{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39911529", "kind": "science-record", "revision": 2, "content_hash": "sha256:b75088b15ab1c8d43ff0edcf44c68618973d89d2b6b0b037e9d4f10f8b8f9cbc", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:33Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Identifying Hub Genes and Pathways in Pancreatic Ductal Adenocarcinoma (PAAD): A comprehensive in silico study.", "doi": "10.1016/j.bbrep.2025.101921", "pmid": "39911529", "authors": null, "journal": "Biochemistry and biophysics reports", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 66.0, "unit": "hub genes", "tolerance": null, "source": "chars 813-1014 of source sha256 aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26"}, "evidence": [{"asset": "source:pmid:39911529", "locator": "chars 813-1014 of source sha256 aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26", "quote": "The analysis of protein-protein interactions (PPI) along with data from the Gene Expression Omnibus (GEO) led to the identification of 66 hub genes and 819 common differentially expressed genes (DEGs)."}]}], "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:39911529"], "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:39911529", "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:39911529' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39911529", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.bbrep.2025.101921", "sha256": "sha256:aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.bbrep.2025.101921", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39911529:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b1ce28fa0cf5aa57595b991c7895cc41e33b4208806610b02cec6fcc993bb978", "bytes": 3706, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tbl1", "version": null, "note": "Functional and pathway enrichment analysis of the common DEGs.", "structure": {"pmcid": "PMC11794163", "section_index": 11, "section_title": "Enrichment analysis revealing muscle cytoskeleton and ECM-receptor interactions", "row_count": 41, "column_count": 4}, "table": {"label": "Table 1", "caption": "Functional and pathway enrichment analysis of the common DEGs.", "rows": [["Category", "Term", "Count", "PValue"], ["GOTERM_BP_DIRECT", "GO:0007155∼cell adhesion", "68", "2.3152201162894E-18"], ["GOTERM_BP_DIRECT", "GO:0030198∼extracellular matrix organization", "34", "2.55505311436389E-14"], ["GOTERM_BP_DIRECT", "GO:0030199∼collagen fibril organization", "20", "2.86039062667398E-12"], ["GOTERM_BP_DIRECT", "GO:0009615∼response to virus", "24", "3.0467039550524E-11"], ["GOTERM_BP_DIRECT", "GO:0045087∼innate immune response", "56", "5.12703607994511E-11"], ["GOTERM_BP_DIRECT", "GO:0051607∼defense response to virus", "33", "9.19122773144152E-10"], ["GOTERM_BP_DIRECT", "GO:0098609∼cell-cell adhesion", "31", "1.25523768696858E-09"], ["GOTERM_BP_DIRECT", "GO:0001525∼angiogenesis", "33", "6.31433577937127E-09"], ["GOTERM_BP_DIRECT", "GO:0016477∼cell migration", "34", "1.58435862152979E-08"], ["GOTERM_BP_DIRECT", "GO:0035987∼endodermal cell differentiation", "12", "3.54494563234197E-08"], ["GOTERM_CC_DIRECT", "GO:0070062∼extracellular exosome", "209", "1.94325487255789E-36"], ["GOTERM_CC_DIRECT", "GO:0005576∼extracellular region", "193", "6.79257111708294E-33"], ["GOTERM_CC_DIRECT", "GO:0005615∼extracellular space", "189", "7.98544054933557E-33"], ["GOTERM_CC_DIRECT", "GO:0062023∼collagen-containing extracellular matrix", "75", "3.83048542521584E-30"], ["GOTERM_CC_DIRECT", "GO:0009986∼cell surface", "86", "7.07444914249172E-24"], ["GOTERM_CC_DIRECT", "GO:0005788∼endoplasmic reticulum lumen", "48", "3.81692376000629E-16"], ["GOTERM_CC_DIRECT", "GO:0005886∼plasma membrane", "307", "2.16789379777687E-14"], ["GOTERM_CC_DIRECT", "GO:0031012∼extracellular matrix", "39", "5.37578980183918E-14"], ["GOTERM_CC_DIRECT", "GO:0005925∼focal adhesion", "53", "1.63099990111405E-13"], ["GOTERM_CC_DIRECT", "GO:0016324∼apical plasma membrane", "50", "8.42322051460147E-13"], ["GOTERM_MF_DIRECT", "GO:0005201∼extracellular matrix structural constituent", "30", "1.51962620511498E-15"], ["GOTERM_MF_DIRECT", "GO:0005178∼integrin binding", "34", "8.01081273367136E-15"], ["GOTERM_MF_DIRECT", "GO:0005518∼collagen binding", "19", "1.42539289754987E-10"], ["GOTERM_MF_DIRECT", "GO:0005515∼protein binding", "589", "3.27383695570828E-10"], ["GOTERM_MF_DIRECT", "GO:0042802∼identical protein binding", "117", "2.13982581822119E-08"], ["GOTERM_MF_DIRECT", "GO:0002020∼protease binding", "21", "4.35690854042364E-08"], ["GOTERM_MF_DIRECT", "GO:0005509∼calcium ion binding", "61", "2.16078827713479E-07"], ["GOTERM_MF_DIRECT", "GO:0004252∼serine-type endopeptidase activity", "26", "3.77068197876645E-07"], ["GOTERM_MF_DIRECT", "GO:0003779∼actin binding", "32", "5.47515172373743E-07"], ["GOTERM_MF_DIRECT", "GO:0030020∼extracellular matrix structural constituent conferring tensile strength", "13", "1.1224463057996E-06"], ["KEGG_PATHWAY", "hsa04820:Cytoskeleton in muscle cells", "34", "1.23803346604229E-08"], ["KEGG_PATHWAY", "hsa04974:Protein digestion and absorption", "22", "1.57326951846491E-08"], ["KEGG_PATHWAY", "hsa04512:ECM-receptor interaction", "20", "2.51772137919501E-08"], ["KEGG_PATHWAY", "hsa05146:Amoebiasis", "20", "2.94607408165439E-07"], ["KEGG_PATHWAY", "hsa04510:Focal adhesion", "28", "1.06711106465381E-06"], ["KEGG_PATHWAY", "hsa04145:Phagosome", "22", "1.56076413008539E-05"], ["KEGG_PATHWAY", "hsa04670:Leukocyte transendothelial migration", "18", "3.08142748503647E-05"], ["KEGG_PATHWAY", "hsa05165:Human papillomavirus infection", "34", "4.57733123284866E-05"], ["KEGG_PATHWAY", "hsa04610:Complement and coagulation cascades", "15", "6.15279695357276E-05"], ["KEGG_PATHWAY", "hsa05205:Proteoglycans in cancer", "23", "2.63911649411884E-04"]], "row_count": 41, "column_count": 4, "numeric_cells": 120, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:39911529:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8f3a324030cf8fdbb7458b50abf61175d2b5eedd685be5b41ddc6ea80c06f7d2", "bytes": 857, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tbl2", "version": null, "note": "The list of top-ranked genes computed by Gephi.", "structure": {"pmcid": "PMC11794163", "section_index": 13, "section_title": "Clustering hub genes using gephi", "row_count": 20, "column_count": 4}, "table": {"label": "Table 2", "caption": "The list of top-ranked genes computed by Gephi.", "rows": [["Module 1", "Module 2", "Module 3", "Module 4"], ["Gene symbol", "Gene symbol", "Gene symbol", "Gene symbol"], ["EGF", "STAT1", "FN1", "ALB"], ["COL1A1", "ICAM1", "ANXA2", "MMP9"], ["ITGB1", "CXCL10", "TAGLN", "PXDN"], ["COL1A2", "PTPRC", "FLNA", "APOE"], ["TIMP1", "CXCR4", "VCL", "CDK1"], ["SPP1", "ITGAM", "ACTA2", "CD9"], ["LOX", "PTGS2", "ANXA1", "CTSB"], ["COL3A1", "CTSS", "CFL1", "RUNX2"], ["MMP9", "CD86", "ACTN1", "CCNB1"], ["LGALS1", "CASP1", "ENO1", "SERPINA1"], ["MET", "ITGB2", "P4HB", "CEACAM5"], ["SDC1", "ISG15", "YWHAZ", "CCNA2"], ["KRT19", "TNFSF10", "PLEC", "GPX2"], ["S100A4", "PSMB9", "SFN", "CLDN1"], ["TWIST1", "TYROBP", "", "SLC2A1"], ["PLAU", "LCK", "", "CBS"], ["", "RAC2", "", "GPT2"], ["", "LGALS3", "", ""]], "row_count": 20, "column_count": 4, "numeric_cells": 10, "header_rows": 2, "locator": "section[13]/table-wrap[1]#tbl2"}}], "gaps": ["asset:source:pmid:39911529 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:39911529", "asset:table:pmid:39911529:1", "asset:table:pmid:39911529:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39911529"]}, "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": "4dc782ab4bd47909e0debef0d6296d9e188fb2c491fbd405d3edf598e6d97ba7", "source_hash": "aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26", "raw_response_sha256": "sha256:b14a9396a40e9f1383f2616fc95c9deb9dc98c67ea667b3a3a5e207ee916be2f", "raw_response_chars": 4051}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "b4b49d3aad218dab369477ce6d15a7c95a1cab213cf134a2f4da3461ef26d6ac", "source_hash": "aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26", "raw_response_sha256": "sha256:7016a83f2537a4d32224e98767b87b6824bcc01ed76ef8c883efcec27b70e15b", "raw_response_chars": 71338}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "e5d9b142a19d2e7554234d6db85016306b3cb508e837905a202fd5dd95af417d", "source_hash": "aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26", "raw_response": "{\"parent_value\":66,\"unit\":\"hub genes\",\"evidence\":\"The analysis of protein-protein interactions (PPI) along with data from the Gene Expression Omnibus (GEO) led to the identification of 66 hub genes and 819 common differentially expressed genes (DEGs).\",\"target_result\":\"The study identified 66 hub genes.\",\"number_stated\":true}", "reading": {"parent_value": 66, "unit": "hub genes", "evidence": "The analysis of protein-protein interactions (PPI) along with data from the Gene Expression Omnibus (GEO) led to the identification of 66 hub genes and 819 common differentially expressed genes (DEGs).", "target_result": "The study identified 66 hub genes.", "number_stated": true, "source_locator": "chars 813-1014 of source sha256 aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26"}, "recorded_at": "2026-10-31T15:29:34.368822+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "19af1ba3dff2e26168812ef4565fc7a54f9a1c0d95598da97f8eecb9c92dde16", "source_hash": "aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26", "raw_response": "<think>We need answer JSON only. Need identify single numerical headline result main finding. Paper states identification 66 hub genes and 819 common DEGs; expression levels of 8 genes. Registered target \"headline numerical result paper states for its main finding\". Which number? Need infer perhaps 66 hub genes is headline main finding, or 8 genes? Abstract results: \"analysis ... led to identification of 66 hub genes and 819 common DEGs. ... expression levels of 8 genes ... notable difference...\" Main finding likely 8 hub genes? User asks single numerical result replication registered target has to reproduce, headline number only, value paper itself states for registered target. Target description vague \"headline numerical result the paper states for its main finding\". Need choose. Source has several headline numbers. They may expect 8, likely \"eight hub genes\" in conclusion. But \"value paper itself states\" and unit printed. Evidence exact quote containing number. Could be \"The expression levels of 8 genes—... demonstrated...\" Main finding likely number of hub genes? Let's parse.\n\nTitle identifying hub genes/pathways. Abstract: PPI + GEO led identification of 66 hub genes and 819 common DEGs. Then GEPIA confirms target genes, expression levels of 8 genes notable difference. Conclusion says following experimental confirmation, eight hub genes ... diagnose early. The \"headline numerical result\" might be 66 hub genes (main abstract result) and \"8 genes\" is validation-selected final set. Registered target likely benchmark question where target result is maybe number of hub genes identified. Need report headline number only unit. They emphasize unit printed, evidence attribution. We must select one.\n\nCould phrase target_result maybe \"8 hub genes\" with parent_value 8, unit \"genes\", evidence exact sentence. But registered target says \"the headline numerical result the paper states for its main finding\", likely asks find one numerical result. What is singular headline? Perhaps abstract's first result \"identification of 66 hub genes\" is headline numerical result. There is also 819 common DEGs. Yet \"single numerical result\" perhaps target registered manually to 8 genes. Need understand task design. They give \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\" generic semantic target, perhaps expected extraction of one headline number. Maybe likely 66 because main finding: 66 hub genes. But later says 8 hub genes final. Let's investigate cues.\n\nQuestion wording: \"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. ... 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.\"\n\nThis may be benchmark where registered target is a metric, and we must extract number. Here target is natural language \"the headline numerical result the paper states for its main finding.\" Could be designed to identify key reported count. \"headline number\" likely 66 (hub genes). Abstract starts results with \"led to identification of 66 hub genes and 819 common differentially expressed genes (DEGs).\" Is 66 the headline number, while 819 secondary. Main finding title \"Identifying Hub Genes\", perhaps 66 hub genes. Yet final conclusion narrows to eight. What does paper itself state for \"registered target\"? Maybe main finding is \"66 hub genes\". Need use exact evidence. Unit \"hub genes\" or \"genes\"? They say unit must unit paper prints. Number 66 followed \"hub genes\". Could unit be \"hub genes\". The question asks headline number only but JSON parent_value and unit. Evidence quote full clause. target_result perhaps concise \"66 hub genes\". number_stated true.\n\nLet's inspect abstract wording:\n\"The analysis ... led to the identification of 66 hub genes and 819 common differentially expressed genes (DEGs). GO ... The expression levels of 8 genes—... demonstrated a notable difference...\"\nCould replication of main finding reproduce both 66 and 819? Target singular headline numerical result maybe number of identified hub genes = 66. \"Main finding\" likely 66 hub genes, yes. The 8 genes are GEPIA notable difference, perhaps more headline in conclusion. Maybe title and conclusion indicate eight final candidates, but abstract says \"identification of 66 hub genes\". Let's search mentally whether this is an article perhaps known. Maybe paper \"Identifying Hub Genes and Pathways in Pancreatic Ductal Adenocarcinoma (PAAD): A comprehensive in silico study\" likely abstract. Main result: 66 hub genes and 819 common DEGs; 8 genes validated via GEPIA. If asked \"headline numerical result\" typically answer \"66 hub genes\". The benchmark may select a single target claim from source. The registered target phrasing may intentionally disambiguate to headline number rather than thresholds or dataset count. They may expect 66. Why call \"headline numerical result\" instead of specific \"number of hub genes\"? Maybe target description generated to avoid giving answer away. We should map to strongest headline claim. First results sentence is headline.\n\nCould be 8, because final conclusion says \"Following experimental confirmation, eight hub genes ... can be utilized to diagnose PAAD early.\" That's explicit final key outcome. But source spells numerical digit \"8\" in abstract and \"eight\" in conclusion. They ask \"value paper itself states\", likely parent_value can be 8 and unit \"genes\"; evidence needs exact contiguous quotation. Why mention \"value paper itself states\" perhaps conversion issue elsewhere. \"The unit must be the unit the paper prints.\" In this source, \"66 hub genes\" clear.\n\nNeed output valid JSON. Evidence exact quote. Could quote:\n\"The analysis of protein-protein interactions (PPI) along with data from the Gene Expression Omnibus (GEO) led to the identification of 66 hub genes and 819 common differentially expressed genes (DEGs).\"\nThis contains also 819, which conflicts \"single\" but attribution clear. They explicitly say quote whole clause if linked. Exact sentence. parent_value 66, unit \"hub genes\". target_result \"66 hub genes\". Is unit \"hub genes\" acceptable? Usually units should perhaps \"genes\". The unit as printed follows number \"hub genes\". Unit likely \"hub genes\". Could be \"genes\". Let's reason schema likely expects numeric result, unit. For counts, unit \"hub genes\". \"headline number only\" perhaps target_result \"66 hub genes\". If they expect 8, answer wrong.\n\nLet's investigate article's structure. It says \"identification of 66 hub genes and 819 common differentially expressed genes.\" Then in conclusion: \"Following experimental confirmation, eight hub genes, including ... can be utilized to diagnose PAAD early.\" Abstract does not explicitly call the eight \"hub genes\", just \"expression levels of 8 genes\". Main result is identification of 66 hub genes. Thus registered target main finding likely 66. Unit should be \"hub genes.\" Evidence exact contiguous quote from source. Include full sentence, no ellipsis. number_stated true.\n\nCould evidence quote only clause \"... led to the identification of 66 hub genes...\" Exact contiguous quotation. They say if text links them by words that name target directly, quote whole clause so reader checks attribution. Full sentence best. JSON escape em dash irrelevant.\n\ntarget_result maybe \"The paper reports 66 hub genes.\" But request headline number only perhaps target_result should simply \"66 hub genes\". We'll do.\n\nNeed ensure number type 66. JSON only no markdown.</think>\n\n{\"parent_value\":66,\"unit\":\"hub genes\",\"evidence\":\"The analysis of protein-protein interactions (PPI) along with data from the Gene Expression Omnibus (GEO) led to the identification of 66 hub genes and 819 common differentially expressed genes (DEGs).\",\"target_result\":\"66 hub genes\",\"number_stated\":true}", "reading": {"parent_value": 66, "unit": "hub genes", "evidence": "The analysis of protein-protein interactions (PPI) along with data from the Gene Expression Omnibus (GEO) led to the identification of 66 hub genes and 819 common differentially expressed genes (DEGs).", "target_result": "66 hub genes", "number_stated": true, "source_locator": "chars 813-1014 of source sha256 aa8995e5a5dbed151368635f693982755a60369aec18e0d940a59ed9a31bbd26"}, "recorded_at": "2026-10-31T15:29:53.515903+00:00"}], "agreement": false, "disagreements": {"analysis_methods": {"minimax": ["GEO2R differential expression analysis", "Protein-protein interaction analysis using Cytoscape and Gephi", "GO and KEGG enrichment analysis using DAVID", "GO annotation and KEGG pathway enrichment using Enrichr", "GEPIA single gene analysis", "GEPIA Analysis Box Plots module"], "minimax_alt": ["GEO2R differential expression analysis", "Protein-protein interaction (PPI) analysis using Cytoscape and Gephi", "Gene Ontology (GO) annotation and enrichment analysis using DAVID and Enrichr", "KEGG pathway enrichment analysis using DAVID and Enrichr", "GEPIA single gene analysis and Analysis Box Plots integrating TCGA normal samples with GTEx data"], "decisive": false}, "statistical_method": {"minimax": "GEO2R differential expression analysis using adjusted P-values below 0.05", "minimax_alt": "GEO2R differential expression analysis with DEGs defined by logFC >1 and ≤ −1 and adjusted p-value <0.05; Cytoscape and Gephi PPI analysis for hub-gene identification", "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:28c32fa1e4369d56ed6161e3934ae6c46387b912f0281ccb55eac28773ca2e6b", "type": "sep_package", "label": "SEP v1 package for pmid:39911529"}], "activities": [{"id": "activity:conversion:pmid:39911529", "type": "conversion", "used": ["package:28c32fa1e4369d56ed6161e3934ae6c46387b912f0281ccb55eac28773ca2e6b"], "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:39911529", "parent_hash": "sha256:2856ca6cae90889dabe1f198a5c6dea9aad1ea4295754d6bf2b7607323f9ebb2", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39911529 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:39911529' 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":"2026-11-04T00:42:31+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}}}