{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40867600", "kind": "science-record", "revision": 2, "content_hash": "sha256:b7cfcec0b75719c8d2116eface453de99dfb6f23770e19f28b8a250cf2918578", "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": "A Brief Review of MicroRNA Profiling in Human Prostate Cancer Tissues and Plasma.", "doi": "10.3390/biom15081156", "pmid": "40867600", "authors": null, "journal": "Biomolecules", "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": 2.0, "unit": "mirnas", "tolerance": null, "source": "chars 1327-1484 of source sha256 91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc"}, "evidence": [{"asset": "source:pmid:40867600", "locator": "chars 1327-1484 of source sha256 91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc", "quote": "Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology."}]}], "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:40867600"], "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:40867600", "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:40867600' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40867600", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/biom15081156", "sha256": "sha256:91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/biom15081156", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40867600:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bfefd68514d625463780c898a34916bf47f8525b23a3f85fc1d731186e705cc6", "bytes": 1744, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#biomolecules-15-01156-t001", "version": null, "note": "miRNAs as predictive biomarkers in prostate cancer.", "structure": {"pmcid": "PMC12384506", "section_index": 7, "section_title": "3.1. miRNAs-Based Biomarkers", "row_count": 16, "column_count": 5}, "table": {"label": "Table 1", "caption": "miRNAs as predictive biomarkers in prostate cancer.", "rows": [["miRNA", "Expression in Prostate Cancer", "Location (Plasma/Tissue/Both)", "Predictive Role", "Authors"], ["miR-205", "Downregulated", "Tissue", "Tumor suppressor; predictive of cancer progression", "[13,14]"], ["miR-221", "Downregulated", "Tissue", "Predictive of tumor suppression and cancer progression", "[14,19]"], ["miR-222", "Downregulated", "Tissue", "Predictive of tumor suppression and cancer progression", "[14,19]"], ["miR-30c", "Downregulated", "Tissue", "Predictive of cancer cell proliferation and invasion", "[14,20]"], ["miR-1225-5p", "Upregulated", "Tissue", "Predictive of tumor promotion", "[14]"], ["miR-663a", "Upregulated", "Tissue", "Predictive of tumor promotion", "[14]"], ["miR-335-5p", "Downregulated", "Tissue", "Predictive of apoptosis induction in prostate cancer", "[21]"], ["miR-21", "Upregulated", "Tissue", "Predictive of aggressive prostate cancer", "[15,22]"], ["miR-125b", "Upregulated", "Tissue", "Predictive of aggressive prostate cancer", "[23]"], ["miR-182-5p", "Upregulated", "Tissue", "Predictive tumor growth and differentiation", "[24,25]"], ["miR-183-5p", "Upregulated", "Tissue", "Predictive of tumor invasion and metastasis", "[25]"], ["miR-96-5p", "Upregulated", "Tissue", "Predictive of metastatic potential", "[25,26]"], ["miR-449b", "Upregulated", "Tissue", "Predictive of biochemical recurrence after radical prostatectomy", "[27]"], ["miR-223-5p", "Downregulated", "Tissue", "Predictive of tumor suppression via ERG inhibition", "[28]"], ["miR-455-3p", "Downregulated", "Tissue", "Predictive of tumor suppression via eIF4E inhibition", "[29]"]], "row_count": 16, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[7]/table-wrap[1]#biomolecules-15-01156-t001"}}, {"id": "asset:table:pmid:40867600:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9a3d9691db784eeb173f61c68b9fc60c78e7a0a153889514ec34f318fdfcaecc", "bytes": 2034, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#biomolecules-15-01156-t002", "version": null, "note": "miRNAs as therapeutic targets in prostate cancer.", "structure": {"pmcid": "PMC12384506", "section_index": 8, "section_title": "3.2. miRNAs in Locally Advanced Prostate Cancer", "row_count": 16, "column_count": 5}, "table": {"label": "Table 2", "caption": "miRNAs as therapeutic targets in prostate cancer.", "rows": [["miRNA", "Expression in Prostate Cancer", "Location (Plasma/Tissue/Both)", "Therapeutic Role", "Authors"], ["miR-205", "Downregulated", "Tissue", "Tumor suppressor; potential therapeutic target for restoring tumor suppression", "[15,32]"], ["miR-221", "Downregulated", "Tissue", "Therapeutic target for inhibiting tumor progression", "[14,19]"], ["miR-222", "Downregulated", "Tissue", "Therapeutic target for inhibiting tumor progression", "[14,19]"], ["miR-30c", "Downregulated", "Tissue", "Therapeutic target for reducing cancer cell proliferation and invasion", "[14,20]"], ["miR-1225-5p", "Upregulated", "Tissue", "Therapeutic target for inhibiting tumor promotion", "[14]"], ["miR-663a", "Upregulated", "Tissue", "Therapeutic target for inhibiting tumor promotion", "[14]"], ["miR-21", "Upregulated", "Tissue", "Therapeutic target for reducing tumor growth and PTEN knockdown", "[22,49]"], ["miR-200 family", "Downregulated", "Tissue", "Therapeutic target for regulating cancer cell migration and tumor suppression", "[33]"], ["miR-23b", "Downregulated", "Tissue", "Therapeutic target for inhibiting tumor proliferation, migration, and metastasis", "[40,42]"], ["miR-449a/b", "Downregulated", "Tissue", "Therapeutic target for inducing cell cycle arrest and apoptosis", "[47,48]"], ["miR-582-5p", "Downregulated", "Tissue", "Therapeutic target for inhibiting TGF-β signaling and metastasis", "[35,37]"], ["miR-548c-3p", "Downregulated", "Tissue", "Therapeutic target for regulating ErbB and Hippo signaling pathways", "[38]"], ["miR-455-3p", "Downregulated", "Tissue", "Therapeutic target for inhibiting eIF4E and tumor growth", "[29]"], ["miR-223-5p", "Downregulated", "Tissue", "Therapeutic target for inhibiting ERG and tumor progression", "[28]"], ["miR-34a/c", "Downregulated", "Tissue", "Therapeutic target for reducing androgen receptor levels and tumor aggression", "[50,51]"]], "row_count": 16, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[8]/table-wrap[1]#biomolecules-15-01156-t002"}}], "gaps": ["asset:source:pmid:40867600 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:40867600", "asset:table:pmid:40867600:1", "asset:table:pmid:40867600:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40867600"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "b6d013bc87c67433625d33d3c446623a24e297a917b55509f3633754c8c0ff1b", "source_hash": "91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc", "raw_response_sha256": "sha256:dd0ef93ca22ffd7c26490a13e12b14d8c4cf4233bf04bee8abcbf9624cc5b026", "raw_response_chars": 64514}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "6db7e406284d8adbf79cd76e4bebb67a8d04f7647bcd446697afa2af428ac010", "source_hash": "91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc", "raw_response": "{\"parent_value\":2,\"unit\":\"miRNAs\",\"evidence\":\"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.\",\"target_result\":\"The headline main finding is that two miRNAs, miR-449b and miR-455-3p, were common to the prostate cancer tissue and plasma signatures.\",\"number_stated\":true}", "reading": {"parent_value": 2, "unit": "miRNAs", "evidence": "Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.", "target_result": "The headline main finding is that two miRNAs, miR-449b and miR-455-3p, were common to the prostate cancer tissue and plasma signatures.", "number_stated": true, "source_locator": "chars 1327-1484 of source sha256 91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc"}, "recorded_at": "2026-10-31T15:32:44.244341+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "c65627649851558dc0238d4141035e686d3bf3f0e85eb617c5aa2ce3aeb6862a", "source_hash": "91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper main finding. Source paper appears review/reanalysis, main finding two miRNAs common. But asks numerical result that replication has reproduce, headline number, value paper states for registered target. Registered target generic \"headline numerical result paper states for main finding\". Need infer likely number = two miRNAs? Unit maybe \"miRNAs\" and evidence exact contiguous quote. There are numerical results: 219 and 326 tissue, 12 plasma, two common. Main finding headline: \"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments...\" Headline numerical result likely 2 miRNAs. Need unit as paper prints. Could unit \"miRNAs\". Evidence exact quote contains number. Maybe \"Two miRNAs...\" spelled word not numeral; parent_value numeric 2. They demand evidence contains number perhaps word counts? Exact quote. \"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.\" Number is textual word \"Two\". Unit printed \"miRNAs\". Could answer 2, unit \"miRNAs\", evidence exact clause. target_result likely \"Two miRNAs (miR-449b and miR-455-3p) were common in tissue and plasma.\" Need JSON valid.\n\nBut let's inspect wording: \"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.\" They may expect a number likely count from abstract. Registered target itself says headline numerical result main finding. The main finding is intersection of tissue/plasma miRNA signatures: 2 common miRNAs. They want \"headline number only\", so parent_value 2. Unit as printed likely \"miRNAs\". Evidence must exact contiguous quote, not shorten. They emphasize \"a number may be attached to target by parenthetical list, respectively, or words name target directly. When that is how text links them, quote whole clause\". We need quote full exact sentence perhaps. Evidence can be exact sentence. \"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.\" This contains \"Two\". Does \"number\" mean numeral? likely okay. Unit \"miRNAs\". target_result perhaps \"Two miRNAs, miR-449b and miR-455-3p, were common in both tissue and plasma.\" Need only headline number perhaps target_result should state result but not extra numerical. Could say \"miR-449b and miR-455-3p were common to tissue and plasma.\" The target result is 2. Ensure unit \"miRNAs\" exactly printed.\n\nBut let's entertain whether headline numerical result could be 24 inclusion criteria, 318 screened, etc. Main finding from abstract is \"Two miRNAs ... common in both compartments.\" Replication of registered target (headline numerical result) perhaps generated by benchmark where target is \"number of shared miRNAs\" and asks exact value. Yes.\n\nNeed output strict JSON no markdown. Evidence exact contiguous quote. Could quote whole sentence, including (3) Results? Exact source has \"(3) Results: Of ... Two...\" If we quote just sentence, contiguous and exact. It starts \"Two...\" and is exact. They say do not shorten it likely means don't alter quote, not necessarily include entire surrounding paragraph. Fine.\n\nUnit maybe \"miRNAs\". Parent_value 2. target_result perhaps \"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments.\" That's effectively evidence duplicate. Should mention compartments tissue and circulation? To avoid calculated interpretation, use exact wording maybe target_result same result. JSON.</think>\n\n{\"parent_value\":2,\"unit\":\"miRNAs\",\"evidence\":\"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.\",\"target_result\":\"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments.\",\"number_stated\":true}", "reading": {"parent_value": 2, "unit": "miRNAs", "evidence": "Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.", "target_result": "Two miRNAs—miR-449b and miR-455-3p—were common in both compartments.", "number_stated": true, "source_locator": "chars 1327-1484 of source sha256 91c103d03885e362b9d030aade1adceb797292501def031e09329d5815c8b0dc"}, "recorded_at": "2026-10-31T15:32:53.036803+00:00"}], "agreement": false, "disagreements": [], "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": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "reason": "a quoted statement is absent from the supplied text", "raw_response": "{\n  \"target_result\": \"In the GEO reanalysis, 219 miRNAs were differentially expressed in GSE54516 tissue, 326 in GSE21032 tissue, and 12 in GSE206793 plasma; miR-449b and miR-455-3p were common to both tissue and plasma.\",\n  \"work_type\": \"analysis_only_for_target\",\n  \"physical_methods\": [],\n  \"analysis_methods\": [\n    \"Re-analysis of three Gene Expression Omnibus datasets\",\n    \"Quality, completeness, and normalization-parameter review\",\n    \"Differential expression testing using Transcriptome Analysis Console (TAC) software\",\n    \"False-discovery-rate and absolute log2 fold-change thresholding\",\n    \"Intersection of tissue and plasma differentially expressed miRNA sets\"\n  ],\n  \"statistical_method\": \"Differential expression testing was performed with Transcriptome Analysis Console (TAC) software, applying p < 0.05 and a false discovery rate (FDR) < 0.05; the reported differentially expressed sets used FDR < 0.05 and |log2FC| ≥ 1.\",\n  \"method_evidence\": \"Differential expression testing was performed with Transcriptome Analysis Console (TAC) software, applying p < 0.05 and a false discovery rate (FDR) < 0.05. The only comparison that yielded a statistically significant set of differentially expressed miRNAs (FDR < 0.05, |log2FC| ≥ 1) was between healthy controls (n = 5) and the high-risk prostate cancer group (n = 91).\",\n  \"repositories\": [\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE54516\",\n      \"data_description\": \"A publicly available prostate-cancer tissue miRNA dataset containing 219 miRNAs and 99 patients.\",\n      \"evidence\": \"In this study, three publicly available prostate cancer (PC) miRNA datasets from the Gene Expression Omnibus (GEO) were selected to identify and compare differentially expressed miRNAs in both tissue and plasma. GSE54516 (GEO set 1, 219 miRNAs, 99 patients) [77] and GSE21032 (GEO set 2, 326 miRNAs, 127 patients) [78] focused on PC tissue, whereas GSE206793 (GEO set 3, 12 miRNAs, 96 patients) [79] examined miRNAs from plasma samples.\",\n      \"publicly_downloadable\": true\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE21032\",\n      \"data_description\": \"A publicly available prostate-cancer tissue miRNA dataset containing 326 miRNAs and 127 patients.\",\n      \"evidence\": \"In this study, three publicly available prostate cancer (PC) miRNA datasets from the Gene Expression Omnibus (GEO) were selected to identify and compare differentially expressed miRNAs in both tissue and plasma. GSE54516 (GEO set 1, 219 miRNAs, 99 patients) [77] and GSE21032 (GEO set 2, 326 miRNAs, 127 patients) [78] focused on PC tissue, whereas GSE206793 (GEO set 3, 12 miRNAs, 96 patients) [79] examined miRNAs from plasma samples.\",\n      \"publicly_downloadable\": true\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE206793\",\n      \"data_description\": \"A publicly available prostate-cancer plasma miRNA dataset containing 12 miRNAs and 96 patients.\",\n      \"evidence\": \"In this study, three publicly available prostate cancer (PC) miRNA datasets from the Gene Expression Omnibus (GEO) were selected to identify and compare differentially expressed miRNAs in both tissue and plasma. GSE54516 (GEO set 1, 219 miRNAs, 99 patients) [77] and GSE21032 (GEO set 2, 326 miRNAs, 127 patients) [78] focused on PC tissue, whereas GSE206793 (GEO set 3, 12 miRNAs, 96 patients) [79] examined miRNAs from plasma samples.\",\n      \"publicly_downloadable\": true\n    }\n  ],\n  \"availability_statement\": \"All data are presented in the manuscript.\",\n  \"data_on_request\": false,\n  \"source_claims\": [\n    \"From the GEO reanalysis (false-discovery-rate < 0.05, |log2FC| ≥ 1), 219 and 326 miRNAs were differentially expressed in tissue, whereas 12 were altered in plasma.\",\n    \"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.\",\n    \"The only comparison that yielded a statistically significant set of differentially expressed miRNAs (FDR < 0.05, |log2FC| ≥ 1) was between healthy controls (n = 5) and the high-risk prostate cancer group (n = 91).\",\n    \"As shown in Figure 1, miR-449b and miR-455-3p, discussed below, were identified in both tissue and plasma signatures, suggesting they may serve as circulating biomarkers for prostate cancer.\",\n    \"Integrative tissue-and-plasma analysis identifies miR-449b and miR-455-3p as robust, concordant biomarkers with plausible functional relevance.\"\n  ],\n  \"missing_information\": [],\n  \"evidence_spans\": [\n    \"From the GEO reanalysis (false-discovery-rate < 0.05, |log2FC| ≥ 1), 219 and 326 miRNAs were differentially expressed in tissue, whereas 12 were altered in plasma.\",\n    \"Two miRNAs—miR-449b and miR-455-3p—were common in both compartments, highlighting their translational potential as liquid biopsy surrogates of tumor biology.\",\n    \"Differential expression testing was performed with Transcriptome Analysis Console (TAC) software, applying p < 0.05 and a false discovery rate (FDR) < 0.05.\",\n    \"The only comparison that yielded a statistically significant set of differentially expressed miRNAs (FDR < 0.05, |log2FC| ≥ 1) was between healthy controls (n = 5) and the high-risk prostate cancer group (n = 91).\",\n    \"In this study, three publicly available prostate cancer (PC) miRNA datasets from the Gene Expression Omnibus (GEO) were selected to identify and compare differentially expressed miRNAs in both tissue and plasma.\",\n    \"GSE54516 (GEO set 1, 219 miRNAs, 99 patients) [77] and GSE21032 (GEO set 2, 326 miRNAs, 127 patients) [78] focused on PC tissue, whereas GSE206793 (GEO set 3, 12 miRNAs, 96 patients) [79] examined miRNAs from plasma samples.\",\n    \"All data are presented in the manuscript.\"\n  ]\n}"}]}}, {"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:acbb0831bc0c3080816b350a7b5d26a1425de1ac95b84fed7be7b8eff581c5a6", "type": "sep_package", "label": "SEP v1 package for pmid:40867600"}], "activities": [{"id": "activity:conversion:pmid:40867600", "type": "conversion", "used": ["package:acbb0831bc0c3080816b350a7b5d26a1425de1ac95b84fed7be7b8eff581c5a6"], "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:40867600", "parent_hash": "sha256:5f33622b157038bad5906a33468344984ad7389c3079f3219f698112003bf20b", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40867600 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:40867600' 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":"2026-11-04T02:36:33+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}}}