{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40890357", "kind": "science-record", "revision": 2, "content_hash": "sha256:59bcb92db2f65105a95b69a6550f2327faf6446a5ec880bba19820abe026fd88", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:47Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Construction of a prognostic risk model for acute myeloid leukemia based on exosomal genes and analysis of immune microenvironment characteristics.", "doi": "10.1038/s41598-025-17845-x", "pmid": "40890357", "authors": null, "journal": "Scientific reports", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "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:40890357"], "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:40890357", "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:40890357' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40890357", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-17845-x", "sha256": "sha256:6f9810fe91bf2a45614e234d57513e9050e672dc8eec96a2e1fd1a89e225877e", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-17845-x", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40890357:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2d90bf24bee87f9cc7f9ac9d3063b57978515eaed13d0b95555e5abb87b2a916", "bytes": 639, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#Tab1", "version": null, "note": "Exosome-related genes and their corresponding risk coefficients.", "structure": {"pmcid": "PMC12402452", "section_index": 19, "section_title": "Construction of an exosome-related prognostic signature", "row_count": 14, "column_count": 2}, "table": {"label": "Table 1", "caption": "Exosome-related genes and their corresponding risk coefficients.", "rows": [["Gene", "Coef"], ["EXOSC4", "0.489131757414089"], ["TMEM109", "0.122385896623323"], ["THBS1", "0.0315566929862512"], ["MYH9", "0.291033480323073"], ["HLA-DRA", "0.107916651629561"], ["CAPZB", "0.269733384075537"], ["ITGA4", "−0.164132610693896"], ["MYL6", "0.405708399356843"], ["CYB5R1", "0.150359117251523"], ["PSMA2", "−0.297116568474912"], ["MPO", "−0.244293996471651"], ["NDST2", "−0.658043797748103"], ["CANX", "−0.0644590533948854"]], "row_count": 14, "column_count": 2, "numeric_cells": 14, "header_rows": 1, "locator": "section[19]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:40890357:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:284ac18e9ffd7b58de240a79965de6b596b884d7347ba6712f1fdc471447f77b", "bytes": 619, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[27]/table-wrap[1]#Tab2", "version": null, "note": "Overview of protein pocket characteristics of verteporfin and ITGA4: Vina score, pocket volume and 3D coordinates, Docking region dimensions.", "structure": {"pmcid": "PMC12402452", "section_index": 27, "section_title": "Molecular docking", "row_count": 6, "column_count": 5}, "table": {"label": "Table 2", "caption": "Overview of protein pocket characteristics of verteporfin and ITGA4: Vina score, pocket volume and 3D coordinates, Docking region dimensions.", "rows": [["ID", "Vina 1 F score", "Cavity 1 F volume (ų)", "Center (x, y, z)", "Docking size (x, y, z)"], ["C1", "−16.0", "8161", "12,22,43", "35,35,25"], ["C2", "−13.8", "5702", "10,65,4", "35,32,25"], ["C4", "−11.4", "2924", "−34,41,48", "25,25,25"], ["C5", "−13.8", "1438", "8,45,26", "25,25,25"], ["C3", "−13.8", "3165", "−35,45,4", "25,25,25"]], "row_count": 6, "column_count": 5, "numeric_cells": 22, "header_rows": 1, "locator": "section[27]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:40890357:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3b9d24051fc8c80b40dbcee14c945ef9ac6e2ab0e789ee6422aca313fb32a0b4", "bytes": 613, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[27]/table-wrap[2]#Tab3", "version": null, "note": "Overview of protein pocket characteristics of Ebselen and MPO: Vina score, pocket volume and 3D coordinates, Docking region dimensions.", "structure": {"pmcid": "PMC12402452", "section_index": 27, "section_title": "Molecular docking", "row_count": 6, "column_count": 5}, "table": {"label": "Table 3", "caption": "Overview of protein pocket characteristics of Ebselen and MPO: Vina score, pocket volume and 3D coordinates, Docking region dimensions.", "rows": [["CurPocket ID", "Vina score", "Cavity volume (ų)", "Cavity center (x, y, z)", "Docking size (x, y, z)"], ["C2", "−7.6", "895", "−4,37,23", "19,19,19"], ["C1", "−7.2", "1170", "−30,11,18", "25,25,35"], ["C4", "−7.0", "746", "23,38,27", "19,19,19"], ["C5", "−6.3", "688", "42,11,24", "19,19,19"], ["C3", "−5.7", "832", "6,27,9", "19,27,19"]], "row_count": 6, "column_count": 5, "numeric_cells": 20, "header_rows": 1, "locator": "section[27]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:40890357:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f4684dd130912f1326ad03e55143d69028dc8fb48332fc13ed9ea38a9e4578ee", "bytes": 623, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[27]/table-wrap[3]#Tab4", "version": null, "note": "Overview of protein pocket characteristics of ginsenoside Rh1 and ITGA4: Vina score, pocket volume and 3D coordinates, Docking region dimensions.", "structure": {"pmcid": "PMC12402452", "section_index": 27, "section_title": "Molecular docking", "row_count": 6, "column_count": 5}, "table": {"label": "Table 4", "caption": "Overview of protein pocket characteristics of ginsenoside Rh1 and ITGA4: Vina score, pocket volume and 3D coordinates, Docking region dimensions.", "rows": [["CurPocket ID", "Vina score", "Cavity 1 volume (ų)", "Center (x, y, z)", "Docking size (x, y, z)"], ["C2", "−10.2", "5702", "10,65,4", "35,32,25"], ["C5", "−9.4", "1438", "8,45,26", "25,25,25"], ["C4", "−8.0", "2924", "−34,41,48", "25,25,25"], ["C3", "−7.8", "3165", "−35,45,4", "25,25,25"], ["C1", "−5.8", "8161", "12,22,43", "35,35,25"]], "row_count": 6, "column_count": 5, "numeric_cells": 21, "header_rows": 1, "locator": "section[27]/table-wrap[3]#Tab4"}}], "gaps": ["asset:source:pmid:40890357 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:40890357", "asset:table:pmid:40890357:1", "asset:table:pmid:40890357:2", "asset:table:pmid:40890357:3", "asset:table:pmid:40890357:4"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40890357"]}, "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": "58ee5d6ef5c259f3bc4cad5a02cdd9176e080ab5ef2ece6a36170d230f8518c6", "source_hash": "6f9810fe91bf2a45614e234d57513e9050e672dc8eec96a2e1fd1a89e225877e", "raw_response_sha256": "sha256:53c655a7316dc70e16f4271e9f7512554b36d0cdc1830602d91c4816a07a0db5", "raw_response_chars": 6350}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "3bfddd2f05cad42e0e19226b7934e5dfb030d0dbd67db0e3403f954715aca86d", "source_hash": "6f9810fe91bf2a45614e234d57513e9050e672dc8eec96a2e1fd1a89e225877e", "raw_response_sha256": "sha256:f29f5ea4c609d38c18eac4673883e4c5e0bf56018811f0530af191e6dc7e559f", "raw_response_chars": 40939}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "78a918ff7ecaa547efabb78f4745fc24867d03d532007134de210e43b17f809c", "source_hash": "6f9810fe91bf2a45614e234d57513e9050e672dc8eec96a2e1fd1a89e225877e", "raw_response": "{\"parent_value\":0.909,\"unit\":\"AUC\",\"evidence\":\"The model demonstrated superior predictive accuracy compared to traditional clinical parameters, with area under the curve (AUC) values of 0.819, 0.825, and 0.832 for 1-, 2-, and 3-year survival predictions in the training set, and 0.909 in the independent GEO validation cohort (GSE71014).\",\"target_result\":\"Independent GEO validation cohort area under the curve (AUC).\",\"number_stated\":true}", "reading": {"parent_value": 0.909, "unit": "AUC", "evidence": "The model demonstrated superior predictive accuracy compared to traditional clinical parameters, with area under the curve (AUC) values of 0.819, 0.825, and 0.832 for 1-, 2-, and 3-year survival predictions in the training set, and 0.909 in the independent GEO validation cohort (GSE71014).", "target_result": "Independent GEO validation cohort area under the curve (AUC).", "number_stated": true, "source_locator": "chars 885-1175 of source sha256 6f9810fe91bf2a45614e234d57513e9050e672dc8eec96a2e1fd1a89e225877e"}, "recorded_at": "2026-10-31T15:33:48.814683+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "ba42af34569b8ad189aee04838d00e4a01c6cd2179699cfed8ecf1b831b57c80", "source_hash": "6f9810fe91bf2a45614e234d57513e9050e672dc8eec96a2e1fd1a89e225877e", "raw_response": "<think>We need answer JSON only. Need interpret registered target: \"the headline numerical result the paper states for its main finding\" likely AUC? Source abstract says model predictive accuracy AUC values 0.819, 0.825, 0.832 for 1,2,3-year training, and 0.909 independent validation. They ask single numerical result replication registered target has to reproduce. Which is headline numerical result? Need infer perhaps main finding is 13-gene prognostic signature, number 13? Registered target phrased generic. Need identify single numerical result paper states for main finding. They likely want headline number perhaps \"13\" genes? Let's parse wording: \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". We need extract single numerical result. Main finding abstract: identified 13 genes and constructed prognostic risk model; model AUC values. Which is headline numerical result? Could be 13-gene exosome-based prognostic signature. The question says value paper itself states for registered target. \"the headline numerical result the paper states for its main finding\" perhaps target is target quantity unknown semantic. We need decide.\n\nSource conclusion: \"successfully constructed an AML risk scoring system incorporating 13 key genes...\" Main finding is model with 13 key genes. Abstract final: \"robust 13-gene exosome-based prognostic signature\". If replication has to reproduce headline numerical result, likely 13 genes. Unit perhaps \"genes\". Evidence exact contiguous quote clause: \"This study establishes a robust 13-gene exosome-based prognostic signature for AML risk stratification and identifies novel immunomodulatory mechanisms mediated by exosome-driven Treg polarization.\" Could parent_value 13, unit \"genes\" (paper prints \"13-gene\"; unit maybe genes). target_result \"The paper states that it established a robust 13-gene exosome-based prognostic signature for AML risk stratification.\" Need headline number only? They say report headline number only, but schema includes target_result. Could target_result concise.\n\nAlternatively AUC perhaps headline numerical result: \"0.909\" independent validation, as strongest headline metric. There are multiple AUCs though single target ambiguity. Registered target says main finding, perhaps model performance, likely AUC. They intentionally say \"single numerical result\". Main finding maybe \"the model demonstrated superior predictive accuracy...\" headline numerical result could be AUC. Which one? Need use contextual clues. \"a replication of the registered target has to reproduce\" Maybe this is from benchmark where target variable (\"parent_value\") perhaps target entity. They give vague registered target, and expect extract headline number. Often tasks ask \"What is the main numerical result reported in abstract?\" The answer likely one value such as AUC = 0.909. Need reason.\n\nThe source abstract has many numbers: cohorts n=151, n=337, 13 genes, AUC 0.819/0.825/0.832, 0.909 validation, HR 0.22, CI, docking score. \"headline numerical result ... main finding\" Main finding likely model predictive performance. The headline performance number is AUC 0.909 in independent validation. But independent validation AUC 0.909 without horizon? The sentence: \"with area under the curve (AUC) values of 0.819, 0.825, and 0.832 for 1-, 2-, and 3-year survival predictions in the training set, and 0.909 in the independent GEO validation cohort (GSE71014).\" This links 0.909 directly to validation cohort. If target registered as \"headline numerical result paper states for main finding\", perhaps 0.909 is likely.\n\nCould be 13 as headline because title/main contribution \"13-gene model\". The target definition uses singular \"headline numerical result the paper states for its main finding\", and asks headline number only. Often these prompts are generated to extract a specific \"parent_value\" from paper, where registered target may be described semantically by benchmark creator. They might intend \"number of genes in model\" as main finding. The phrase \"the paper itself states for the registered target\" generic boilerplate. We need infer target from source.\n\nLet's inspect exact wording. Title: \"Construction of a prognostic risk model for acute myeloid leukemia based on exosomal genes and analysis of immune microenvironment characteristics\". Abstract says \"we identified 13 ... and constructed a prognostic risk model.\" Main result is 13-gene signature. Headline number might be 13 genes. If asking AUC, they'd perhaps register \"the model's area under the curve in the independent validation cohort\". But they didn't. Registered target explicitly \"the headline numerical result the paper states for its main finding\" perhaps designed to let us identify central reported metric. Usually headline numerical result is 13? A paper title doesn't say 13. Conclusion does. Abstract’s first results: 13 genes. The model performance is 0.909.\n\nCould target_result need mention number and unit. \"headline number only\" perhaps no extra numerical values in evidence? But evidence exact quote may contain only target number. If 13, quote contains 13. If 0.909, quote clause contains other AUCs. They say \"When that is how the text links them, quote the whole clause so a reader can check the attribution\". Could quote whole clause with list. The request says \"find the single numerical result ... Report the headline number only ... evidence exact contiguous quotation ... contains the number; do not shorten it\". This suggests maybe target is part of a list, and evidence should preserve attribution. Could be 0.909 attached via \"and\". Or 13 attached to genes directly.\n\n\"single numerical result\" maybe asks replicate target, likely one number. If quoting AUC sentence, whole sentence includes many numbers but parent_value one. Fine.\n\nLet's search patterns mentally from similar benchmark prompts. They often say:\n\"Read 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. ... REGISTERED TARGET: [specific thing]\"\nHere registered target sometimes generic phrase. Need output exact source. This one perhaps target is \"the headline numerical result ... main finding\" and expected likely number of selected genes. The source has a target article whose central result is \"13-gene risk signature\". Replication would need reproduce 13 genes, whereas AUC is secondary validation metric. Yet \"headline numerical result\" perhaps central metric 0.909.\n\nCould be \"main finding\" = \"prognostic risk model based on exosomal genes\", and numerical result associated = \"13 genes\". The unit printed = \"genes\". The conclusion specifically: \"This study establishes a robust 13-gene exosome-based prognostic signature...\" That's very headline-like. The abstract's final conclusion same. The model performance values are several, not \"single\". Thus only unambiguous singular headline number tied to main contribution is 13. I'd lean 13.\n\nLet's ensure exact quote contiguous. Could use: \"This study establishes a robust 13-gene exosome-based prognostic signature for AML risk stratification and identifies novel immunomodulatory mechanisms mediated by exosome-driven Treg polarization.\" This is exact. Unit should paper prints: perhaps \"genes\" based on \"13-gene\". parent_value 13. target_result could be \"13 genes\" or \"The study established a 13-gene exosome-based prognostic signature for AML risk stratification.\" But \"Report headline number only\" maybe target_result should say \"13 genes\" only, though evidence also required. They likely expect target_result description. Schema demands string. Could set \"13 genes\". The evidence quote necessarily text. number_stated true.\n\nWould unit be \"genes\" or \"exosome-associated genes\"? The printed unit is \"13-gene\"; likely unit \"genes\". They say unit must be unit paper prints. Use \"genes\". Exact quote includes \"13-gene\". Good.\n\nNeed valid JSON no markdown. Ensure en dash etc okay. Let's answer.</think>\n\n{\"parent_value\":13,\"unit\":\"genes\",\"evidence\":\"This study establishes a robust 13-gene exosome-based prognostic signature for AML risk stratification and identifies novel immunomodulatory mechanisms mediated by exosome-driven Treg polarization.\",\"target_result\":\"13 genes\",\"number_stated\":true}", "reading": {"parent_value": 13, "unit": "genes", "evidence": "This study establishes a robust 13-gene exosome-based prognostic signature for AML risk stratification and identifies novel immunomodulatory mechanisms mediated by exosome-driven Treg polarization.", "target_result": "13 genes", "number_stated": true, "source_locator": "chars 1885-2082 of source sha256 6f9810fe91bf2a45614e234d57513e9050e672dc8eec96a2e1fd1a89e225877e"}, "recorded_at": "2026-10-31T15:33:59.773947+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The 13-gene exosome-based prognostic model achieved AUC values of 0.819, 0.825, and 0.832 for 1-, 2-, and 3-year survival predictions in the training set and 0.909 in the independent GEO validation cohort (GSE71014).", "minimax_alt": "The model demonstrated superior predictive accuracy compared to traditional clinical parameters, with area under the curve (AUC) values of 0.819, 0.825, and 0.832 for 1-, 2-, and 3-year survival predictions in the training set, and 0.909 in the independent GEO validation cohort (GSE71014).", "decisive": false}, "analysis_methods": {"minimax": ["univariate Cox regression", "least absolute shrinkage and selection operator (LASSO)", "receiver operating characteristic (ROC) curve analysis", "Kaplan-Meier analysis with log-rank test", "univariate and multivariate Cox regression analyses", "Wilcoxon rank-sum test", "Benjamini-Hochberg false discovery rate correction", "gene ontology (GO) enrichment analysis", "Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis", "CIBERSORTx immune-cell infiltration analysis", "STRING protein-protein interaction network analysis", "DSigDB drug enrichment analysis", "molecular docking"], "minimax_alt": ["univariate Cox regression", "multivariate Cox regression", "least absolute shrinkage and selection operator (LASSO)", "ROC curve analysis (AUC)", "Kaplan-Meier analysis with log-rank test", "Wilcoxon rank-sum test", "Benjamini-Hochberg false discovery rate correction", "CIBERSORTx", "GO and KEGG pathway enrichment analysis", "STRING protein-protein interaction network analysis", "DSigDB drug enrichment analysis", "molecular docking"], "decisive": false}, "statistical_method": {"minimax": "receiver operating characteristic (ROC) curve analysis", "minimax_alt": "ROC curve analysis (area under the curve [AUC])", "decisive": true}, "parent_value": {"minimax": 0.909, "minimax_alt": 13, "decisive": true}, "unit": {"minimax": "AUC", "minimax_alt": "genes", "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:f51938cef1f597e760353b1ce1b436ce58301b1c12b646eeaffeeee5f915f101", "type": "sep_package", "label": "SEP v1 package for pmid:40890357"}], "activities": [{"id": "activity:conversion:pmid:40890357", "type": "conversion", "used": ["package:f51938cef1f597e760353b1ce1b436ce58301b1c12b646eeaffeeee5f915f101"], "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:40890357", "parent_hash": "sha256:6668e7675fd035141ec29cfd5b4db0dbf010788fa96189563173d7e0a7249933", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40890357 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:40890357' 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":"2026-11-04T03:45:57+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}}}