{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33369450", "kind": "science-record", "revision": 8, "content_hash": "sha256:4bc9b972d22513e18098ca13e0a81b5320d5e7c855e76d86d67e62ef25af70a3", "created_at": "2026-11-01T15:41:20Z", "updated_at": "2026-11-01T22:45:52Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Omics Integration Analysis Unravel the Landscape of Driving Mechanisms of Colorectal Cancer.", "doi": "10.31557/APJCP.2020.21.12.3539", "pmid": "33369450", "authors": ["Fatemeh Nikmanesh", "Shamim Sarhadi", "Mehdi Dadashpour", "Yazdan Asghari", "Nosratollah Zarghami"], "journal": "Asian Pacific journal of cancer prevention : APJCP", "year": 2020, "abstract": "Colorectal cancer (CRC) is one of the most malignant cancers and results in a substantial rate of morbidity and mortality. Diagnosis of this malignancy in early stages increases the chance of effective treatment. High-throughput data analyses reveal omics signatures and also provide the possibility of developing computational models for early detection of this disease. Such models would be able to use as complementary tools for early detection of different types of cancers including CRC. In this study, using gene expression data, the Flux balance analysis (FBA) applied to decode metabolic fluxes in cancer and normal cells. Moreover, transcriptome and genome analyses revealed driver agents of CRC in a biological network scheme. By applying comprehensive publicly available data from TCGA, different aspect of CRC regulome including the regulatory effect of gene expression, methylation, microRNA, copy number aberration and point mutation profile over protein levels investigated and the results provide a regulatory picture underlying CRC. Compiling omics profiles indicated snapshots of changes in different omics levels and flux rate of CRC. In conclusion, considering obtained CRC signatures and their role in biological operating systems of cells, the results suggest reliable driver regulatory modules that could potentially serve as biomarkers and therapeutic targets and furthermore expand our understanding of driving mechanisms of this disease.<br />.", "claims": [{"id": "claim-method", "statement": "To find differentially expressed genes (DEGs) in CRC cells in comparison with the normal cells, gene expression microarray data sets preprocessed by FRMA package (McCall et al., 2010) in R and then limma (Smyth, 2005) was used to develop a linear model for finding DEGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33369450", "locator": "sections[2] \"Materials and Methods\" paragraph 13", "quote": "To find differentially expressed genes (DEGs) in CRC cells in comparison with the normal cells, gene expression microarray data sets preprocessed by FRMA package (McCall et al., 2010) in R and then limma (Smyth, 2005) was used to develop a linear model for finding DEGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Gene expression microarray data related to colorectal cancer were downloaded from the Gene Expression Omnibus (GEO) database. Microarray data platform was Affymetrix Human Genome U133 Plus 2.0 Array (GPL570) for both datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33369450", "locator": "sections[2] \"Materials and Methods\" paragraph 3", "quote": "Gene expression microarray data related to colorectal cancer were downloaded from the Gene Expression Omnibus (GEO) database. Microarray data platform was Affymetrix Human Genome U133 Plus 2.0 Array (GPL570) for both datasets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:33369450"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33369450", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.31557/APJCP.2020.21.12.3539", "sha256": "sha256:c77de111c1d50b444c8379310953785806a9049b346e134c96b832d78d2fd171", "bytes": 40519, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.31557/APJCP.2020.21.12.3539", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8046321", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33369450:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:38ae5f940dada5690763847e4164fda5ce682dbf104c7737f290a709c45d71ba", "bytes": 580, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Summary of CRC Data Used in This Study", "structure": {"pmcid": "PMC8046321", "section_index": 3, "section_title": "Results", "row_count": 13, "column_count": 2}, "table": {"label": "Table 1", "caption": "Summary of CRC Data Used in This Study", "rows": [["Gene expression microarray data"], ["Source", "Number of samples"], ["GSE8671", "64 (32 normal, 32 cancer)"], ["GSE23878", "59 (24 normal, 35 cancer)"], ["Copy number aberration data"], ["Source", "Number of samples"], ["Cbioportal", "1354"], ["Point mutation data"], ["Source", "Number of samples"], ["Cbioportal", "1596"], ["Data applied for regulome analyses"], ["Source", "Number of samples"], ["TCGA", "621"]], "row_count": 13, "column_count": 2, "numeric_cells": 7, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33369450:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4a7cc47b4201d33685ebb523a91d336f607d4ca2014ba1db4c7d23fe72b16dc9", "bytes": 1215, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#T2", "version": null, "note": "Altered Reactions in the Subsystems for Colorectal Cancerous Model Compared to the Normal Model", "structure": {"pmcid": "PMC8046321", "section_index": 3, "section_title": "Results", "row_count": 15, "column_count": 3}, "table": {"label": "Table 2", "caption": "Altered Reactions in the Subsystems for Colorectal Cancerous Model Compared to the Normal Model", "rows": [["Altered Subsystem", "Altered Reaction", "Alteration type (Tumor Model)"], ["Vitamin A Metabolism", "Retinol Dehydrogenase", "Decreased"], ["Transport Extracellular", "Bicarbonate Transport", "Decreased"], ["Pyrimidine Catabolism", "Cytosine Deaminase", "Decreased"], ["Glutathione Metabolism", "Glutathione Peroxidase", "Decreased"], ["Transport Mitochondrial", "ADP/ATP Transporter", "Decreased"], ["Fatty Acid Elongation", "Fatty Acyl-CoA Desaturase", "Decreased"], ["Glutamate Metabolism", "Glutamine Synthetase", "Decreased"], ["Oxidative Phosphorylation", "ATP Synthase", "Decreased"], ["Galactose Metabolism", "UTP-Glucose-1-Phosphate Uridylyltransferase", "Decreased"], ["Nucleotides Metabolism", "Nucleoside-Diphosphate Kinase", "Increased"], ["Pyruvate Metabolism", "L-Lactate Dehydrogenase", "Increased"], ["Purine Metabolism", "Adenosine Deaminase", "Increased"], ["Glycolysis/Gluconeogenesis", "Glucose-6-Phosphate Isomerase", "Increased"], ["Hyaluronan Metabolism", "Hyaluronan Synthase", "Increased"]], "row_count": 15, "column_count": 3, "numeric_cells": 2, "header_rows": 1, "locator": "section[3]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:33369450:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6df0ac715937c61da480dfbfd76a307207eb0b54df53ed7caf373b94d533f953", "bytes": 1238, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[3]#T3", "version": null, "note": "The most Impacted Pathways that Enriched by Reactom Geneset", "structure": {"pmcid": "PMC8046321", "section_index": 3, "section_title": "Results", "row_count": 12, "column_count": 4}, "table": {"label": "Table 3", "caption": "The most Impacted Pathways that Enriched by Reactom Geneset", "rows": [["Under-expressed pathways", "Over expressed pathways"], ["NAME", "FDR (q-val)", "NAME", "FDR q-val"], ["Reactome_immunoregulatory_interactions_between_a_lymphoid_and_a_non_lymphoid_cell", "0", "Reactome_dna_replication", "0"], ["Reactome_g_alpha_s_signalling_events", "0.000434", "Reactome_mitotic_m_m_g1_phases", "0"], ["Reactome_cgmp_effects", "0.002634", "Reactome_cell_cycle_mitotic", "0"], ["Reactome_class_a1_rhodopsin_like_receptors", "0.002183", "Reactome_cell_cycle", "0"], ["Reactome_gpcr_downstream_signaling", "0.001746", "Reactome_g2_m_checkpoints", "0"], ["Reactome_nitric_oxide_stimulates_guanylate_cyclase", "0.001455", "Reactome_mitotic_prometaphase", "0"], ["Reactome_generation_of_second_messenger_molecules", "0.00283", "Reactome_activation_of_atr_in_response_to_replication_stress", "0"], ["Reactome_tcr_signaling", "0.003662", "Reactome_dna_strand_elongation", "0"], ["Reactome_gpcr_ligand_binding", "0.003533", "Reactome_s_phase", "0"], ["Reactome_glucagon_type_ligand_receptors", "0.003693", "Reactome_activation_of_the_pre_replicative_complex", "0"]], "row_count": 12, "column_count": 4, "numeric_cells": 20, "header_rows": 2, "locator": "section[3]/table-wrap[3]#T3"}}, {"id": "asset:table:pmid:33369450:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2c7a4661a158f90d90ef2d21330a9ef96813ed70a185826bc6cce39ec6c890f3", "bytes": 1050, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[4]#T4", "version": null, "note": "The Most Important Hub Nodes in Network Created by Transcriptomic and Genomic Signatures", "structure": {"pmcid": "PMC8046321", "section_index": 3, "section_title": "Results", "row_count": 11, "column_count": 9}, "table": {"label": "Table 4", "caption": "The Most Important Hub Nodes in Network Created by Transcriptomic and Genomic Signatures", "rows": [["DEGs network", "Point mutation network", "CNA network"], ["Label", "Degree", "Betweenness", "Label", "Degree", "Betweenness", "Label", "Degree", "Betweenness"], ["ITGA4", "402", "819295.4", "TP53", "556", "596332.47", "MYC", "849", "492887.81"], ["TRIP13", "75", "146383.85", "EP300", "293", "252816.94", "BCL2L1", "66", "54377.5"], ["PTP4A3", "73", "138377.42", "CREBBP", "196", "127599.6", "DNMT3B", "35", "28506.19"], ["CCNB1", "57", "127533.74", "CTNNB1", "194", "182161.38", "RBFOX1", "29", "25624.5"], ["NR3C1", "54", "159978.78", "SMARCA4", "100", "93783.27", "GNAS", "28", "21732.5"], ["PTN", "49", "79172.5", "SMAD4", "100", "78005.5", "ASXL1", "11", "5978"], ["THRB", "46", "89620.76", "APC", "89", "96969.15", "FLT3", "8", "5973.5"], ["EPB41L3", "45", "94762.82", "FBXW7", "82", "85781.6", "POLR2A", "3", "6998.88"], ["PCK1", "45", "60748.27", "MTOR", "68", "59152.88", "EZH2", "3", "1577.2"]], "row_count": 11, "column_count": 9, "numeric_cells": 58, "header_rows": 1, "locator": "section[3]/table-wrap[4]#T4"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To find differentially expressed genes (DEGs) in CRC cells in comparison with the normal cells, gene expression microarray data sets preprocessed by FRMA package (McCall et al., 2010) in R and then limma (Smyth, 2005) was used to develop a linear model for finding DEGs."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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: limma_voom."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Gene expression microarray data related to colorectal cancer were downloaded from the Gene Expression Omnibus (GEO) database. Microarray data platform was Affymetrix Human Genome U133 Plus 2.0 Array (GPL570) for both datasets."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33369450", "asset:table:pmid:33369450:1", "asset:table:pmid:33369450:2", "asset:table:pmid:33369450:3", "asset:table:pmid:33369450:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:48Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 30473, "completion_tokens": 2483, "cached_tokens": 777}}, "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:33369450", "type": "paper", "label": "pmid:33369450"}, {"id": "source:pmid:33369450", "type": "manuscript", "label": "PMID 33369450 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33369450", "type": "paper", "label": "pmid:33369450"}, {"id": "source:pmid:33369450", "type": "manuscript", "label": "PMID 33369450 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33369450", "type": "extraction", "used": ["source:pmid:33369450"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33369450", "parent_hash": "sha256:882fd35013d795b666a141225ec722c4df21d2c095e2548630d3bc7e0fbdb132", "fork_of": null, "generation": 7}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["and Methods Data collection Gene expression microarray data related to colorectal cancer were downl", "the Gene Expression Omnibus (GEO) database. Microarray data platform was Affymetrix Human Genome U1", "used to portrait regulome signatures of CRC. Microarray raw data were preprocessed using MATLAB soft", "rison with the normal cells, gene expression microarray data sets preprocessed by FRMA package (McCa"], "order_basis": "paper_text_order:1574", "id": "assay:1"}, {"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 find differentially expressed genes (DEGs) in CRC cells in comparison with the normal cells, gene expression microarray data sets preprocessed by FRMA package (McCall et al., 2010) in R and then limma (Smyth, 2005) was used to develop a linear model for finding DEGs."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T02:43:43+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}}}