{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38410234", "kind": "science-record", "revision": 4, "content_hash": "sha256:041f8ce5f35418058c5f4e153da30a9fa1db60ef619cf6a1c2d999b0538a73a2", "created_at": "2026-11-01T19:20:21Z", "updated_at": "2026-11-01T22:53:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Complement and coagulation cascades are associated with prognosis and the immune microenvironment of lower-grade glioma.", "doi": "10.21037/tcr-23-906", "pmid": "38410234", "authors": ["Jianmei Yang", "Lei Shen", "Jingyi Yang", "Yinzong Qu", "Chengxian Gong", "Fang Zhou", "Yuhan Liu", "Ming Luo", "Li Zhao"], "journal": "Translational cancer research", "year": 2024, "abstract": "Background: Abnormal coagulation is a common feature of glioma. There is a strong correlation between coagulation and the complement system, named complement and coagulation cascades (CCC). However, the role of CCC genes in lower-grade glioma (LGG) remains unclear. This study aimed to investigate the role of CCC genes in LGG.\nMethods: In total, 5,628 differential expressed genes were identified between 498 LGG tissues from The Cancer Genome Atlas (TCGA) and 207 normal brain tissues from Genotype-Tissue Expression Project (GTEx). Among them, 20 overlapped CCC genes were identified as differentially expressed CCC genes. Then, comprehensive bioinformatics analysis was used to investigate the role of CCC genes in LGG; 271 LGG tissues from the Chinese Glioma Genome Atlas (CGGA) were used as the validation dataset. Cell Counting Kit-8 (CCK8) proliferation assay, colony formation assay, and wound healing assay were conducted to explore the anti-glioma effect of the sensitive drugs we predicted.\nResults: We constructed a risk signature consisting of six CCC genes, including F2R, SERPINA1, TFPI, C1QC, C2, and C3AR1. The CCC gene-based risk signature could accurately predict the prognosis of patients with LGG. In addition, we found that the JAK-STAT, NOD-like receptor, Notch, PI3K-Akt, and Rap1 signaling pathways might be activated and had crosstalk with CCC in the high-risk group. Our findings analyses demonstrated that samples in high- and low-risk groups had different immune landscapes. Moreover, patients in the high-risk group might have greater resistance to immunotherapy. We validated the accuracy of the risk signature in predicting immunotherapy response in two public immunotherapy cohorts, GSE135222 and GSE78220. By means of oncoPredict, MG-132, BMS-536924, PLX-4720, and AZD6482 were identified as potential sensitive drugs for high-risk patients, of which MG-132 was particularly recommended for high-risk patients. We performed in vitro experiments to explore the anti-glioma effect of MG-132, and the results demonstrated MG-132 could inhibit the proliferation and migration of glioma cells.\nConclusions: Our findings show that CCC genes are associated with the prognosis and immune infiltration of LGG and provide possible immunotherapeutic and novel chemotherapeutic strategies for patients with LGG based on the risk signature.", "claims": [{"id": "claim-method", "statement": "R package “limma” was used to identify differentially expressed genes between TCGA and GTEx, and genes with logFC (Log2 foldchange) >1 and q<0.05 were considered as differentially expressed genes (27).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38410234", "locator": "sections[5] \"Identification of differentially expressed CCC genes\" paragraph 2", "quote": "R package “limma” was used to identify differentially expressed genes between TCGA and GTEx, and genes with logFC (Log2 foldchange) >1 and q<0.05 were considered as differentially expressed genes (27)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "A total of 769 patients with LGG were included in this study, 498 in TCGA, and 271 in CGGA. Among them, patients in TCGA were divided into the training set, and patients in CGGA were divided into the validation set. RNA-seq and clinical data of patients were collected from TCGA and CGGA.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38410234", "locator": "sections[4] \"Data extraction\" paragraph 2", "quote": "A total of 769 patients with LGG were included in this study, 498 in TCGA, and 271 in CGGA. Among them, patients in TCGA were divided into the training set, and patients in CGGA were divided into the validation set. RNA-seq and clinical data of patients were collected from TCGA and CGGA."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In total, 5,628 differential expressed genes were identified between 498 LGG tissues from The Cancer Genome Atlas (TCGA) and 207 normal brain tissues from Genotype-Tissue Expression Project (GTEx).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38410234", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "In total, 5,628 differential expressed genes were identified between 498 LGG tissues from The Cancer Genome Atlas (TCGA) and 207 normal brain tissues from Genotype-Tissue Expression Project (GTEx)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "In total, 5,628 differential expressed genes were identified between 498 LGG tissues from The Cancer Genome Atlas (TCGA) and 207 normal brain tissues from Genotype-Tissue Expression Project (GTEx).", "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:38410234"], "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:GSE135222"], "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:GSE135222"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38410234", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/tcr-23-906", "sha256": "sha256:0e1898d3ce0c8c857609a99c2e5081a06c8e93c279fe1a9ea546cd57ae3f5fb1", "bytes": 45019, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/tcr-23-906", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10894340", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE135222", "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=GSE135222", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE135222", "version": null, "note": "A total of 769 patients with LGG were included in this study, 498 in TCGA, and 271 in CGGA. Among them, patients in TCGA were divided into the training set, and patients in CGGA were divided into the validation set. RNA-seq and clinical data of patients were collected from TCGA and CGGA.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "A total of 769 patients with LGG were included in this study, 498 in TCGA, and 271 in CGGA. Among them, patients in TCGA were divided into the training set, and patients in CGGA were divided into the validation set. RNA-seq and clinical data of patients were collected from TCGA and CGGA.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3995402", "GSM3995403", "GSM3995404", "GSM3995405", "GSM3995406", "GSM3995407", "GSM3995408", "GSM3995409", "GSM3995410", "GSM3995411", "GSM3995412", "GSM3995413", "GSM3995414", "GSM3995415", "GSM3995416", "GSM3995417", "GSM3995418", "GSM3995419", "GSM3995420", "GSM3995421", "GSM3995422", "GSM3995423", "GSM3995424", "GSM3995425", "GSM3995426", "GSM3995427", "GSM3995428"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "DNA methylation loss coupled with mitotic cell division promotes immune evasion of tumours with high mutation load [RNA-seq]", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE78220", "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=GSE78220", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE78220", "version": null, "note": "A total of 769 patients with LGG were included in this study, 498 in TCGA, and 271 in CGGA. Among them, patients in TCGA were divided into the training set, and patients in CGGA were divided into the validation set. RNA-seq and clinical data of patients were collected from TCGA and CGGA.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "A total of 769 patients with LGG were included in this study, 498 in TCGA, and 271 in CGGA. Among them, patients in TCGA were divided into the training set, and patients in CGGA were divided into the validation set. RNA-seq and clinical data of patients were collected from TCGA and CGGA.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2069823", "GSM2069824", "GSM2069825", "GSM2069826", "GSM2069827", "GSM2069828", "GSM2069829", "GSM2069830", "GSM2069831", "GSM2069832", "GSM2069833", "GSM2069834", "GSM2069835", "GSM2069836", "GSM2069837", "GSM2069838", "GSM2069839", "GSM2069840", "GSM2069841", "GSM2069842", "GSM2069843", "GSM2069844", "GSM2069845", "GSM2069846", "GSM2069847", "GSM2069848", "GSM2069849", "GSM2069850"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "mRNA expressions in pre-treatment melanomas undergoing anti-PD-1 checkpoint inhibition therapy", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE135222 not downloaded", "asset:data:geo:GSE135222 licence not read", "asset:data:geo:GSE78220 not downloaded", "asset:data:geo:GSE78220 licence not read"]}, "analysis": {"state": "partial", "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": "R package “limma” was used to identify differentially expressed genes between TCGA and GTEx, and genes with logFC (Log2 foldchange) >1 and q<0.05 were considered as differentially expressed genes (27)."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-4", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-5", "family": "image_quantification", "specific": "densitometry", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "optical density"}}, {"id": "method-6", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-7", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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: 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": "R1", "reachable": true, "accessions": ["GSE135222", "GSE78220"], "resolved_accessions": ["GSE135222", "GSE78220"], "statements": ["A total of 769 patients with LGG were included in this study, 498 in TCGA, and 271 in CGGA. Among them, patients in TCGA were divided into the training set, and patients in CGGA were divided into the validation set. RNA-seq and clinical data of patients were collected from TCGA and CGGA."], "basis": "The paper names GSE135222, GSE78220 in GSE135222 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:38410234", "data:geo:GSE135222"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE135222"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:10:19Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 12398, "completion_tokens": 2389, "cached_tokens": 256}}, "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:38410234", "type": "paper", "label": "pmid:38410234"}, {"id": "source:pmid:38410234", "type": "manuscript", "label": "PMID 38410234 full text"}, {"id": "data:geo:GSE135222", "type": "dataset", "label": "GEO GSE135222"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38410234", "type": "paper", "label": "pmid:38410234"}, {"id": "source:pmid:38410234", "type": "manuscript", "label": "PMID 38410234 full text"}, {"id": "data:geo:GSE135222", "type": "dataset", "label": "GEO GSE135222"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38410234", "type": "extraction", "used": ["source:pmid:38410234"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE135222", "type": "accession_resolution", "used": ["data:geo:GSE135222"], "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:38410234", "parent_hash": "sha256:c568e66595cc1ddfe08a506dd553bc9bd27f8a23d11e940232136564e92d63a5", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE135222 licence not read", "asset:data:geo:GSE135222 not downloaded", "asset:data:geo:GSE78220 licence not read", "asset:data:geo:GSE78220 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": 0.99, "evidence": ["the validation dataset. Cell Counting Kit-8 (CCK8) proliferation assay, colony formation assay", "re the anti-glioma effect of the MG-132. The CCK8 assay and colony formation assay demonstrate", "xplore the anti-glioma effect of MG-132. (A) CCK8 results showing MG-132 inhibited the prolife", "<0.001; ****, P<0.0001. OD, optical density; CCK8, Cell Counting Kit-8."], "order_basis": "paper_text_order:918", "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": 0.99, "evidence": ["e Academy of Sciences (Shanghai, China) were cultured in complete medium [Dulbecco’s modified Eagle m", "g sensitivity experiments, glioma cells were cultured in normal complete medium and complete medium c"], "order_basis": "paper_text_order:2862", "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": ["R package “limma” was used to identify differentially expressed genes between TCGA and GTEx, and genes with logFC (Log2 foldchange) >1 and q<0.05 were considered as differentially expressed genes (27)."], "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":"2026-11-04T02:51:16+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}}}