{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34034744", "kind": "science-record", "revision": 6, "content_hash": "sha256:eeb183f2333ad4a8dcb23b10159bb945a114f3bf0610dcc7d17a6392bfafeca8", "created_at": "2026-11-01T15:41:36Z", "updated_at": "2026-11-01T21:25:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of collagen genes related to immune infiltration and epithelial-mesenchymal transition in glioma.", "doi": "10.1186/s12935-021-01982-0", "pmid": "34034744", "authors": ["Wen Yin", "Hecheng Zhu", "Jun Tan", "Zhaoqi Xin", "Quanwei Zhou", "Yudong Cao", "Zhaoping Wu", "Lei Wang", "Ming Zhao", "Xingjun Jiang", "Caiping Ren", "Guihua Tang"], "journal": "Cancer cell international", "year": 2021, "abstract": "BACKGROUND: Gliomas account for the majority of fatal primary brain tumors, and there is much room for research in the underlying pathogenesis, the multistep progression of glioma, and how to improve survival. In our study, we aimed to identify potential biomarkers or therapeutic targets of glioma and study the mechanism underlying the tumor progression.\nMETHODS: We downloaded the microarray datasets (GSE43378 and GSE7696) from the Gene Expression Omnibus (GEO) database. Then, we used weighted gene co-expression network analysis (WGCNA) to screen potential biomarkers or therapeutic targets related to the tumor progression. ESTIMATE (Estimation of STromal and Immune cells in MAlignant Tumors using Expression data) algorithm and TIMER (Tumor Immune Estimation Resource) database were used to analyze the correlation between the selected genes and the tumor microenvironment. Real-time reverse transcription polymerase chain reaction was used to measure the selected gene. Transwell and wound healing assays were used to measure the cell migration and invasion capacity. Western blotting was used to test the expression of epithelial-mesenchymal transition (EMT) related markers.\nRESULTS: We identified specific module genes that were positively correlated with the WHO grade but negatively correlated with OS of glioma. Importantly, we identified that 6 collagen genes (COL1A1, COL1A2, COL3A1, COL4A1, COL4A2, and COL5A2) could regulate the immunosuppressive microenvironment of glioma. Moreover, we found that these collagen genes were significantly involved in the EMT process of glioma. Finally, taking COL3A1 as a further research object, the results showed that knockdown of COL3A1 significantly inhibited the migration, invasion, and EMT process of SHG44 and A172 cells.\nCONCLUSIONS: In summary, our study demonstrated that collagen genes play an important role in regulating the immunosuppressive microenvironment and EMT process of glioma and could serve as potential therapeutic targets for glioma management.", "claims": [{"id": "claim-method", "statement": "The coefficients of correlation were calculated by Pearson correlation analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34034744", "locator": "sections[17] \"Statistical analysis\" paragraph 2", "quote": "The coefficients of correlation were calculated by Pearson correlation analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used in the current study are included within the article. Other data and materials are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34034744", "locator": "sections[35] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used in the current study are included within the article. Other data and materials are available from the corresponding author on reasonable request."}], "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:34034744"], "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:GSE43378"], "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:GSE43378"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34034744", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12935-021-01982-0", "sha256": "sha256:8aaf861969d438d794a3ccd4f10a0b8351a6f4c5fd4836f66609af594ac83478", "bytes": 60837, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12935-021-01982-0", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8147444", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE43378", "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=GSE43378", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43378", "version": null, "note": "The datasets used in the current study are included within the article. Other data and materials are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used in the current study are included within the article. Other data and materials are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1061661", "GSM1061662", "GSM1061663", "GSM1061664", "GSM1061665", "GSM1061666", "GSM1061667", "GSM1061668", "GSM1061669", "GSM1061670", "GSM1061671", "GSM1061672", "GSM1061673", "GSM1061674", "GSM1061675", "GSM1061676", "GSM1061677", "GSM1061678", "GSM1061679", "GSM1061680", "GSM1061681", "GSM1061682", "GSM1061683", "GSM1061684", "GSM1061685", "GSM1061686", "GSM1061687", "GSM1061688", "GSM1061689", "GSM1061690", "GSM1061691", "GSM1061692", "GSM1061693", "GSM1061694", "GSM1061695", "GSM1061696", "GSM1061697", "GSM1061698", "GSM1061699", "GSM1061700", "GSM1061701", "GSM1061702", "GSM1061703", "GSM1061704", "GSM1061705", "GSM1061706", "GSM1061707", "GSM1061708", "GSM1061709", "GSM1061710"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from glioma patients", "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:GSE7696", "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=GSE7696", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7696", "version": null, "note": "The datasets used in the current study are included within the article. Other data and materials are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used in the current study are included within the article. Other data and materials are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM187153", "GSM187154", "GSM187155", "GSM187156", "GSM187157", "GSM187158", "GSM187159", "GSM187160", "GSM187161", "GSM187162", "GSM187163", "GSM187164", "GSM187165", "GSM187166", "GSM187167", "GSM187168", "GSM187169", "GSM187170", "GSM187171", "GSM187172", "GSM187173", "GSM187174", "GSM187175", "GSM187176", "GSM187177", "GSM187178", "GSM187179", "GSM187180", "GSM187181", "GSM187182", "GSM187183", "GSM187184", "GSM187185", "GSM187186", "GSM187187", "GSM187188", "GSM187189", "GSM187190", "GSM187191", "GSM187192", "GSM187193", "GSM187194", "GSM187195", "GSM187196", "GSM187197", "GSM187198", "GSM187199", "GSM187200", "GSM187201", "GSM187202", "GSM187203", "GSM187204", "GSM187205", "GSM187206", "GSM187207", "GSM187208", "GSM187209", "GSM187210", "GSM187211", "GSM187212", "GSM187213", "GSM187214", "GSM187215", "GSM187216", "GSM187217", "GSM187218", "GSM187219", "GSM187220", "GSM187221", "GSM187222", "GSM187223", "GSM187224", "GSM187225", "GSM187226", "GSM187227", "GSM187228", "GSM187229", "GSM187230", "GSM187231", "GSM187232", "GSM187233", "GSM187234", "GSM187235", "GSM187236"], "sample_count": 84, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Glioblastoma from a homogenous cohort of patients treated within clinical trial", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34034744:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c9fe4d6b7a945295def03faf0023e6b7b71793f1bea65193292eac2ee4e5d7e0", "bytes": 1037, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#Tab1", "version": null, "note": "Hub genes ranked in cytoHubba", "structure": {"pmcid": "PMC8147444", "section_index": 20, "section_title": "Screening collagen genes", "row_count": 22, "column_count": 5}, "table": {"label": "Table 1", "caption": "Hub genes ranked in cytoHubba", "rows": [["Category", "Rank methods in cytoHubba"], ["Degree", "EPC", "Closeness", "Radiality"], ["Genes top 20", "FN1", "FN1", "FN1", "FN1"], ["", "CD44", "COL4A1", "COL4A1", "COL4A1"], ["", "COL4A1", "ANGPT2", "ANXA2", "ANXA2"], ["", "ANXA2", "COL5A2", "CD44", "ANGPT2"], ["", "COL5A2", "ANXA2", "ANGPT2", "LAMB1"], ["", "ANGPT2", "COL3A1", "LAMB1", "COL1A1"], ["", "COL3A1", "COL1A1", "SERPINH1", "SERPINH1"], ["", "COL1A1", "CALD1", "COL5A2", "CALD1"], ["", "CLIC1", "CD44", "COL1A1", "CD44"], ["", "CALD1", "SERPINH1", "CALD1", "NAMPT"], ["", "LAMB1", "COL1A2", "COL1A2", "LAMC1"], ["", "SERPINH1", "NAMPT", "LAMC1", "COL5A2"], ["", "COL1A2", "LAMB1", "NAMPT", "COL1A2"], ["", "LAMC1", "LAMC1", "CLIC1", "PDPN"], ["", "NAMPT", "CLIC1", "COL3A1", "COL4A2"], ["", "ADAM12", "COL4A2", "COL4A2", "GALNT2"], ["", "CAV1", "ADAM12", "PDPN", "P4HB"], ["", "COL4A2", "CAV1", "P4HB", "CXCR4"], ["", "CD93", "NOX4", "ADAM12", "CLIC1"], ["", "PDPN", "ENPEP", "GALNT2", "COL3A1"]], "row_count": 22, "column_count": 5, "numeric_cells": 9, "header_rows": 2, "locator": "section[20]/table-wrap[1]#Tab1"}}], "gaps": ["asset:data:geo:GSE43378 not downloaded", "asset:data:geo:GSE43378 licence not read", "asset:data:geo:GSE7696 not downloaded", "asset:data:geo:GSE7696 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The coefficients of correlation were calculated by Pearson correlation analysis."}}, {"id": "method-2", "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-3", "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"}}], "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": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE43378", "GSE7696"], "resolved_accessions": ["GSE43378", "GSE7696"], "statements": ["The datasets used in the current study are included within the article. Other data and materials are available from the corresponding author on reasonable request."], "basis": "The paper names GSE43378, GSE7696 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:34034744", "data:geo:GSE43378", "asset:table:pmid:34034744:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE43378"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:33Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 46957, "completion_tokens": 2533, "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:34034744", "type": "paper", "label": "pmid:34034744"}, {"id": "source:pmid:34034744", "type": "manuscript", "label": "PMID 34034744 full text"}, {"id": "data:geo:GSE43378", "type": "dataset", "label": "GEO GSE43378"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34034744", "type": "paper", "label": "pmid:34034744"}, {"id": "source:pmid:34034744", "type": "manuscript", "label": "PMID 34034744 full text"}, {"id": "data:geo:GSE43378", "type": "dataset", "label": "GEO GSE43378"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34034744", "type": "extraction", "used": ["source:pmid:34034744"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE43378", "type": "accession_resolution", "used": ["data:geo:GSE43378"], "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:34034744", "parent_hash": "sha256:93d8b0c6fc0bba1fcb6c2c4dd0d6fc17030044b3d0c389426872cb3828b8d57b", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE43378 licence not read", "asset:data:geo:GSE43378 not downloaded", "asset:data:geo:GSE7696 licence not read", "asset:data:geo:GSE7696 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": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["umor progression. METHODS: We downloaded the microarray datasets (GSE43378 and GSE7696) from the Gen", "and glioma grades were executed on a cancer microarray data-mining database: Oncomine [25]. The res", "ain dataset [26], a maximal sample size mRNA microarray that could be grouped by glioma grade in his"], "order_basis": "paper_text_order:452", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["re the cell migration and invasion capacity. Western blotting was used to test the expression of epithelia"], "order_basis": "paper_text_order:1146", "id": "assay:2"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["her research object, the results showed that knockdown of COL3A1 significantly inhibited the migrat"], "order_basis": "paper_text_order:1743", "id": "assay:3"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ere analyzed by R language. Cell culture and real-time quantitative PCR (qRT-PCR) SHG44 and A172 glioma cells were p"], "order_basis": "paper_text_order:2964", "id": "assay:4"}, {"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": ["angsha, China. The SHG44 and A172 cells were cultured in DMEM high glucose medium (Gibco/Thermo Fishe"], "order_basis": "paper_text_order:3145", "id": "assay:5"}, {"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["e increases. From the UCSC database, level 3 RNA-Seq datasets (TCGA-GBMLGG) and their clinical in"], "order_basis": "paper_text_order:5589", "id": "assay:6"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["CGGA (B) datasets. **** p < 0.0001 Moreover, immunohistochemistry (IHC) datasets retrieved from the Human Prot", "n genes in the Human Protein Atlas database (immunohistochemistry). The translational expression level of the", "IL6 in WHO II-IV grade glioma tissues using immunofluorescence. Additional file 7: Fig. S7. The correlation", "* p < 0.0001 Moreover, immunohistochemistry (IHC) datasets retrieved from the Human Protein A"], "order_basis": "paper_text_order:7747", "id": "assay:7"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The coefficients of correlation were calculated by Pearson correlation analysis."], "order_basis": "consumes_earlier_output", "id": "assay:8"}]},"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":"2026-11-04T03:03:45+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}}}