{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41376822", "kind": "science-record", "revision": 2, "content_hash": "sha256:d9e84630fc8c742e9170fbb484587c0278ad5be8f6c42617ad348d3d8d1d9676", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:52Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrative analysis of tissue and circulating miRNAs as biomarkers for progression and survival in hepatocellular carcinoma.", "doi": "10.1016/j.ncrna.2025.11.002", "pmid": "41376822", "authors": null, "journal": "Non-coding RNA research", "year": 2026, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 16.0, "unit": "mirnas", "tolerance": null, "source": "chars 750-950 of source sha256 59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7"}, "evidence": [{"asset": "source:pmid:41376822", "locator": "chars 750-950 of source sha256 59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7", "quote": "We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41376822"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:41376822", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41376822' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41376822", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.ncrna.2025.11.002", "sha256": "sha256:59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.ncrna.2025.11.002", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41376822:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9608640486ea80bfe901d37201443a70bd59d034a99f1646cc6fb36c5d396c1b", "bytes": 968, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#tbl1", "version": null, "note": "Differentially expressed miRNAs in HCC tissues. List of 16 significantly dysregulated miRNAs identified from TCGA-LIHC dataset, with corresponding log2 fold change, p-values, and expression direction (upregulated or downregulated) between tumor and normal samples.", "structure": {"pmcid": "PMC12686728", "section_index": 15, "section_title": "Differential expression analysis of TCGA liver hepatocellular carcinoma (LIHC) dataset", "row_count": 11, "column_count": 4}, "table": {"label": "Table 1", "caption": "Differentially expressed miRNAs in HCC tissues. List of 16 significantly dysregulated miRNAs identified from TCGA-LIHC dataset, with corresponding log2 fold change, p-values, and expression direction (upregulated or downregulated) between tumor and normal samples.", "rows": [["miRNA", "log2FC", "adj. p-value", "Regulation"], ["hsa-miR-1258", "−2.12", "3.59 × 10−83", "Down"], ["hsa-miR-490", "−2.16", "3.04 × 10−76", "Down"], ["hsa-miR-383", "−1.53", "1.40 × 10−31", "Down"], ["hsa-miR-6718", "−1.15", "3.66 × 10−21", "Down"], ["hsa-miR-5589", "−1.05", "1.37 × 10−18", "Down"], ["hsa-miR-1247", "−1.16", "6.73 × 10−18", "Down"], ["hsa-miR-187", "−1.07", "1.55 × 10−17", "Down"], ["hsa-miR-767", "+1.33", "3.42 × 10−27", "Up"], ["hsa-miR-105-2", "+1.19", "1.02 × 10−24", "Up"], ["hsa-miR-105-1", "+1.18", "7.93 × 10−23", "Up"]], "row_count": 11, "column_count": 4, "numeric_cells": 30, "header_rows": 1, "locator": "section[15]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:41376822:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bfdb785f315e52818bb105698e738637915e50463e417fc06607387cbe19d09b", "bytes": 1417, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[2]#tbl2", "version": null, "note": "Comparison of representative differentially expressed miRNAs and associated functional enrichment across liver disease conditions. The table lists key upregulated and downregulated miRNAs for HCC versus Non-Cancer, Cirrhosis, and Hepatitis, alongside top enriched KEGG pathways and significant Gene Ontology (GO) biological processes. Pathways and processes highlight the predominant molecular and cellular functions affected in each comparison.", "structure": {"pmcid": "PMC12686728", "section_index": 15, "section_title": "Differential expression analysis of TCGA liver hepatocellular carcinoma (LIHC) dataset", "row_count": 4, "column_count": 5}, "table": {"label": "Table 2", "caption": "Comparison of representative differentially expressed miRNAs and associated functional enrichment across liver disease conditions. The table lists key upregulated and downregulated miRNAs for HCC versus Non-Cancer, Cirrhosis, and Hepatitis, alongside top enriched KEGG pathways and significant Gene Ontology (GO) biological processes. Pathways and processes highlight the predominant molecular and cellular functions affected in each comparison.", "rows": [["Comparison", "Representative Upregulated miRNAs", "Representative Downregulated miRNAs", "Top Enriched Pathways (KEGG)", "Key GO Processes"], ["HCC vs NonCancer", "hsa-miR-5100, hsa-miR-195-5p, hsa-miR-221-3p, hsa-miR-1290", "None", "Cell cycle, Endocytosis, Proteoglycans in cancer, Colorectal cancer", "Nucleocytoplasmic transport, Chromosome segregation"], ["HCC vs Cirrhosis", "hsa-miR-422a, hsa-miR-204-3p, hsa-miR-744-5p", "hsa-miR-4687-3p, hsa-miR-3619-3p, hsa-miR-30c-1-3p", "Cell cycle, ER protein processing, Senescence, Neurodegeneration", "Protein localization to nucleus, Wnt signaling"], ["HCC vs Hepatitis", "hsa-miR-1185-2-3p, hsa-miR-6132, hsa-miR-422a", "hsa-miR-6778-5p, hsa-miR-3619-3p, hsa-miR-4739", "Cell cycle, Viral carcinogenesis, Endocytosis, Adherens junction", "RNA localization, Nuclear transport, Autophagy"]], "row_count": 4, "column_count": 5, "numeric_cells": 5, "header_rows": 1, "locator": "section[15]/table-wrap[2]#tbl2"}}, {"id": "asset:table:pmid:41376822:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:714ba2f136154618618700bc937299222e03805a507da25f5c4355034e582ed8", "bytes": 1580, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[24]/table-wrap[1]#tbl3", "version": null, "note": "Tabular presentation showing AFP association: Positive/Negative/None = direction of correlation, Stage/Child-Pugh association: Strong/Moderate/Significant/None = relative significance from Kruskal-Wallis tests. Interpretation column provides biologically meaningful insight for each miRNA.", "structure": {"pmcid": "PMC12686728", "section_index": 24, "section_title": "Association of circulating miRNAs with AFP levels and cancer stage", "row_count": 10, "column_count": 5}, "table": {"label": "Table 3", "caption": "Tabular presentation showing AFP association: Positive/Negative/None = direction of correlation, Stage/Child-Pugh association: Strong/Moderate/Significant/None = relative significance from Kruskal-Wallis tests. Interpretation column provides biologically meaningful insight for each miRNA.", "rows": [["miRNA", "AFP Association", "Stage Association", "Child-Pugh Association", "Interpretation"], ["hsa-miR-3619-3p", "Negative", "Moderate", "Moderate", "Strong inverse correlation with AFP; expression decreases with tumor progression."], ["hsa-miR-1290", "Negative", "Strong", "Strong", "Consistently lower in higher stages; mirrors tissue dysregulation."], ["hsa-miR-1185-2-3p", "Positive", "Strong", "Moderate", "Higher expression in advanced stages; potential biomarker for progression."], ["hsa-miR-422a", "Positive", "Strong", "Significant", "Upregulated with stage; may reflect liver function (Child-Pugh)."], ["hsa-miR-4687-3p", "Negative", "Moderate", "Significant", "Downregulated in higher Child-Pugh classes; may indicate disease severity."], ["hsa-miR-204-3p", "Positive", "Moderate", "Significant", "Expression tracks AFP and liver function."], ["hsa-miR-5100", "None", "Strong", "Strong", "Stage- and Child-Pugh-dependent; less informative for AFP."], ["hsa-miR-195-5p", "None", "Strong", "Significant", "Reflects cancer stage; minimal AFP correlation."], ["hsa-miR-6132", "None", "None", "None", "No clear clinical associations; may be HCC-specific but not stage-dependent."]], "row_count": 10, "column_count": 5, "numeric_cells": 9, "header_rows": 1, "locator": "section[24]/table-wrap[1]#tbl3"}}, {"id": "asset:table:pmid:41376822:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:85adcad6d6258881fc0a0f4dfae8f74d9544d4884cb167dd8532e974de22ea00", "bytes": 2759, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[27]/table-wrap[1]#tbl4", "version": null, "note": "Differentially expressed miRNAs identified in hepatocellular carcinoma (HCC) tissue and serum. The table shows expression direction, key clinical associations (KM and multivariable Cox analyses), concordance with prior literature, proposed molecular roles or pathways, and validating references.", "structure": {"pmcid": "PMC12686728", "section_index": 27, "section_title": "Circulating miRNAs and clinical translation", "row_count": 11, "column_count": 7}, "table": {"label": "Table 4", "caption": "Differentially expressed miRNAs identified in hepatocellular carcinoma (HCC) tissue and serum. The table shows expression direction, key clinical associations (KM and multivariable Cox analyses), concordance with prior literature, proposed molecular roles or pathways, and validating references.", "rows": [["miRNA", "Source (this study)", "Direction in HCC (tumor vs normal or HCC vs non-HCC serum)", "Key clinical association in this study", "Concordance with prior literature", "Proposed role/pathways", "Validating refs"], ["hsa-miR-187", "Tissue", "↑", "Independent risk in multivariable Cox (HR 1.40; p < 0.001); KM significant", "Nonconcurrent with our study Reported to be tumor suppressor and downregulated in HCC", "miR-187 acted as a tumor suppressor in HCC progression via direct targeting of IGF-1R.", "[17]; Present study"], ["hsa-miR-6718", "Tissue", "↑", "Independent risk in multivariable Cox (HR 1.29; p = 0.045)", "Novel/under-reported in HCC", "Putative cell-cycle/MAPK regulation (by enrichment)", "Present study"], ["hsa-miR-5589", "Tissue", "↓", "Concurrent with previous study; Protective in multivariable Cox (HR 0.88; p = 0.038)", "under-reported in HCC", "Can upregulate CDK1 and CCNA2 and promote oncogenesis", "[21]; Present study"], ["hsa-miR-106b", "Tissue", "↑ (T3/T4 > T1/T2)", "Stage-linked upregulation (advanced T); marker of aggressiveness", "Consistent with previous study on HCC and poorer outcomes in epithelial cancers", "Inhibits RUNX3", "[22]; Present study"], ["hsa-miR-124 family (-1/-2/-3)", "Tissue", "↓ (M1 < M0)", "Down in metastatic tumors; metastasis suppressor signal", "Concordant with HCC data showing miR-124-3p suppresses invasion via CRKL/ERK", "ERK/CRKL, anti-metastatic", "[30]; Present study"], ["hsa-miR-33b", "Tissue", "variable", "KM significant; not independent in Cox", "Prior HCC work links miR-33b to proliferation and mobility", "Notch1/Fli-1 axis", "[31]; Present study"], ["hsa-miR-424 (-3p/-5p)", "Tissue", "variable", "KM significant; not independent in Cox", "Mixed reports in HCC (pro- or anti-metastatic depending on isoform/context)", "SRF-STAT1/2; CHEK1/cell cycle", "[32,33]; Present study"], ["miR-21", "Tissue & serum (literature)", "↑", "–", "Robust diagnostic/prognostic signal across cancers and HCC; correlates with advanced stage and poorer survival", "PTEN, PDCD4; apoptosis evasion", "[34]"], ["miR-122", "Tissue & serum", "↓", "–", "Liver-specific tumor suppressor; consistently down in HCC", "Metabolism, cell-cycle control", "[16]"], ["miR-221/222", "Tissue & serum", "↑", "–", "Recurrent oncogenic pair in HCC; progression/recurrence associations", "CDKN1B/p27, CDKN1C/p57", "[16]"]], "row_count": 11, "column_count": 7, "numeric_cells": 28, "header_rows": 1, "locator": "section[27]/table-wrap[1]#tbl4"}}], "gaps": ["asset:source:pmid:41376822 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41376822", "asset:table:pmid:41376822:1", "asset:table:pmid:41376822:2", "asset:table:pmid:41376822:3", "asset:table:pmid:41376822:4"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41376822"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "f380d52616ddc458d9f19f64209efde8d9db7c241aec86a45b21a0bfc61788fd", "source_hash": "59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7", "raw_response_sha256": "sha256:25c0c79d5c259e64196d90e027ef41394430ab01f3bc05317559ecc3f2048b3f", "raw_response_chars": 3937}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "d690be862bb161c09e7a529b93f68a51d3bf4bfbc3d4fbc4df12ca39c5716276", "source_hash": "59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7", "raw_response_sha256": "sha256:3d069d90d38bb022738ec8409d419eab27bc53279a9f2dc7459570a1ccfc0fb6", "raw_response_chars": 56166}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "b212cb6973878fda470df1fdca9106f79afecc650022324648905d286c299470", "source_hash": "59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7", "raw_response": "{\"parent_value\":16,\"unit\":\"miRNAs\",\"evidence\":\"We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect.\",\"target_result\":\"16 significantly dysregulated miRNAs in HCC tissues\",\"number_stated\":true}", "reading": {"parent_value": 16, "unit": "miRNAs", "evidence": "We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect.", "target_result": "16 significantly dysregulated miRNAs in HCC tissues", "number_stated": true, "source_locator": "chars 750-950 of source sha256 59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7"}, "recorded_at": "2026-10-31T15:15:54.764185+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "46a78e8a68d8504902cc04a79c537a896cc92ed598799c58558836f497c5cedf", "source_hash": "59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7", "raw_response": "<think>We need reason carefully, output JSON only. Need extract single numerical result that replication registered target main finding headline number, stated by paper, unit printed. Need determine what is headline numerical result. Source study integrative tissue/serum miRNAs HCC, main findings 16 dysregulated miRNAs, hsa-miR-187 significant survival p=.0324, Cox HR 1.25 etc. User asking single numerical result paper states for registered target: \"the headline numerical result the paper states for its main finding\". Need infer likely target 16 (number of significantly dysregulated miRNAs) from abstract and result. Need decide. We have ample budget but must not overanalyze? Need parse user intent exactly.\n\n\"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\"\n\nREGISTERED TARGET: \"the headline numerical result the paper states for its main finding\"\n\nThey expect identify main finding's headline numerical result from abstract perhaps 16. Source abstract \"We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect.\" Main numerical result 16. Unit likely \"miRNAs\" (paper prints). Evidence exact contiguous quote contains 16 and target. Could quote abstract whole sentence. parent_value 16, unit \"miRNAs\", target_result e.g. \"16 significantly dysregulated miRNAs in HCC tissues\" number_stated true. Need consider if headline number is hsa-miR-187 HR 1.25 etc. The registered target generic likely mapped to headline numerical result of main finding. In biomedical paper often key outcome HR, sample size? Need discern expected based task templates. Need reason what \"single numerical result\" means and \"parent_value\" schema odd. Could be from replication check numerical result. They want \"headline number\" not multiple. For abstract of computational paper main finding is 16 DE miRNAs. Source begins abstract identifies 16. Conclusion focuses hsa-miR-187/6718 no number. Likely answer 16 miRNAs with evidence exact sentence. But need ensure \"unit must be unit paper prints\" if no unit? Count \"miRNAs\". They may consider \"16 significantly dysregulated miRNAs\" unit \"miRNAs\" acceptable. They might expect unit empty because no explicit unit? Many similar tasks have unit like \"%\" \"cases\" etc. Count miRNAs is natural unit.\n\nLet's consider alternative interpretation: registered target could mean survival association and headline numerical result = HR=1.25? \"the headline numerical result the paper states for its main finding\" main finding prognostic biomarkers. The main claim abstract \"identified 16 significantly dysregulated miRNAs in HCC tissues\" with 16 main finding. Usually in extraction evaluation target not explicitly named beyond \"headline numerical result\". They expect pick the single key count in abstract. We need output only JSON object. We can ensure evidence whole clause abstract with 16: \"We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect.\" That is exact. Unit \"miRNAs\". target_result \"16 significantly dysregulated miRNAs in HCC tissues.\" Parent 16. No invented.\n\nNeed examine if 16 percent 0.85 % candidate? Single number 16. Good.\n\nLet's not overcomplicate. Need fulfill developer \"You extract claims only from supplied source text. Reply with JSON object.\" Only JSON final. Should target_result maybe \"The study identified 16 significantly dysregulated miRNAs in HCC tissues.\" Unit \"miRNAs\". Evidence exact quote sentence. Is headline result a count not value? Yes.\n\nCould parent_value 16 unit \"\"? They expressly \"unit must be the unit the paper prints.\" Text prints 16 miRNAs, so use miRNAs. No need percent.\n\nLet's inspect source abstract: \"We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect.\" Exactly. Good.\n\nWe should maybe choose evidence shorter contiguous clause \"We identified 16 significantly dysregulated miRNAs in HCC tissues\" but user \"When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" Whole sentence is safe and exact. It includes other numbers? No other numbers in sentence besides 16. hsa names have numbers, but those aren't numeric results. Fine.\n\ntarget_result may not need say calculated. \"The paper reports 16 significantly dysregulated miRNAs in HCC tissues as its headline main finding.\" That is a claim direct from source, acceptable. Could simpler \"16 significantly dysregulated miRNAs in HCC tissues.\" We should ensure schema fields all included, no extra. Use valid JSON double quotes. number_stated true. final.</think>\n\n{\"parent_value\":16,\"unit\":\"miRNAs\",\"evidence\":\"We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect.\",\"target_result\":\"16 significantly dysregulated miRNAs in HCC tissues.\",\"number_stated\":true}", "reading": {"parent_value": 16, "unit": "miRNAs", "evidence": "We identified 16 significantly dysregulated miRNAs in HCC tissues, including hsa-miR-187 and hsa-miR-6718, which were associated with poor survival, and hsa-miR-5589, which showed a protective effect.", "target_result": "16 significantly dysregulated miRNAs in HCC tissues.", "number_stated": true, "source_locator": "chars 750-950 of source sha256 59f1130ccae1528afbe456a634081733a0d993a38e7f7e81ade93bc591d56ff7"}, "recorded_at": "2026-10-31T15:16:18.213215+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "16 miRNAs were significantly dysregulated between HCC tumor and non-tumor tissues.", "minimax_alt": "Using this threshold, we found a focused set of 16 miRNAs that showed significant expression changes between tumour and non-tumour tissues (Fig. 1).", "decisive": false}, "analysis_methods": {"minimax": ["Differential expression analysis using limma-trend", "Kaplan-Meier survival analysis with log-rank tests", "Univariate and multivariate Cox proportional hazards regression", "DAVID Gene Ontology and KEGG functional enrichment analysis", "Clinical subgroup differential expression analysis"], "minimax_alt": ["limma-trend (v3.50.0) differential expression analysis", "adjusted-p-value and absolute-log2-fold-change filtering", "DAVID GO and KEGG functional enrichment analysis", "Kaplan–Meier survival analysis with log-rank tests", "univariate and multivariate Cox proportional hazards regression", "clinical subgroup differential expression analysis"], "decisive": false}, "statistical_method": {"minimax": "limma-trend", "minimax_alt": "limma-trend (v3.50.0)", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:83acc78b554a872818b0562a56e3703db03ff814ea6f5fc3423b52186b55d6e9", "type": "sep_package", "label": "SEP v1 package for pmid:41376822"}], "activities": [{"id": "activity:conversion:pmid:41376822", "type": "conversion", "used": ["package:83acc78b554a872818b0562a56e3703db03ff814ea6f5fc3423b52186b55d6e9"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41376822", "parent_hash": "sha256:66f1f39fbfec3c8f57aee75e3d13e7b0d9154a4e2cf74410b3e5de3490cb6382", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41376822 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41376822' does not resolve to a declared asset", "targets"]},"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":"2026-11-04T02:39:07+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}}}