{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39742277", "kind": "science-record", "revision": 4, "content_hash": "sha256:db736427dd95199c1a06b9619c29a6126ffaa424df5c087c050fe8b5518117f6", "created_at": "2026-11-01T20:30:04Z", "updated_at": "2026-11-01T22:55:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PAQR6 as a prognostic biomarker and potential therapeutic target in kidney renal clear cell carcinoma.", "doi": "10.3389/fimmu.2024.1521629", "pmid": "39742277", "authors": ["Tao Zou", "Zongming Jia", "Jixiang Wu", "Xuxu Liu", "Minghao Deng", "Xuefeng Zhang", "Yuxin Lin", "Jigen Ping"], "journal": "Frontiers in immunology", "year": 2024, "abstract": "Background: Progestin And AdipoQ Receptor Family Member VI (PAQR6) plays a significant role in the non-genomic effects of rapid steroid responses and is abnormally expressed in various tumors. However, its biological function in kidney renal clear cell carcinoma (KIRC) and its potential as a therapeutic target remain underexplored.\nMethods: In this study, PAQR6 was identified as a critical oncogene by WGCNA algorithm and differential gene expression analysis using TCGA - KIRC and GSE15641 data. The differences in PAQR6 expression and its association with KIRC survival outcomes were investigated, and transcriptomic data were used to further elucidate PAQR6's biological functions. Moreover, XCELL and single - cell analysis assessed the correlation between PAQR6 expression and immune infiltration. TIDE algorithm was used to assess how well various patient cohorts responded to immune checkpoint therapy. Finally, the role of PAQR6 in the development of KIRC was verified through EdU, scratch assays, and Transwell assays.\nResults: Our findings suggest that elevated expression of PAQR6 is linked to a poor prognosis for KIRC patients. Functional enrichment analysis demonstrated that PAQR6 is primarily involved in angiogenesis and pluripotent stem cell differentiation, which are crucial in mediating the development of KIRC. Additionally, we established a ceRNA network that is directly related to overall prognosis, further supporting the role of PAQR6 as a prognostic biomarker for KIRC.\nConclusion: Using both computational and experimental methods, this study leads the charge in discovering and verifying PAQR6 as a prognostic biomarker and possible therapeutic target for KIRC. In the future, to determine its molecular mechanism in KIRC carcinogenesis, more in vivo research will be carried out.", "claims": [{"id": "claim-method", "statement": "The expression of PAQR6 in KIRC and normal kidney tissues was detected by the Wilcoxon rank-sum test. The log-rank test was used for prognostic analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39742277", "locator": "sections[13] \"Statistical analysis\" paragraph 2", "quote": "The expression of PAQR6 in KIRC and normal kidney tissues was detected by the Wilcoxon rank-sum test. The log-rank test was used for prognostic analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39742277", "locator": "sections[25] \"Data availability statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Elevated PAQR6 expression is linked to a poor prognosis for KIRC patients.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39742277", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Our findings suggest that elevated expression of PAQR6 is linked to a poor prognosis for KIRC patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Elevated PAQR6 expression is linked to a poor prognosis for KIRC patients.", "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:39742277"], "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:GSE111360"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:GSE111360"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39742277", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2024.1521629", "sha256": "sha256:5618247b85459f0227a41da133a9f8a317365811fa4d61fe18b76b1f9091d0cb", "bytes": 51655, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2024.1521629", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11685228", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE111360", "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=GSE111360", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE111360", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3029087", "GSM3029088", "GSM3029089", "GSM3029090", "GSM3029091", "GSM3029092", "GSM3029093", "GSM3029094", "GSM3029103", "GSM3029104", "GSM3029105", "GSM3029106", "GSM3029107", "GSM3029108", "GSM3029109", "GSM3029110", "GSM3029111", "GSM3029112", "GSM3029113", "GSM3029114", "GSM3029115", "GSM3029116", "GSM3029117", "GSM3029118", "GSM3029119", "GSM3029120", "GSM3029121", "GSM3457010", "GSM3457011", "GSM3457012", "GSM3457013", "GSM3457014", "GSM3457015", "GSM3457016", "GSM3457017"], "sample_count": 35, "group_sizes": null, "group_sizes_basis": null, "platform": "24676;20301", "taxon": "Homo sapiens", "title": "Organoid modeling of the tumor immune microenvironment", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE15641", "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=GSE15641", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15641", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM391107", "GSM391108", "GSM391109", "GSM391110", "GSM391111", "GSM391112", "GSM391113", "GSM391114", "GSM391115", "GSM391116", "GSM391117", "GSM391118", "GSM391119", "GSM391120", "GSM391121", "GSM391122", "GSM391123", "GSM391124", "GSM391125", "GSM391126", "GSM391127", "GSM391128", "GSM391129", "GSM391130", "GSM391131", "GSM391132", "GSM391133", "GSM391134", "GSM391135", "GSM391136", "GSM391137", "GSM391138", "GSM391139", "GSM391140", "GSM391141", "GSM391142", "GSM391143", "GSM391144", "GSM391145", "GSM391146", "GSM391147", "GSM391148", "GSM391149", "GSM391150", "GSM391151", "GSM391152", "GSM391153", "GSM391154", "GSM391155", "GSM391156", "GSM391157", "GSM391158", "GSM391159", "GSM391160", "GSM391161", "GSM391162", "GSM391163", "GSM391164", "GSM391165", "GSM391166", "GSM391167", "GSM391168", "GSM391169", "GSM391170", "GSM391171", "GSM391172", "GSM391173", "GSM391174", "GSM391175", "GSM391176", "GSM391177", "GSM391178", "GSM391179", "GSM391180", "GSM391181", "GSM391182", "GSM391183", "GSM391184", "GSM391185", "GSM391186", "GSM391187", "GSM391188", "GSM391189", "GSM391190", "GSM391191", "GSM391192", "GSM391193", "GSM391194", "GSM391195", "GSM391196", "GSM391197", "GSM391198"], "sample_count": 92, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene signatures of progression and metastasis in renal cell cancer", "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:GSE29609", "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=GSE29609", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29609", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM733579", "GSM733580", "GSM733581", "GSM733582", "GSM733583", "GSM733584", "GSM733585", "GSM733586", "GSM733587", "GSM733588", "GSM733589", "GSM733590", "GSM733591", "GSM733592", "GSM733593", "GSM733594", "GSM733595", "GSM733596", "GSM733597", "GSM733598", "GSM733599", "GSM733600", "GSM733601", "GSM733602", "GSM733603", "GSM733604", "GSM733605", "GSM733606", "GSM733607", "GSM733608", "GSM733609", "GSM733610", "GSM733611", "GSM733612", "GSM733613", "GSM733614", "GSM733615", "GSM733616", "GSM733617"], "sample_count": 39, "group_sizes": null, "group_sizes_basis": null, "platform": "1708", "taxon": "Homo sapiens", "title": "Clear-cell renal cell carcinomas tumors", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE111360 not downloaded", "asset:data:geo:GSE111360 licence not read", "asset:data:geo:GSE15641 not downloaded", "asset:data:geo:GSE15641 licence not read", "asset:data:geo:GSE29609 not downloaded", "asset:data:geo:GSE29609 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The expression of PAQR6 in KIRC and normal kidney tissues was detected by the Wilcoxon rank-sum test. The log-rank test was used for prognostic analysis."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "Cox regression"}}, {"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.group_comparison_wilcoxon"]}, "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": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["GSE15641", "GSE29609", "GSE111360"], "resolved_accessions": ["GSE15641", "GSE29609", "GSE111360"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: TCGA-TCGA: https://portal.gdc.cancer.gov/GEO (GSE15641,GSE29609): https://www.ncbi.nlm.nih.gov/geo/."], "basis": "The paper names GSE15641, GSE29609, GSE111360 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": [], "assets": ["source:pmid:39742277", "data:geo:GSE111360"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE111360"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:43:47Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14626, "completion_tokens": 1550, "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:39742277", "type": "paper", "label": "pmid:39742277"}, {"id": "source:pmid:39742277", "type": "manuscript", "label": "PMID 39742277 full text"}, {"id": "data:geo:GSE111360", "type": "dataset", "label": "GEO GSE111360"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39742277", "type": "paper", "label": "pmid:39742277"}, {"id": "source:pmid:39742277", "type": "manuscript", "label": "PMID 39742277 full text"}, {"id": "data:geo:GSE111360", "type": "dataset", "label": "GEO GSE111360"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39742277", "type": "extraction", "used": ["source:pmid:39742277"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE111360", "type": "accession_resolution", "used": ["data:geo:GSE111360"], "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:39742277", "parent_hash": "sha256:edec1909a17a8651763d9f4fce4b9e9d73cc1b246fd844c17388c67f80b9851b", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE111360 licence not read", "asset:data:geo:GSE111360 not downloaded", "asset:data:geo:GSE15641 licence not read", "asset:data:geo:GSE15641 not downloaded", "asset:data:geo:GSE29609 licence not read", "asset:data:geo:GSE29609 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["cular mechanism in KIRC carcinogenesis, more in vivo research will be carried out."], "order_basis": "paper_text_order:1834", "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": ["l cultures and viral infection 769P cell was cultured in RPMI 1640 medium (cytiva, UK) containing 10%", "l bovine serum (Gibco, USA) and the cell was cultured in a 37°C cell incubator containing 5% CO2. PAQ", "l bovine serum (Gibco, USA) and the cell was cultured in a 37°C cell incubator containing 5% CO2."], "order_basis": "paper_text_order:2929", "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": 0.99, "evidence": ["37°C cell incubator containing 5% CO2. PAQR6 knockdown lentivirus were purchased from Shanghai Gene", "re the role of PAQR6 in KIRC phenotypes. The knockdown treatment was performed using three differen", "of PAQR6 on tumor cell proliferation. In the knockdown group, the decreased PAQR6 significantly inh", "D ). The scratch assay demonstrated that the knockdown of PAQR6 evidently inhibited the migration o"], "order_basis": "paper_text_order:3094", "id": "assay:3"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["e-based therapies. Experimental verification Western blot was performed to evaluate the protein level", "ntibodies: Information on antibodies used in Western Blot experiments. Flowchart: The bioinformatics a"], "order_basis": "paper_text_order:8738", "id": "assay:4"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The expression of PAQR6 in KIRC and normal kidney tissues was detected by the Wilcoxon rank-sum test. The log-rank test was used for prognostic analysis."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"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":"2026-11-04T02:16:48+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}}}