{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34135913", "kind": "science-record", "revision": 7, "content_hash": "sha256:5c6704016a74b72fd6a0e31163151538aa0c5bff53ab2ae612f2862f6a8f97d3", "created_at": "2026-11-01T15:41:39Z", "updated_at": "2026-11-01T22:03:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prognosis and Characterization of Immune Microenvironment in Acute Myeloid Leukemia Through Identification of an Autophagy-Related Signature.", "doi": "10.3389/fimmu.2021.695865", "pmid": "34135913", "authors": ["Denggang Fu", "Biyu Zhang", "Shiyong Wu", "Yinghua Zhang", "Jingwu Xie", "Wangbin Ning", "Hua Jiang"], "journal": "Frontiers in immunology", "year": 2021, "abstract": "Acute myeloid leukemia (AML) is one of the most common hematopoietic malignancies that has an unfavorable outcome and a high rate of relapse. Autophagy plays a vital role in the development of and therapeutic responses to leukemia. This study identifies a potential autophagy-related signature to monitor the prognoses of patients of AML. Transcriptomic profiles of AML patients (GSE37642) with the relevant clinical information were downloaded from Gene Expression Omnibus (GEO) as the training set while TCGA-AML and GSE12417 were used as validation cohorts. Univariate regression analyses and multivariate stepwise Cox regression analysis were respectively applied to identify the autophagy-related signature. The univariate Cox regression analysis identified 32 autophagy-related genes (ARGs) that were significantly associated with the overall survival (OS) of the patients, and were mainly rich in signaling pathways for autophagy, p53, AMPK, and TNF. A prognostic signature that comprised eight ARGs (BAG3, CALCOCO2, CAMKK2, CANX, DAPK1, P4HB, TSC2, and ULK1) and had good predictive capacity was established by LASSO-Cox stepwise regression analysis. High-risk patients were found to have significantly shorter OS than patients in low-risk group. The signature can be used as an independent prognostic predictor after adjusting for clinicopathological parameters, and was validated on two external AML sets. Differentially expressed genes analyzed in two groups were involved in inflammatory and immune signaling pathways. An analysis of tumor-infiltrating immune cells confirmed that high-risk patients had a strong immunosuppressive microenvironment. Potential druggable OS-related ARGs were then investigated through protein-drug interactions. This study provides a systematic analysis of ARGs and develops an OS-related prognostic predictor for AML patients. Further work is needed to verify its clinical utility and identify the underlying molecular mechanisms in AML.", "claims": [{"id": "claim-method", "statement": "OS-related ARGs with P < 0.05 were identified using univariate Cox hazard regression analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34135913", "locator": "sections[5] \"Identification of Overall Survival (OS)-Related ARGs\" paragraph 2", "quote": "OS-related ARGs with P < 0.05 were identified using univariate Cox hazard regression analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/ Supplementary Material , further inquiries can be directed to the corresponding authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34135913", "locator": "sections[23] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/ Supplementary Material , further inquiries can be directed to the corresponding authors."}], "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:34135913"], "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:34135913", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2021.695865", "sha256": "sha256:933ab3d24664144413fd96fb6135afc3f9bf1a5bf363ad3d8533c0ffeb5c6461", "bytes": 57836, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2021.695865", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8200670", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:34135913:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:317ca818eb0c8c56e74c27f4fa1c9954459b1c6d0248e92827452ef99481251f", "bytes": 1839, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T1", "version": null, "note": "Overall survival-related ARGs in the AML patients (P < 0.05).", "structure": {"pmcid": "PMC8200670", "section_index": 14, "section_title": "Identification and Functional Enrichment Analysis of OS-Related ARGs in AML", "row_count": 33, "column_count": 3}, "table": {"label": "Table 1", "caption": "Overall survival-related ARGs in the AML patients (P < 0.05).", "rows": [["Gene symbol", "HR (95% CI)", "P value"], ["TSC2", "0.4072(0.2832 - 0.5856)", "1.25E-06"], ["CALCOCO2", "0.6758(0.5680 - 0.8039)", "9.69E-06"], ["DAPK1", "1.3835(1.1847 - 1.6157)", "4.10E-05"], ["BAG3", "1.1503(1.0753 - 1.2305)", "4.72E-05"], ["CAMKK2", "0.5397(0.3882 - 0.7504)", "0.000244719"], ["CANX", "0.7301(0.6099 - 0.8739)", "0.000606334"], ["ULK1", "0.7257(0.6025 - 0.8742)", "0.000735293"], ["P4HB", "0.8215(0.7324 - 0.9215)", "0.000790605"], ["CCL2", "1.1482(1.0510 - 1.2544)", "0.002205099"], ["GABARAP", "0.7085(0.5667 - 0.8859)", "0.002507313"], ["GABARAPL1", "0.8216(0.7213 - 0.9360)", "0.003127288"], ["EEF2", "0.6578(0.4920 - 0.8793)", "0.004684677"], ["GAPDH", "0.7715(0.6369 - 0.9345)", "0.007994922"], ["NCKAP1", "1.6932(1.1345 - 2.5271)", "0.009954145"], ["CDKN1B", "1.1991(1.0424 - 1.3793)", "0.011027097"], ["CAPNS1", "0.8504(0.7469 - 0.9684)", "0.014474617"], ["SERPINA1", "0.9062(0.8370 - 0.9811)", "0.015041995"], ["BECN1", "0.7031(0.5283 - 0.9358)", "0.015733367"], ["ARSB", "0.7888(0.6501 - 0.9571)", "0.016217681"], ["CDKN2A", "0.7312(0.5641 - 0.9477)", "0.017994775"], ["DLC1", "0.7460(0.5785 - 0.9619)", "0.023876677"], ["ERN1", "0.6722(0.4728 - 0.9558)", "0.026995358"], ["CAPN1", "0.8331(0.7073 - 0.9813)", "0.028824089"], ["ATG9A", "0.8343(0.7059 - 0.9861)", "0.03365361"], ["EIF2AK2", "1.2624(1.0181 - 1.5653)", "0.03374212"], ["WIPI2", "0.7297(0.5453 - 0.9765)", "0.034038805"], ["ITGB4", "0.5864(0.3552 - 0.9682)", "0.036949174"], ["CLN3", "0.7788(0.6128 - 0.9897)", "0.04089584"], ["ATG7", "0.8389(0.7072 - 0.9952)", "0.043928123"], ["HGS", "0.8035(0.6488 - 0.9951)", "0.044918193"], ["FAS", "0.8763 (0.7692 - 0.9982)", "0.046832376"], ["CASP3", "0.8846(0.7838 - 0.9983)", "0.046888189"]], "row_count": 33, "column_count": 3, "numeric_cells": 65, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34135913:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:022aae11e5676cfd0fb726a74ca3decbf046107c9150008d38b9bf29c08d2e84", "bytes": 1441, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#T2", "version": null, "note": "Eight OS-related ARGs targeted by the drugs available from DrugBank.", "structure": {"pmcid": "PMC8200670", "section_index": 20, "section_title": "Multiple Survival-Related ARGs Are Potential Druggable Targets", "row_count": 9, "column_count": 6}, "table": {"label": "Table 2", "caption": "Eight OS-related ARGs targeted by the drugs available from DrugBank.", "rows": [["Gene Symbol", "HR (95%CI)", "P-value", "Number of drugs", "DrugBank ID", "Drug name examples"], ["CASP3", "0.8846(0.7838-0.9983)", "0.04689", "11", "DB08497, DB08229, DB08213, DB07696, DB01017, DB06862, DB05408, DB03124, DB08498, DB08251, DB08499", "EMRICASAN, MINOCYCLINE, METHYL (3S)-3-[(TERT-BUTOXYCARBONYL]-4-OXOPENTANOATE, 2-HYDROXY-5-(2-MERCAPTO-ETHYLSUFAMOYL)-BENZOIC ACID"], ["EEF2", "0.6578(0.4920-0.8793)", "0.00468", "4", "DB04315,DB03223,DB08348,DB02059", "Diphthamide, Glycinamide, Guanosine-5’-Diphosphate, Adenosine-5-Diphosphoribose"], ["GAPDH", "0.7715(0.6369-0.9345)", "0.00799", "4", "DB03893,DB00157,DB07347", "Thionicotinamide-Adenine-Dinucleotide,NADH,4-(2-Aminoethyl)Benzenesulfonyl Fluoride"], ["CAPN1", "0.8331(0.7073-0.9813)", "0.02882", "3", "DB07627,DB04276,DB04653", "CBZ-LEU-LEU-TYR-CH2F"], ["DAPK1", "1.3835(1.1847-1.6157)", "0.00004", "3", "DB04069,DB04395,DB07444", "5,6-Dihydro-Benzo[H]Cinnolin-3-Ylamine"], ["SERPINA1", "0.9062(0.8370-0.9811)", "0.01504", "3", "DB01998,DB05481,DB03345", "Recombinant alpha 1-antitrypsin,Mercaptoethanol"], ["CANX", "0.7301(0.6099-0.8739)", "0.00061", "2", "DB00031,DB00025", "Tenecteplase, Antihemophilic factor"], ["CCL2", "1.1482(1.0510-1.2544)", "0.00221", "2", "DB01055,DB01406", "Mimosine, Danazol"]], "row_count": 9, "column_count": 6, "numeric_cells": 38, "header_rows": 1, "locator": "section[20]/table-wrap[1]#T2"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-4", "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"}}, {"id": "method-5", "family": null, "specific": null, "label": "univariate Cox hazard regression analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "OS-related ARGs with P < 0.05 were identified using univariate Cox hazard regression analysis."}}], "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["The original contributions presented in the study are included in the article/ Supplementary Material , further inquiries can be directed to the corresponding authors."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:34135913", "asset:table:pmid:34135913:1", "asset:table:pmid:34135913:2"], "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": "2026-10-31T19:37:43Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 45867, "completion_tokens": 2251, "cached_tokens": 15368}}, "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:34135913", "type": "paper", "label": "pmid:34135913"}, {"id": "source:pmid:34135913", "type": "manuscript", "label": "PMID 34135913 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34135913", "type": "paper", "label": "pmid:34135913"}, {"id": "source:pmid:34135913", "type": "manuscript", "label": "PMID 34135913 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34135913", "type": "extraction", "used": ["source:pmid:34135913"], "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:34135913", "parent_hash": "sha256:dc31bc76f53ed91c280c50b46c7a3ac0fc19231d6a1d3a973904632ee761a015", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["gnaling pathway, AMPK signaling pathway, and apoptosis ( Figure 1B ). Overall survival-related ARGs"], "order_basis": "paper_text_order:5202", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Cox regression"], "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":"2026-11-04T02:52:12+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}}}