{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39182081", "kind": "science-record", "revision": 3, "content_hash": "sha256:0289a42583031de9902a8773e3444eaceb9da483f8bc0d37e140234a65494906", "created_at": "2026-11-01T20:29:18Z", "updated_at": "2026-11-01T22:12:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prognostic and immunological implications of heterogeneous cell death patterns in prostate cancer.", "doi": "10.1186/s12935-024-03462-7", "pmid": "39182081", "authors": ["Ming Wang", "Bangshun Dai", "Qiushi Liu", "Xiansheng Zhang"], "journal": "Cancer cell international", "year": 2024, "abstract": "BACKGROUND: Prostate cancer is one of the most common cancers in men with a significant proportion of patients developing biochemical recurrence (BCR) after treatment. Programmed cell death (PCD) mechanisms are known to play critical roles in tumor progression and can potentially serve as prognostic and therapeutic biomarkers in PCa. This study aimed to develop a prognostic signature for BCR in PCa using PCD-related genes.\nMATERIALS AND METHODS: We conducted an analysis of 19 different modes of PCD to develop a comprehensive model. Bulk transcriptomic, single-cell transcriptomic, genomic, and clinical data were collected from multiple cohorts, including TCGA-PRAD, GSE58812, METABRIC, GSE21653, and GSE193337. We analyzed the expression and mutations of the 19 PCD modes and constructed, evaluated, and validated the model.\nRESULTS: Ten PCD modes were found to be associated with BCR in PCa, with specific PCD patterns exhibited by various cell components within the tumor microenvironment. Through Lasso Cox regression analysis, we established a Programmed Cell Death Index (PCDI) utilizing an 11-gene signature. High PCDI values were validated in five independent datasets and were found to be associated with an increased risk of BCR in PCa patients. Notably, older age and advanced T and N staging were associated with higher PCDI values. By combining PCDI with T staging, we constructed a nomogram with enhanced predictive performance. Additionally, high PCDI values were significantly correlated with decreased drug sensitivity, including drugs such as Docetaxel and Methotrexate. Patients with lower PCDI values demonstrated higher immunophenoscores (IPS), suggesting a potentially higher response rate to immune therapy. Furthermore, PCDI was associated with immune checkpoint genes and key components of the tumor microenvironment, including macrophages, T cells, and NK cells. Finally, clinical specimens validated the differential expression of PCDI-related PCDRGs at both the gene and protein levels.\nCONCLUSION: In conclusion, we developed a novel PCD-based prognostic feature that successfully predicted BCR in PCa patients and provided insights into drug sensitivity and potential response to immune therapy. These findings have significant clinical implications for the treatment of PCa.", "claims": [{"id": "claim-method", "statement": "To further refine the candidate signature, we utilized the LASSO Cox regression method with the glmnet package, employing the deviance method for loss in cross-validation.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39182081", "locator": "sections[6] \"Construction of PCD prognostic model\" paragraph 2", "quote": "To further refine the candidate signature, we utilized the LASSO Cox regression method with the glmnet package, employing the deviance method for loss in cross-validation."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data used to support the findings of this study are available from the corresponding author upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39182081", "locator": "sections[30] \"Data availability\" paragraph 2", "quote": "Data used to support the findings of this study are available from the corresponding author upon request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Through Lasso Cox regression analysis, we established a Programmed Cell Death Index (PCDI) utilizing an 11-gene signature.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39182081", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Through Lasso Cox regression analysis, we established a Programmed Cell Death Index (PCDI) utilizing an 11-gene signature."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Through Lasso Cox regression analysis, we established a Programmed Cell Death Index (PCDI) utilizing an 11-gene signature.", "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:39182081"], "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:GSE116918"], "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:GSE116918"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39182081", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12935-024-03462-7", "sha256": "sha256:8a049b11236365c405f2e343ea821b8be9257a0407740fccdbd48261607688f9", "bytes": 61562, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12935-024-03462-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11344416", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE116918", "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=GSE116918", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE116918", "version": null, "note": "Data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3263664", "GSM3263665", "GSM3263666", "GSM3263667", "GSM3263668", "GSM3263669", "GSM3263670", "GSM3263671", "GSM3263672", "GSM3263673", "GSM3263674", "GSM3263675", "GSM3263676", "GSM3263677", "GSM3263678", "GSM3263679", "GSM3263680", "GSM3263681", "GSM3263682", "GSM3263683", "GSM3263684", "GSM3263685", "GSM3263686", "GSM3263687", "GSM3263688", "GSM3263689", "GSM3263690", "GSM3263691", "GSM3263692", "GSM3263693", "GSM3263694", "GSM3263695", "GSM3263696", "GSM3263697", "GSM3263698", "GSM3263699", "GSM3263700", "GSM3263701", "GSM3263702", "GSM3263703", "GSM3263704", "GSM3263705", "GSM3263706", "GSM3263707", "GSM3263708", "GSM3263709", "GSM3263710", "GSM3263711", "GSM3263712", "GSM3263713", "GSM3263714", "GSM3263715", "GSM3263716", "GSM3263717", "GSM3263718", "GSM3263719", "GSM3263720", "GSM3263721", "GSM3263722", "GSM3263723", "GSM3263724", "GSM3263725", "GSM3263726", "GSM3263727", "GSM3263728", "GSM3263729", "GSM3263730", "GSM3263731", "GSM3263732", "GSM3263733", "GSM3263734", "GSM3263735", "GSM3263736", "GSM3263737", "GSM3263738", "GSM3263739", "GSM3263740", "GSM3263741", "GSM3263742", "GSM3263743", "GSM3263744", "GSM3263745", "GSM3263746", "GSM3263747", "GSM3263748", "GSM3263749", "GSM3263750", "GSM3263751", "GSM3263752", "GSM3263753", "GSM3263754", "GSM3263755", "GSM3263756", "GSM3263757", "GSM3263758", "GSM3263759", "GSM3263760", "GSM3263761", "GSM3263762", "GSM3263763", "GSM3263764", "GSM3263765", "GSM3263766", "GSM3263767", "GSM3263768", "GSM3263769", "GSM3263770", "GSM3263771", "GSM3263772", "GSM3263773", "GSM3263774", "GSM3263775", "GSM3263776", "GSM3263777", "GSM3263778", "GSM3263779", "GSM3263780", "GSM3263781", "GSM3263782", "GSM3263783", "GSM3263784", "GSM3263785", "GSM3263786", "GSM3263787", "GSM3263788", "GSM3263789", "GSM3263790", "GSM3263791", "GSM3263792", "GSM3263793", "GSM3263794", "GSM3263795", "GSM3263796", "GSM3263797", "GSM3263798", "GSM3263799", "GSM3263800", "GSM3263801", "GSM3263802", "GSM3263803", "GSM3263804", "GSM3263805", "GSM3263806", "GSM3263807", "GSM3263808", "GSM3263809", "GSM3263810", "GSM3263811", "GSM3263812", "GSM3263813", "GSM3263814", "GSM3263815", "GSM3263816", "GSM3263817", "GSM3263818", "GSM3263819", "GSM3263820", "GSM3263821", "GSM3263822", "GSM3263823", "GSM3263824", "GSM3263825", "GSM3263826", "GSM3263827", "GSM3263828", "GSM3263829", "GSM3263830", "GSM3263831", "GSM3263832", "GSM3263833", "GSM3263834", "GSM3263835", "GSM3263836", "GSM3263837", "GSM3263838", "GSM3263839", "GSM3263840", "GSM3263841", "GSM3263842", "GSM3263843", "GSM3263844", "GSM3263845", "GSM3263846", "GSM3263847", "GSM3263848", "GSM3263849", "GSM3263850", "GSM3263851", "GSM3263852", "GSM3263853", "GSM3263854", "GSM3263855", "GSM3263856", "GSM3263857", "GSM3263858", "GSM3263859", "GSM3263860", "GSM3263861", "GSM3263862", "GSM3263863", "GSM3263864", "GSM3263865", "GSM3263866", "GSM3263867", "GSM3263868", "GSM3263869", "GSM3263870", "GSM3263871", "GSM3263872", "GSM3263873", "GSM3263874", "GSM3263875", "GSM3263876", "GSM3263877", "GSM3263878", "GSM3263879", "GSM3263880", "GSM3263881", "GSM3263882", "GSM3263883", "GSM3263884", "GSM3263885", "GSM3263886", "GSM3263887", "GSM3263888", "GSM3263889", "GSM3263890", "GSM3263891", "GSM3263892", "GSM3263893", "GSM3263894", "GSM3263895", "GSM3263896", "GSM3263897", "GSM3263898", "GSM3263899", "GSM3263900", "GSM3263901", "GSM3263902", "GSM3263903", "GSM3263904", "GSM3263905", "GSM3263906", "GSM3263907", "GSM3263908", "GSM3263909", "GSM3263910", "GSM3263911"], "sample_count": 248, "group_sizes": null, "group_sizes_basis": null, "platform": "25318", "taxon": "Homo sapiens", "title": "Using biopsies to improve risk stratification in patients with prostate cancer treated with radical radiation therapy", "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:GSE193337", "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=GSE193337", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE193337", "version": null, "note": "Data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5793824", "GSM5793825", "GSM5793826", "GSM5793827", "GSM5793828", "GSM5793829", "GSM5793831", "GSM5793832", "GSM5793833", "GSM5793834", "GSM5793835", "GSM5793836", "GSM5793837", "GSM5793838", "GSM5793839", "GSM5793841", "GSM5793842", "GSM5793843", "GSM5793844", "GSM5793845", "GSM5793846", "GSM5793847", "GSM5793848", "GSM5793849", "GSM5793850", "GSM5793852", "GSM5793853"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "17303;20301", "taxon": "Homo sapiens", "title": "Single-cell and bulk RNA-seq of human tumor-benign prostate adenocarinoma samples", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE46602", "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=GSE46602", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46602", "version": null, "note": "Data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1133136", "GSM1133137", "GSM1133138", "GSM1133139", "GSM1133140", "GSM1133141", "GSM1133142", "GSM1133143", "GSM1133144", "GSM1133145", "GSM1133146", "GSM1133147", "GSM1133148", "GSM1133149", "GSM1133150", "GSM1133151", "GSM1133152", "GSM1133153", "GSM1133154", "GSM1133155", "GSM1133156", "GSM1133157", "GSM1133158", "GSM1133159", "GSM1133160", "GSM1133161", "GSM1133162", "GSM1133163", "GSM1133164", "GSM1133165", "GSM1133166", "GSM1133167", "GSM1133168", "GSM1133169", "GSM1133170", "GSM1133171", "GSM1133172", "GSM1133173", "GSM1133174", "GSM1133175", "GSM1133176", "GSM1133177", "GSM1133178", "GSM1133179", "GSM1133180", "GSM1133181", "GSM1133182", "GSM1133183", "GSM1133184", "GSM1133185"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from prostate cancer and benign prostate glands", "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:GSE70769", "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=GSE70769", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE70769", "version": null, "note": "Data used to support the findings of this study are available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data used to support the findings of this study are available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1817906", "GSM1817907", "GSM1817908", "GSM1817909", "GSM1817910", "GSM1817911", "GSM1817912", "GSM1817913", "GSM1817914", "GSM1817915", "GSM1817916", "GSM1817917", "GSM1817918", "GSM1817919", "GSM1817920", "GSM1817921", "GSM1817922", "GSM1817923", "GSM1817924", "GSM1817925", "GSM1817926", "GSM1817927", "GSM1817928", "GSM1817929", "GSM1817930", "GSM1817931", "GSM1817932", "GSM1817933", "GSM1817934", "GSM1817935", "GSM1817936", "GSM1817937", "GSM1817938", "GSM1817939", "GSM1817940", "GSM1817941", "GSM1817942", "GSM1817943", "GSM1817944", "GSM1817945", "GSM1817946", "GSM1817947", "GSM1817948", "GSM1817949", "GSM1817950", "GSM1817951", "GSM1817952", "GSM1817953", "GSM1817954", "GSM1817955", "GSM1817956", "GSM1817957", "GSM1817958", "GSM1817959", "GSM1817960", "GSM1817961", "GSM1817962", "GSM1817963", "GSM1817964", "GSM1817965", "GSM1817966", "GSM1817967", "GSM1817968", "GSM1817969", "GSM1817970", "GSM1817971", "GSM1817972", "GSM1817973", "GSM1817974", "GSM1817975", "GSM1817976", "GSM1817977", "GSM1817978", "GSM1817979", "GSM1817980", "GSM1817981", "GSM1817982", "GSM1817983", "GSM1817984", "GSM1817985", "GSM1817986", "GSM1817987", "GSM1817988", "GSM1817989", "GSM1817990", "GSM1817991", "GSM1817992", "GSM1817993", "GSM1817994", "GSM1817995", "GSM1817996", "GSM1817997", "GSM1817998", "GSM1817999"], "sample_count": 94, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Prostate cancer stratification using molecular profiles [Stockholm ExpressionArray]", "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:GSE116918 not downloaded", "asset:data:geo:GSE116918 licence not read", "asset:data:geo:GSE193337 not downloaded", "asset:data:geo:GSE193337 licence not read", "asset:data:geo:GSE46602 not downloaded", "asset:data:geo:GSE46602 licence not read", "asset:data:geo:GSE70769 not downloaded", "asset:data:geo:GSE70769 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To further refine the candidate signature, we utilized the LASSO Cox regression method with the glmnet package, employing the deviance method for loss in cross-validation."}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Principal component analysis"}}, {"id": "method-3", "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 analysis"}}, {"id": "method-4", "family": "model_calibration", "specific": "decision_curve", "label": "Model calibration / clinical utility", "dsl_operations": ["calibration_bins", "net_benefit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictions_and_outcomes"], "evidence": {"score": 0.8, "band": "high", "quote": "decision curve analysis"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE116918", "GSE46602", "GSE70769", "GSE193337"], "resolved_accessions": ["GSE116918", "GSE46602", "GSE70769", "GSE193337"], "statements": ["Data used to support the findings of this study are available from the corresponding author upon request."], "basis": "The paper names GSE116918, GSE46602, GSE70769, GSE193337 in GSE116918 dataset and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:39182081", "data:geo:GSE116918"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE116918"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:29:41Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 17198, "completion_tokens": 2016, "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:39182081", "type": "paper", "label": "pmid:39182081"}, {"id": "source:pmid:39182081", "type": "manuscript", "label": "PMID 39182081 full text"}, {"id": "data:geo:GSE116918", "type": "dataset", "label": "GEO GSE116918"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39182081", "type": "paper", "label": "pmid:39182081"}, {"id": "source:pmid:39182081", "type": "manuscript", "label": "PMID 39182081 full text"}, {"id": "data:geo:GSE116918", "type": "dataset", "label": "GEO GSE116918"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39182081", "type": "extraction", "used": ["source:pmid:39182081"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE116918", "type": "accession_resolution", "used": ["data:geo:GSE116918"], "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:39182081", "parent_hash": "sha256:1b6f71b07809b53a034409bf46eb7cd70f1e6de9f624f981c92636f4ea8bc338", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE116918 licence not read", "asset:data:geo:GSE116918 not downloaded", "asset:data:geo:GSE193337 licence not read", "asset:data:geo:GSE193337 not downloaded", "asset:data:geo:GSE46602 licence not read", "asset:data:geo:GSE46602 not downloaded", "asset:data:geo:GSE70769 licence not read", "asset:data:geo:GSE70769 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Materials and methods scRNA-Seq data processing Following established protoc"], "order_basis": "paper_text_order:2411", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To further refine the candidate signature, we utilized the LASSO Cox regression method with the glmnet package, employing the deviance method for loss in cross-validation."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:49:10+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}}}