{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33761685", "kind": "science-record", "revision": 6, "content_hash": "sha256:9e999aa70a4268d7f95b94ef1ea1c7a84b47171931f6eb620e078841e1589c98", "created_at": "2026-11-01T15:41:30Z", "updated_at": "2026-11-01T21:24:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of core genes and clinical outcomes in tumors originated from endoderm (gastric cancer and lung carcinoma) via bioinformatics analysis.", "doi": "10.1097/MD.0000000000025154", "pmid": "33761685", "authors": ["Yewen Shi", "Dongmin Chang", "Wenhan Li", "FengYu Zhao", "Xiaoyong Ren", "Bin Hou"], "journal": "Medicine", "year": 2021, "abstract": "ABSTRACT: During last decade, bioinformatics analysis has provided an effective way to study the relationship between various genes and biological processes. In this study, we aimed to identify potential core candidate genes and underlying mechanisms of progression of lung and gastric carcinomas which both originated from endoderm. The expression profiles, GSE54129 (gastric carcinoma) and GSE27262 (lung carcinoma), were collected from GEO database. One hundred eleven patients with gastric carcinoma and 21 health people were included in this research. Meanwhile, there were 25 lung carcinoma patients. Then, 75 differentially expressed genes were selected via GEO2R online tool and Venn software, including 31 up-regulated genes and 44 down-regulated genes. Next, we used Database for Annotation, Visualization, and Integrated Discovery and Metascpe software to analyze Kyoto Encyclopedia of Gene and Genome pathway and gene ontology. Furthermore, Cytoscape software and MCODE App were performed to construct complex of these differentially expressed genes . Twenty core genes were identified, which mainly enriched in extracellular matrix-receptor interaction, focal adhesion, and PI3K-Akt pathway (P < .01). Finally, the significant difference of gene expression between cancer tissues and normal tissues in both lung and gastric carcinomas was examined by Gene Expression Profiling Interactive Analysis database. Twelve candidate genes with positive statistical significance (P < .01), COMP CTHRC1 COL1A1 SPP1 COL11A1 COL10A1 CXCL13 CLDN3 CLDN1 matrix metalloproteinases 7 ADAM12 PLAU, were picked out to further analysis. The Kaplan-Meier plotter website was applied to examine relationship among these genes and clinical outcomes. We found 4 genes (ADAM12, SPP1, COL1A1, COL11A1) were significantly associated with poor prognosis in both lung and gastric carcinoma patients (P < .05). In conclusion, these candidate genes may be potential therapeutic targets for cancer treatment.", "claims": [{"id": "claim-method", "statement": "Thus, we applied Kaplan–Meier-plotter website to estimate the effect of candidate genes on patients’ clinical outcomes based on GEO, EGA, and TCGA databases. The hazard ratio with 95% confidence intervals and log rank P value were calculated and showed on the plot.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33761685", "locator": "sections[8] \"Expression levels of hub genes and clinical outcomes analysis\" paragraph 2", "quote": "Thus, we applied Kaplan–Meier-plotter website to estimate the effect of candidate genes on patients’ clinical outcomes based on GEO, EGA, and TCGA databases. The hazard ratio with 95% confidence intervals and log rank P value were calculated and showed on the plot."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated during and/or analyzed during the current study are publicly available.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33761685", "locator": "sections[18] \"fn-group\" paragraph 1", "quote": "The datasets generated during and/or analyzed during the current study are publicly available."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:33761685"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33761685", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1097/MD.0000000000025154", "sha256": "sha256:6c9257d392d51de9e8f04a4b4a1cca8b746b0f92666d36cfaffb092044911261", "bytes": 25229, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1097/MD.0000000000025154", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10545272", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33761685:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0177b89ceaa2cdc6bab75be31d13c55fb820c832fc8039533c45ed6c2ba6f003", "bytes": 810, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "All 75 differentially expressed genes (DEGs) were selected from 2 GSE datasets, including 31 up-regulated genes and 44 down-regulated genes.", "structure": {"pmcid": "PMC10545272", "section_index": 10, "section_title": "Identification of core genes in tumors originated from endoderm", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "All 75 differentially expressed genes (DEGs) were selected from 2 GSE datasets, including 31 up-regulated genes and 44 down-regulated genes.", "rows": [["DEGs", "Genes name"], ["Up-regulated", "ADAM12 PLAU MMP7 IGF2BP3 ANP32E CXCL13 COL1A1 CCL19 PCDH7 CST1 HOXA10 SPP1 GREM1 BUB1 COL3A1 CLDN3 HOXC10 COMP THBS2 WISP1 ESYT2 FDCSP SULF1 DOK5 ENC1 CLDN1 COL10A1 COL11A1 CTHRC1 COL1A2 PTPRB"], ["Down-regulated", "OTUD1 FRMD3 GATA6 MAL AHNAK KLF4 TMEM246 ABCA8 ACKR4 NEDD4L ASPA BMP2 ADRB2 FKBP1B KANK4 LAMA3 MIR6872 SEMA3B ADGRG6 NCKAP5 PLCB4 MYRF CLIC3 ADAMTS15 ADGRL3 CA2 ADTRP SSTR1 MYZAP PLLP HHIP PGC SOSTDC1 LRP4 RMST PIP5K1B SCNN1G KLK11 MAMDC2 BMP5 CLDN18 ABHD6 GKN2 HYAL1"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33761685:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b203612078151b3180301fb9f16cf22969b5c3c8713e647c2c3680eb87b0e945", "bytes": 2447, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T2", "version": null, "note": "Different genes ontology in tumors originated from endoderm.", "structure": {"pmcid": "PMC10545272", "section_index": 11, "section_title": "DEGs ontology and KEGG pathway analysis in tumors originated from endoderm", "row_count": 24, "column_count": 6}, "table": {"label": "Table 2", "caption": "Different genes ontology in tumors originated from endoderm.", "rows": [["Expression", "Category", "Term", "Count", "P value", "FDR"], ["up-regulated", "GOTERM_BP_DIRECT", "GO:0030199–collagen fibril organization", "5", "9.1E-8", "1.14E-4"], ["", "GOTERM_BP_DIRECT", "GO:0007155∼cell adhesion", "5", "1.2E-4", "0.149489"], ["", "GOTERM_BP_DIRECT", "GO:0009954∼proximal/distal pattern formation", "3", "5.9E-4", "0.738304"], ["", "GOTERM_BP_DIRECT", "GO:0030326∼embryonic limb morphogenesis", "3", "1.0E-3", "1.233105"], ["", "GOTERM_BP_DIRECT", "GO:0071230∼cellular response to amino acid stimulus", "3", "2.0E-3", "2.464763"], ["", "GOTERM_CC_DIRECT", "GO:0005581∼collagen trimer", "6", "3.5E-8", "3.2E-5"], ["", "GOTERM_CC_DIRECT", "GO:0005615∼extracellular space", "10", "1.5E-5", "0.013266"], ["", "GOTERM_CC_DIRECT", "GO:0005578∼proteinaceous extracellular matrix", "5", "2.1E-4", "0.194531"], ["", "GOTERM_CC_DIRECT", "GO:0005584∼collagen type I trimer", "2", "3.4E-3", "3.032843"], ["", "GOTERM_MF_DIRECT", "GO:0005201∼extracellular matrix structural constituent", "4", "3.5E-5", "0.031544"], ["", "GOTERM_MF_DIRECT", "GO:0008201∼heparin binding", "4", "8.1E-4", "0.721484"], ["", "GOTERM_MF_DIRECT", "GO:0042802∼identical protein binding", "4", "1.6E-3", "1.446008"], ["", "GOTERM_MF_DIRECT", "GO:0048407∼platelet-derived growth factor binding", "2", "5.3E-3", "4.595293"], ["", "GOTERM_MF_DIRECT", "GO:0005509∼calcium ion binding", "5", "1.6E-2", "13.686396"], ["Down-regulated", "GOTERM_BP_DIRECT", "GO:0030509∼BMP signaling pathway", "3", "5.6E-3", "7.069993"], ["", "GOTERM_BP_DIRECT", "GO:2000065∼negative regulation of cortisol biosynthetic process", "2", "9.4E-3", "11.498954"], ["", "GOTERM_BP_DIRECT", "GO:0008285∼negative regulation of cell proliferation", "4", "1.3E-2", "15.820081"], ["", "GOTERM_BP_DIRECT", "GO:0043569∼negative regulation of insulin-like growth factor receptor signaling pathway", "2", "1.4E-2", "16.743886"], ["", "GOTERM_BP_DIRECT", "GO:0040007∼growth", "2", "3.9E-2", "40.514446"], ["", "GOTERM_CC_DIRECT", "GO:0005615∼extracellular space", "9", "9.2E-4", "0.886836"], ["", "GOTERM_CC_DIRECT", "GO:0070062∼extracellular exosome", "11", "3.6E-2", "29.452708"], ["", "GOTERM_MF_DIRECT", "GO:0070700∼BMP receptor binding", "2", "9.2E-4", "11.849758"], ["", "GOTERM_MF_DIRECT", "GO:0005160∼transforming growth factor beta receptor binding", "2", "3.6E-2", "44.045834"]], "row_count": 24, "column_count": 6, "numeric_cells": 92, "header_rows": 2, "locator": "section[11]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:33761685:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:721ae25352f299cfe4d5939f31ae5b5ae78797a44310b72151eb529c9f2d7d01", "bytes": 890, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#T3", "version": null, "note": "KEGG pathway analysis of different genes.", "structure": {"pmcid": "PMC10545272", "section_index": 11, "section_title": "DEGs ontology and KEGG pathway analysis in tumors originated from endoderm", "row_count": 7, "column_count": 6}, "table": {"label": "Table 3", "caption": "KEGG pathway analysis of different genes.", "rows": [["Pathway ID", "Name", "Count", "%", "P value", "Genes"], ["hsa04512", "ECM–receptor interaction", "8", "0.1", "5.7E-8", "LAMA3, COMP, COL3A1, COL1A2, COL1A1, THBS2, COL11A1, SPP1"], ["hsa04510", "Focal adhesion", "8", "0.1", "2.0E-5", "LAMA3, COMP, COL3A1, COL1A2, COL1A1, THBS2, COL11A1, SPP1"], ["hsa05146", "Amoebiasis", "6", "01.", "7.6E-5", "PLCB4, LAMA3, COL3A1, COL1A2, COL1A1, COL11A1"], ["hsa04974", "Protein digestion and absorption", "5", "0.1", "4.2E-4", "COL3A1, COL1A2, COL1A1, COL11A1, COL10A1"], ["hsa04151", "PI3K-Akt signaling pathway", "8", "0.1", "4.4E-4", "LAMA3, COMP, COL3A1, COL1A2, COL1A1, THBS2, COL11A1, SPP1"], ["hsa04611", "Platelet activation", "5", "0.1", "2.0E-3", "PLCB4, COL3A1, COL1A2, COL1A1, COL11A1"]], "row_count": 7, "column_count": 6, "numeric_cells": 30, "header_rows": 1, "locator": "section[11]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:33761685:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4fc988b905f3c5e24e75b766bdaff892c21cf3a73127808ad6df6ab786398a55", "bytes": 546, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T4", "version": null, "note": "KEGG pathway analysis of 20 selected genes.", "structure": {"pmcid": "PMC10545272", "section_index": 13, "section_title": "Reanalysis of 20 selected genes by KEGG pathway enrichment", "row_count": 4, "column_count": 6}, "table": {"label": "Table 4", "caption": "KEGG pathway analysis of 20 selected genes.", "rows": [["Pathway ID", "Name", "Count", "%", "P value", "Genes"], ["hsa04512", "ECM–receptor interaction", "6", "30", "5.0E-7", "COMP, COL1A2, COL1A1, COL11A1, THBS2, SPP1"], ["hsa04510", "Focal adhesion", "6", "30", "3.6E-5", "COMP, COL1A2, COL1A1, COL11A1, THBS2, SPP1"], ["hsa04151", "PI3K-Akt signaling pathway", "6", "30", "4.1E-4", "COMP, COL1A2, COL1A1, COL11A1, THBS2, SPP1"]], "row_count": 4, "column_count": 6, "numeric_cells": 15, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T4"}}, {"id": "asset:table:pmid:33761685:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5ba6b642612bffb8c0d7e8634ae00ad3c06e5c5be29e25bd0b76cdc2dea51ee4", "bytes": 813, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T5", "version": null, "note": "Different expression of 20 genes via GEPIA online tool.", "structure": {"pmcid": "PMC10545272", "section_index": 14, "section_title": "Analysis of core genes via the GEPIA and Kaplan–Meier plotter", "row_count": 5, "column_count": 2}, "table": {"label": "Table 5", "caption": "Different expression of 20 genes via GEPIA online tool.", "rows": [["Category", "Genes"], ["Genes with statistical difference in gastric cancers (P < .01)", "ADAM12 CLDN1 CLDN3 COL1A1 COL1A2 COL10A1 COL11A1 COMP CTHRC1 CXCL13 MMP7 PLAU SPP1 THBS2 WISP1"], ["Genes with statistical difference in lung cancers (P > .01)", "ACKR4 ADAM12 BMP2 CCL19 CLDN1 CLDN3 CLDN18 COL1A1 COL10A1 COL11A1 COMP CTHRC1 CXCL13 MMP7 PLAU SPP1 SSTR1"], ["Genes with statistical difference in 2 cancers (P < .01)", "COMP CTHRC1 COL1A1 SPP1 COL11A1 COL10A1 CXCL13 CLDN3 CLDN1 MMP7 ADAM12 PLAU"], ["Genes without statistical difference in 2 cancers (P > .01)", "COL1A2 BMP2 CCL19 ACKR4 SSTR1 CLDN18 THBS2 WISP1"]], "row_count": 5, "column_count": 2, "numeric_cells": 8, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T5"}}, {"id": "asset:table:pmid:33761685:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3f7574d28498b0006b4b74d2c5c2b1c7b25d8971bf99a9a4ba2d8763c3d69e2e", "bytes": 682, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#T6", "version": null, "note": "The prognostic information of the 12 key genes in both 2 cancers.", "structure": {"pmcid": "PMC10545272", "section_index": 14, "section_title": "Analysis of core genes via the GEPIA and Kaplan–Meier plotter", "row_count": 5, "column_count": 2}, "table": {"label": "Table 6", "caption": "The prognostic information of the 12 key genes in both 2 cancers.", "rows": [["Category", "Genes"], ["Genes with significantly worse survival in gastric cancer (P < .05)", "ADAM12 CLDN3 COL1A1 COL10A1 COL11A1 COMP CTHRC1 MMP7 PLAU SPP1"], ["Genes with significantly worse survival in lung cancer (P > .05)", "ADAM12 COL1A1 COL11A1 SPP1"], ["Genes with significantly worse survival in both 2 cancer types (P < .05)", "ADAM12 COL1A1 SPP1 COL11A1"], ["Genes without significantly worse survival (P > .05)", "COMP COL10A1 CTHRC1 CXCL13 CLDN3 CLDN1 MMP7 PLAU"]], "row_count": 5, "column_count": 2, "numeric_cells": 8, "header_rows": 1, "locator": "section[14]/table-wrap[2]#T6"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Thus, we applied Kaplan–Meier-plotter website to estimate the effect of candidate genes on patients’ clinical outcomes based on GEO, EGA, and TCGA databases. The hazard ratio with 95% confidence intervals and log rank P value were calculated and showed on the plot."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["The datasets generated during and/or analyzed during the current study are publicly available."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["logrank_test"], "assets": ["source:pmid:33761685", "asset:table:pmid:33761685:1", "asset:table:pmid:33761685:2", "asset:table:pmid:33761685:3", "asset:table:pmid:33761685:4", "asset:table:pmid:33761685:5", "asset:table:pmid:33761685:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:29:04Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 18640, "completion_tokens": 1397, "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:33761685", "type": "paper", "label": "pmid:33761685"}, {"id": "source:pmid:33761685", "type": "manuscript", "label": "PMID 33761685 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33761685", "type": "paper", "label": "pmid:33761685"}, {"id": "source:pmid:33761685", "type": "manuscript", "label": "PMID 33761685 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33761685", "type": "extraction", "used": ["source:pmid:33761685"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33761685", "parent_hash": "sha256:c5cc120d5bccd82acf918b74e7d14e4082691dd40b85d3fa71e47bbe2a695916", "fork_of": null, "generation": 5}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Thus, we applied Kaplan–Meier-plotter website to estimate the effect of candidate genes on patients’ clinical outcomes based on GEO, EGA, and TCGA databases. The hazard ratio with 95% confidence intervals and log rank P value were calculated and showed on the plot."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:41:48+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}}}