A/Puerto Rico/8/1934 (H1N1) virus.", "doi": "10.1016/j.dib.2020.106604", "pmid": "33318985", "authors": ["Evgenii Zhuravlev", "Mariia Sergeeva", "Sergey Malanin", "Rinat Amirkhanov", "Dmitriy Semenov", "Tatiana Grigoryeva", "Andrey Komissarov", "Grigory Stepanov"], "journal": "Data in brief", "year": 2020, "abstract": "Human influenza remains a serious public health problem. This data article reports the transcriptome analysis data of human cell lines infected with influenza A/Puerto Rico/8/1934 (H1N1) virus. Mock-infected cells were included as controls. Human embryonic fibroblasts (MRC-5) and immortalized cell lines (A549, HEK293FT, WI-38 VA-13) were selected for RNA sequencing using Illumina NextSeq500 platform. Raw data were applied to the bioinformatic pipeline, which includes quality control with FastQC and MultiQC, adapter and quality trimming with Cutadapt, filtering to the genome of influenza A with STAR, transcript quantification with Salmon tool (GRCh38_RefSeq_Transcripts). Differential expressed genes were identified using R package DESeq2 with FDR-adjusted p-value < 0.001 and absolute value of log2(FC) > 1. Lists of differentially expressed genes is provided. The raw and processed RNA-seq data presented in this article were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511 .", "claims": [{"id": "claim-method", "statement": "To study genes involved in cellular response to influenza A virus infection, differential expressed genes were identified using R package DESeq2 with a FDR-adjusted p-value < 0.001 and the absolute value of a log2(FC) > 1 [9]. The raw data (FASTQ files) were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511 [1].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33318985", "locator": "sections[10] \"Differential expression analysis\" paragraph 2", "quote": "To study genes involved in cellular response to influenza A virus infection, differential expressed genes were identified using R package DESeq2 with a FDR-adjusted p-value < 0.001 and the absolute value of a log2(FC) > 1 [9]."}, {"asset": "source:pmid:33318985", "locator": "sections[3] \"Data Description\" paragraph 2", "quote": "The raw data (FASTQ files) were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511 [1]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Both raw and processed RNA-seq data were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33318985", "locator": "sections[1] \"Specifications Table\" paragraph 2", "quote": "Both raw and processed RNA-seq data were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511."}], "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:33318985"], "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:E-MTAB-9511"], "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:E-MTAB-9511"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33318985", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2020.106604", "sha256": "sha256:010241319c107bd9a451199f07777f84653d6f77436f872bfee77c9522ee3401", "bytes": 13583, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2020.106604", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7725734", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-9511", "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=E-MTAB-9511", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-9511", "version": null, "note": "Both raw and processed RNA-seq data were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Both raw and processed RNA-seq data were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:04Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33318985:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bfe69d89254af699483c976f343594ee7a46b96b91d025a1618f8fa0c7a51aa9", "bytes": 1684, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#utbl0001", "version": null, "note": null, "structure": {"pmcid": "PMC7725734", "section_index": 1, "section_title": "Specifications Table", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject", "Molecular biology, Biochemistry, Virology"], ["Specific subject area", "NGS, Transcriptomics"], ["Type of data", "FASTQ filesProcessed data filesTableChart"], ["How data were acquired", "Sequencing data acquired by Illumina NextSeq 500 platform (1 × 75 bp single-read sequencing)"], ["Data format", "Raw and Processed Data"], ["Parameters for data collection", "MRC-5, WI-38 VA-13, A549 and HEK293FT human cells were infected with influenza A/Puerto Rico/8/1934 virus at a dose of 1 TCID50/cell and incubated at 37°С for 48 h. Mock-infected cells were included as controls."], ["Description of data collection", "Following the incubation period, the cell monolayer was directly lysed. Total RNA was extracted, then polyA RNA fraction was enriched and used for construction cDNA libraries using a NEBNext Ultra II Directional RNA library preparation kit and NEBNext mRNA Magnetic Isolation Module. Massive parallel sequencing was performed on a NextSeq Illumina 500 platform using NextSeq 500/550 High Output v2.5 Kit (75 cycles)."], ["Data source location", "Institute of Chemical Biology and Fundamental Medicine, Siberian Branch of the Russian Academy of Sciences, Novosibirsk, Russia"], ["Data accessibility", "Both raw and processed RNA-seq data were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511.Repository name: ArrayExpressData identification number: E-MTAB-9511Direct URL to data: https://www.ebi.ac.uk/arrayexpress/experiments/E-MTAB-9511/"]], "row_count": 9, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#utbl0001"}}, {"id": "asset:table:pmid:33318985:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5b36a41d5591bd831b014a490ad43d7e8fef2fd5861f9847307d5066f236d14c", "bytes": 1016, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl0001", "version": null, "note": "Number of raw, trimmed and filtered reads of 16 cDNA libraries of mock-infected (0h) and infected with influenza A virus (48h) cell lines (MRC-5, WI-38 VA-13, A549 and HEK293FT).", "structure": {"pmcid": "PMC7725734", "section_index": 3, "section_title": "Data Description", "row_count": 17, "column_count": 5}, "table": {"label": "Table 1", "caption": "Number of raw, trimmed and filtered reads of 16 cDNA libraries of mock-infected (0h) and infected with influenza A virus (48h) cell lines (MRC-5, WI-38 VA-13, A549 and HEK293FT).", "rows": [["Sample name", "Biological replicate", "M Reads (Raw)", "M Reads(after trimming)", "M Seqs(after filtering)"], ["MRC-5_0h", "M01", "11.3", "11.3", "11.3"], ["M02", "11.6", "11.6", "11.6"], ["MRC-5_48h", "M481", "11.4", "11.3", "10.0"], ["M482", "11.5", "11.4", "10.1"], ["WI-38 VA-13_0h", "W01", "13.8", "13.8", "13.8"], ["W02", "13.9", "13.9", "13.9"], ["WI-38 VA-13_48h", "W481", "13.9", "13.9", "12.6"], ["W482", "14.1", "14.1", "12.4"], ["A549_0h", "A01", "12.7", "12.7", "12.7"], ["A02", "10.6", "10.6", "10.6"], ["A549_48h", "A481", "11.4", "11.4", "8.9"], ["A482", "11.6", "11.5", "8.9"], ["HEK293FT_0h", "H01", "13.0", "13.0", "13.0"], ["H02", "13.6", "13.6", "13.6"], ["HEK293FT_48h", "H481", "14.1", "14.1", "13.7"], ["H482", "13.5", "13.4", "12.7"]], "row_count": 17, "column_count": 5, "numeric_cells": 72, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl0001"}}], "gaps": ["asset:data:geo:E-MTAB-9511 not downloaded", "asset:data:geo:E-MTAB-9511 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": "reordered", "quote": "To study genes involved in cellular response to influenza A virus infection, differential expressed genes were identified using R package DESeq2 with a FDR-adjusted p-value < 0.001 and the absolute value of a log2(FC) > 1 [9]. The raw data (FASTQ files) were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511 [1]."}}], "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": ["E-MTAB-9511"], "resolved_accessions": ["E-MTAB-9511"], "statements": ["Both raw and processed RNA-seq data were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511."], "basis": "The paper names E-MTAB-9511 in European Nucleotide Archive via the ArrayExpress partner repository 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:33318985", "data:geo:E-MTAB-9511", "asset:table:pmid:33318985:1", "asset:table:pmid:33318985:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-9511"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:05Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 12529, "completion_tokens": 1138, "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:33318985", "type": "paper", "label": "pmid:33318985"}, {"id": "source:pmid:33318985", "type": "manuscript", "label": "PMID 33318985 full text"}, {"id": "data:geo:E-MTAB-9511", "type": "dataset", "label": "GEO E-MTAB-9511"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33318985", "type": "paper", "label": "pmid:33318985"}, {"id": "source:pmid:33318985", "type": "manuscript", "label": "PMID 33318985 full text"}, {"id": "data:geo:E-MTAB-9511", "type": "dataset", "label": "GEO E-MTAB-9511"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33318985", "type": "extraction", "used": ["source:pmid:33318985"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-9511", "type": "accession_resolution", "used": ["data:geo:E-MTAB-9511"], "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:33318985", "parent_hash": "sha256:521312e3a6e17213c7b7ef3384bff345d5037cecb6eb8163b4c5eda9de3b886d", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:E-MTAB-9511 licence not read", "asset:data:geo:E-MTAB-9511 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": ["RNA-Seq transcriptome data of human cells infected w", "sed genes is provided. The raw and processed RNA-seq data presented in this article were deposite", "49, HEK293FT, WI-38 VA-13) were selected for RNA sequencing using Illumina NextSeq500 platform. Raw data", "RNA-Seq transcriptome data of human cells infected with influenza"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["oblasts (MRC-5) and immortalized cell lines (A549, HEK293FT, WI-38 VA-13) were selected for RN"], "order_basis": "paper_text_order:362", "id": "assay:2"}, {"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": ["To study genes involved in cellular response to influenza A virus infection, differential expressed genes were identified using R package DESeq2 with a FDR-adjusted p-value < 0.001 and the absolute value of a log2(FC) > 1 [9]. The raw data (FASTQ files) were deposited to the European Nucleotide Archive via the ArrayExpress partner repository with the dataset accession number E-MTAB-9511 [1]."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T02:12:40+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}}}