{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33447050", "kind": "science-record", "revision": 7, "content_hash": "sha256:d9aab8a38c550fbb392648284b7cc5eddd6fd15e765ae0295ab5a4b6242442d2", "created_at": "2026-11-01T15:41:22Z", "updated_at": "2026-11-01T22:45:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Overexpression of a Long Non-Coding RNA BC037916 is Associated with Pancreatic Tumorigenesis and Poor Prognosis.", "doi": "10.2147/OTT.S282350", "pmid": "33447050", "authors": ["Gang Chen", "Litao Xu", "Guanxiong Ye", "Junhua Lin", "Zhiqiang Meng", "Yehua Shen"], "journal": "OncoTargets and therapy", "year": 2020, "abstract": "BACKGROUND: Pancreatic cancer is one of the most lethal malignancies. Accumulating evidence supports for the critical contribution of long noncoding RNAs (lncRNAs) to the cancer development and progression. We tried to identify novel lncRNAs involved in the pancreatic carcinogenesis.\nMATERIALS AND METHODS: Two independent datasets (Gene Expression Omnibus datasets: GSE16515 and GSE32688) were obtained from the Gene Expression Omnibus (GEO). The level of BC037916 was detected in pancreatic cancer tissues and adjacent no-tumorous tissues (n=86) by qRT-PCR. Effects of BC037916 on proliferation, apoptosis, and invasion of pancreatic cancer cells were examined.\nRESULTS: We identified a novel lncRNA BC037916 involved in the pancreatic carcinogenesis by analyzing GEO datasets. Quantitative RT-PCR analysis showed that 86.0% (74/86) pancreatic cancer tissues had increased BC037916 expression as compared with normal counterparts. Further, positive correlation was observed between BC037916 expression and clinical stage, primary tumor, and regional lymph node invasion. Importantly, BC037916 was an independent prognostic factor of pancreatic cancer. Functionally, knockdown of BC037916 repressed cell proliferation, inhibited cell invasion, halted cell cycle progression, and promoted apoptosis in both PANC-1 and SW1990 cells. In contrast, overexpression of BC037916 in CAPAN-1 had opposite effects. Moreover, silencing of BC037916 significantly inhibited the tumor growth of xenografted SW1990 cells in vivo. Results of Western blot assays suggested that BC037916 knockdown also suppressed the activation of JAK2/STAT3 and TGF-β signaling. Further experiments suggested that BC037916 positively regulated the expression of Twist through miR-3145-3p.\nCONCLUSION: BC037916 exhibited oncogenic potential in pancreatic cancer development.", "claims": [{"id": "claim-method", "statement": "Data were analyzed by SPSS software (v16.0, SPSS, Inc., Chicago, IL, USA) and shown as mean ± standard deviation (SD). Student’s t-test was carried out to compare the differences between the two groups. The clinical characteristics of tumors with differential BC037916 expression were determined by the Chi-square tests. Cox regression model was employed to determine univariate and multivariate hazard ratios. Patients’ survival analyses were carried out using Kaplan-Meier analysis and Log-rank test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33447050", "locator": "sections[15] \"Statistical Analysis\" paragraph 2", "quote": "Data were analyzed by SPSS software (v16.0, SPSS, Inc., Chicago, IL, USA) and shown as mean ± standard deviation (SD). Student’s t-test was carried out to compare the differences between the two groups. The clinical characteristics of tumors with differential BC037916 expression were determined by the Chi-square tests. Cox regression model was employed to determine univariate and multivariate hazard ratios. Patients’ survival analyses were carried out using Kaplan-Meier analysis and Log-rank test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33447050", "locator": "sections[32] \"Data Sharing Statement\" paragraph 2", "quote": "The datasets used and/or analyzed during the current study 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:33447050"], "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:GSE16515"], "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:GSE16515"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33447050", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/OTT.S282350", "sha256": "sha256:a80723641f765f0eaba536f29a32803e7cb0106127879bc59bd0bec73442f9c5", "bytes": 38787, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/OTT.S282350", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7801918", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE16515", "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=GSE16515", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16515", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM414924", "GSM414925", "GSM414926", "GSM414927", "GSM414928", "GSM414929", "GSM414930", "GSM414931", "GSM414932", "GSM414933", "GSM414934", "GSM414935", "GSM414936", "GSM414937", "GSM414938", "GSM414939", "GSM414940", "GSM414941", "GSM414942", "GSM414943", "GSM414944", "GSM414945", "GSM414946", "GSM414947", "GSM414948", "GSM414949", "GSM414950", "GSM414951", "GSM414952", "GSM414953", "GSM414954", "GSM414955", "GSM414956", "GSM414957", "GSM414958", "GSM414959", "GSM414960", "GSM414961", "GSM414962", "GSM414963", "GSM414964", "GSM414965", "GSM414966", "GSM414967", "GSM414968", "GSM414969", "GSM414970", "GSM414971", "GSM414972", "GSM414973", "GSM414974", "GSM414975"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from Mayo Clinic Pancreatic Tumor and Normal samples", "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:GSE32688", "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=GSE32688", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32688", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM811004", "GSM811005", "GSM811006", "GSM811007", "GSM811008", "GSM811009", "GSM811010", "GSM811011", "GSM811012", "GSM811013", "GSM811014", "GSM811015", "GSM811016", "GSM811017", "GSM811018", "GSM811019", "GSM811020", "GSM811021", "GSM811022", "GSM811023", "GSM811024", "GSM811025", "GSM811026", "GSM811027", "GSM811028", "GSM811029", "GSM811030", "GSM811031", "GSM811032", "GSM811033", "GSM811034", "GSM811035", "GSM811039", "GSM811040", "GSM811041", "GSM811042", "GSM811043", "GSM811044", "GSM811045", "GSM811046", "GSM811047", "GSM811048", "GSM811049", "GSM811050", "GSM811051", "GSM811052", "GSM811053", "GSM811054", "GSM811055", "GSM811056", "GSM811057", "GSM811058", "GSM811059", "GSM811060", "GSM811061", "GSM811062", "GSM811063", "GSM811064", "GSM811065", "GSM811066", "GSM811067", "GSM811068", "GSM811069", "GSM811070", "GSM811143", "GSM811144", "GSM811145", "GSM811146", "GSM811147", "GSM811148", "GSM811149", "GSM811150", "GSM811151", "GSM811152", "GSM811153", "GSM811154", "GSM811155", "GSM811156", "GSM811157", "GSM811158", "GSM811159", "GSM811160", "GSM811161", "GSM811162", "GSM811163", "GSM811164", "GSM811165", "GSM811166", "GSM811167", "GSM811168", "GSM811169", "GSM811170", "GSM811171", "GSM811172", "GSM811173", "GSM811174"], "sample_count": 96, "group_sizes": null, "group_sizes_basis": null, "platform": "6801;7723;570", "taxon": "Mus musculus; Murid betaherpesvirus 1; JC polyomavirus; Human immunodeficiency virus 1; Human gammaherpesvirus 8; Homo sapiens; Human alphaherpesvirus 1; Human betaherpesvirus 5; human gammaherpesvirus 4; Betapolyomavirus macacae; Rattus norvegicus; Murid gammaherpesvirus 4; Betapolyomavirus hominis", "title": "Integrative Survival-Based Molecular Profiling of Human Pancreatic 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": "asset:table:pmid:33447050:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1d788110dc8fd2145a097f3be44f2a968c917b781330eec9fccb679f5d1a347f", "bytes": 1108, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#t0001", "version": null, "note": "Correlations Between BC037916 Expression and Clinicopathologic Features in Patients with Pancreatic Cancer", "structure": {"pmcid": "PMC7801918", "section_index": 19, "section_title": "Correlation Analysis Between BC037916 Expression and the Clinical Parameters of Pancreatic Cancer", "row_count": 26, "column_count": 5}, "table": {"label": "Table 1", "caption": "Correlations Between BC037916 Expression and Clinicopathologic Features in Patients with Pancreatic Cancer", "rows": [["Clinicopathologic features", "Total", "BC037916 Expression", "P value"], ["", "", "Low (n=43)", "High (n=43)", ""], ["Age (years)", "", "", "", ""], ["≤65", "56", "32", "24", "0.1125"], [">65", "30", "11", "19", ""], ["Gender", "", "", "", ""], ["Male", "50", "22", "28", "0.2744"], ["Female", "36", "21", "15", ""], ["Tumor size", "", "", "", ""], [">4cm", "35", "18", "17", "1.000"], ["≤4cm", "51", "25", "26", ""], ["Tumor location", "", "", "", ""], ["Head", "49", "25", "24", "1.000"], ["Body/tail", "37", "18", "17", ""], ["Clinical stage (AJCC)", "", "", "", ""], ["I–II", "66", "38", "28", "0.0202*"], ["III–IV", "20", "5", "15", ""], ["T-Primary tumor", "", "", "", ""], ["T1-T2", "48", "30", "18", "0.0164*"], ["T3-T4", "38", "13", "25", ""], ["N-Regional lymph nodes", "", "", "", ""], ["N0", "51", "31", "20", "0.0275*"], ["N1", "35", "12", "23", ""], ["M-Distant metastasis", "", "", "", ""], ["M0", "77", "40", "37", "0.4833"], ["M1", "9", "3", "6", ""]], "row_count": 26, "column_count": 5, "numeric_cells": 63, "header_rows": 2, "locator": "section[19]/table-wrap[1]#t0001"}}, {"id": "asset:table:pmid:33447050:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9f4f9a54f911eb681f69bf065d055b8014e64a1d0a4cf7a447e277bbe515ed79", "bytes": 1074, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#t0002", "version": null, "note": "Cox Regression Analysis of BC037916 Expression with Cancer-Specific Mortality in Pancreatic Cancer", "structure": {"pmcid": "PMC7801918", "section_index": 20, "section_title": "BC037916 Serves as an Independent Prognostic Factor for Pancreatic Cancer", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Cox Regression Analysis of BC037916 Expression with Cancer-Specific Mortality in Pancreatic Cancer", "rows": [["", "Univariate Analysis", "Multivariate Analysis"], ["", "HR (95% CI)", "P value", "HR (95% CI)", "P value"], ["BC037916 (high vs low)", "2.81(1.65–4.79)", "0.000***", "2.13 (1.18–3.83", "0.012*"], ["Gender (male vs female)", "0.67 (0.39–1.13)", "0.133", "", ""], ["Age (>65 vs ≤65)", "0.78 (0.46–1.32)", "0.358", "", ""], ["Tumor Size (>4cm vs ≤4cm)", "1.20 (0.71–2.03)", "0.490", "", ""], ["Tumor location (Head vs bodyandtail)", "1.26 (0.76–2.10)", "0.377", "", ""], ["Clinical Stage (I–II vs III–IV)", "2.15 (1.22–3.79)", "0.008**", "1.92 (1.08–3.41)", "0.026*"], ["T-Primary tumor (T1–2 vs T3–4)", "1.76 (1.01–2.93)", "0.030*", "1.32 (0.77–2.27)", "0.315"], ["N-Regional lymph nodes (N0 vs N1)", "2.17 (1.30–3.63)", "0.003**", "1.78 (1.05–3.04)", "0.034*"], ["M-Distant metastasis (M0 vs M1)", "0.88 (0.38–2.04)", "0.762", "", ""]], "row_count": 11, "column_count": 5, "numeric_cells": 32, "header_rows": 2, "locator": "section[20]/table-wrap[1]#t0002"}}], "gaps": ["asset:data:geo:GSE16515 not downloaded", "asset:data:geo:GSE16515 licence not read", "asset:data:geo:GSE32688 not downloaded", "asset:data:geo:GSE32688 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Data were analyzed by SPSS software (v16.0, SPSS, Inc., Chicago, IL, USA) and shown as mean ± standard deviation (SD). Student’s t-test was carried out to compare the differences between the two groups. The clinical characteristics of tumors with differential BC037916 expression were determined by the Chi-square tests. Cox regression model was employed to determine univariate and multivariate hazard ratios. Patients’ survival analyses were carried out using Kaplan-Meier analysis and Log-rank test."}}, {"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"}}, {"id": "method-4", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}], "targets": [], "gaps": []}, "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE16515", "GSE32688"], "resolved_accessions": ["GSE16515", "GSE32688"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE16515, GSE32688 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": ["survival_km"], "assets": ["source:pmid:33447050", "data:geo:GSE16515", "asset:table:pmid:33447050:1", "asset:table:pmid:33447050:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE16515"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:26:09Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32871, "completion_tokens": 1366, "cached_tokens": 785}}, "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:33447050", "type": "paper", "label": "pmid:33447050"}, {"id": "source:pmid:33447050", "type": "manuscript", "label": "PMID 33447050 full text"}, {"id": "data:geo:GSE16515", "type": "dataset", "label": "GEO GSE16515"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33447050", "type": "paper", "label": "pmid:33447050"}, {"id": "source:pmid:33447050", "type": "manuscript", "label": "PMID 33447050 full text"}, {"id": "data:geo:GSE16515", "type": "dataset", "label": "GEO GSE16515"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33447050", "type": "extraction", "used": ["source:pmid:33447050"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE16515", "type": "accession_resolution", "used": ["data:geo:GSE16515"], "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:33447050", "parent_hash": "sha256:4fa8edce080f44e9c76bdc179c2820b451d5bbee67ec2c4fc0e410ca8b4c3e34", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE16515 licence not read", "asset:data:geo:GSE16515 not downloaded", "asset:data:geo:GSE32688 licence not read", "asset:data:geo:GSE32688 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["T-PCR. Effects of BC037916 on proliferation, apoptosis, and invasion of pancreatic cancer cells wer", "halted cell cycle progression, and promoted apoptosis in both PANC-1 and SW1990 cells. In contrast"], "order_basis": "paper_text_order:667", "id": "assay:1"}, {"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": ["c factor of pancreatic cancer. Functionally, knockdown of BC037916 repressed cell proliferation, in", "Western blot assays suggested that BC037916 knockdown also suppressed the activation of JAK2/STAT3"], "order_basis": "paper_text_order:1237", "id": "assay:2"}, {"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": ["the tumor growth of xenografted SW1990 cells in vivo. Results of Western blot assays suggested th"], "order_basis": "paper_text_order:1575", "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": 0.93, "evidence": ["xenografted SW1990 cells in vivo. Results of Western blot assays suggested that BC037916 knockdown als"], "order_basis": "paper_text_order:1595", "id": "assay:4"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Data were analyzed by SPSS software (v16.0, SPSS, Inc., Chicago, IL, USA) and shown as mean ± standard deviation (SD). Student’s t-test was carried out to compare the differences between the two groups. The clinical characteristics of tumors with differential BC037916 expression were determined by the Chi-square tests. Cox regression model was employed to determine univariate and multivariate hazard ratios. Patients’ survival analyses were carried out using Kaplan-Meier analysis and Log-rank test."], "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":"2026-11-04T02:26:59+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}}}