{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40933995", "kind": "science-record", "revision": 1, "content_hash": "sha256:168b4699664e9eb7d1c5cda24b606721bbd8d10fd68542643369fc13feb08aff", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T10:25:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Decoding the hypoxic tumor microenvironment in colorectal cancer for prognostic modeling and therapeutic target discovery.", "doi": "10.3389/fimmu.2025.1651749", "pmid": "40933995", "authors": null, "journal": "Frontiers in immunology", "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": 0.0026, "unit": "p-value", "tolerance": null, "source": "chars 1434-1624 of source sha256 f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47"}, "evidence": [{"asset": "source:pmid:40933995", "locator": "chars 1434-1624 of source sha256 f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47", "quote": "The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011)."}]}], "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:40933995"], "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:40933995", "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:40933995' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40933995", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2025.1651749", "sha256": "sha256:f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2025.1651749", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40933995 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:40933995"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40933995"]}, "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": "beca1b66e7e5e4da9dd332b429dfbd17c7f5dbee8980980193de963c5733068f", "source_hash": "f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47", "raw_response_sha256": "sha256:fcb6cb2b5545cf3918eb8570d5c13ac1080d02b1f3940248d7dee6876cfd71d8", "raw_response_chars": 5737}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "19ae96ff5138bf8a74582fa3da772a035ce5269df2841f0a9844f855d08eca0c", "source_hash": "f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47", "raw_response_sha256": "sha256:fd97aa90b772571dc19745bd3dcb0d89e42d0b9011ef96d8ec180e0255bb04f6", "raw_response_chars": 55279}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "4ffacddf6eac26453ecf69b2fdd21f95d7d11e76cb8fe770e61545dcd43be9f3", "source_hash": "f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47", "raw_response": "{\"parent_value\":0.0026,\"unit\":\"P-value\",\"evidence\":\"The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).\",\"target_result\":\"The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in the TCGA cohort (P = 0.0026).\",\"number_stated\":true}", "reading": {"parent_value": 0.0026, "unit": "P-value", "evidence": "The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).", "target_result": "The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in the TCGA cohort (P = 0.0026).", "number_stated": true, "source_locator": "chars 1434-1624 of source sha256 f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47"}, "recorded_at": "2026-10-31T15:35:51.875863+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "34ad6eb5fc86da88e0496199e8e2815613c0e64db43525996a21c619c1446234", "source_hash": "f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47", "raw_response": "<think>We need answer JSON object only. Need identify single numerical result registered target headline numerical result paper states for main finding. Source abstract/results: eight-gene prognostic model stratified ... OS in TCGA (P=0.0026) and validation (P=0.011). \"headline numerical result\" perhaps main finding numerical result? Registered target generic, likely expected perhaps P=0.0026? Need determine singular. They emphasize headline number only, value paper itself states for registered target. Target: \"the headline numerical result the paper states for its main finding\". Could be eight? Main finding maybe eight-gene prognostic model and significantly different OS with P values. Which single numerical result? \"headline number\" maybe P = 0.0026 in TCGA main cohort, primary registered target. Need quote whole clause linking target. Unit must printed: likely \"P = 0.0026\" perhaps unit \"P = 0.0026\"? They request parent_value number, unit string. Usually unit can be \"P-value\" perhaps printed unit is P? Let's parse task formulation. They want one numerical result replication of registered target reproduce. Registered target says headline numerical result paper states for its main finding. Maybe \"eight-gene prognostic model\" is numerical headline (8 genes), but result is main finding? Yet \"single numerical result\" perhaps number of genes in prognostic model, no unit. They ask headline number only, value paper itself states for registered target, not calculated. Evidence exact contiguous quote. Need infer likely intended extraction.\n\nPotential numerical outputs:\n- 15 CRC samples\n- eight hypoxic clusters\n- eight-gene prognostic model\n- P=0.0026 and P=0.011\n- top 1%\n- 30 μg etc.\n\n\"the headline numerical result the paper states for its main finding\" could refer to P=0.0026, likely headline significance in TCGA. The abstract states model stratified patients with significantly different OS in TCGA (P=0.0026) and validation cohorts (P=0.011). If target singular headline number, primary cohort result P=0.0026. But target wording may intentionally allow attached via parenthetical list. \"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.\" This generic instruction from benchmark asks extract a target and a number. Here target registered as semantic \"headline numerical result...\". We need identify what counts headline. The abstract's main finding perhaps prognostic model: \"eight-gene prognostic model ... significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).\" There are two P values. \"single numerical result\" likely primary TCGA P. Which is headline? Maybe \"P = 0.0026\" because main cohort and validation is secondary. Need output evidence exact clause. parent_value 0.0026, unit perhaps \"P-value\" or \"P = 0.0026\"? Unit must be unit paper prints. The paper prints P = 0.0026; there isn't conventional unit. Usually schema expected unit perhaps \"P-value\". They explicitly say unit must be unit paper prints. For p-values, likely \"P\" as unit. Could set unit: \"P-value\". But paper prints \"P = 0.0026\", not unit separately. Maybe unit should be \"P\". Need think benchmark conventions. They ask number with unit. Common outputs: value 0.0026, unit \"P-value\"; evidence quote. Could target_result perhaps \"P = 0.0026\" and unit \"P\". Yet target_result likely string describing extracted result. The schema includes target_result perhaps headline itself. We should say \"Overall survival difference in the TCGA cohort (P = 0.0026).\" number_stated true.\n\nCould headline number instead be 8 genes. Main finding: \"We present a robust hypoxia-related gene signature...\" The headline result in abstract: \"Single-cell profiling uncovered eight distinct hypoxic clusters...\" then \"The eight-gene prognostic model...\" \"headline numerical result the paper states for its main finding\" likely eight-gene signature. Replication target perhaps model consists of eight genes. But \"single numerical result\" and \"headline number\" often benchmark asks for a specific target like \"effect size\" or \"sample size\". Here target is vague. Let's inspect wording: REGISTERED TARGET: the headline numerical result the paper states for its main finding. They expect to find headline number. Could be \"eight-gene prognostic model\" because that's the headline numerical characteristic of main finding. Yet then there are P values as statistical result. Which is more headline? They may have constructed target intentionally to ask \"headline numerical result\" likely an effect metric from abstract, perhaps P=0.0026. Need analyze task genre. Maybe user asks extraction agent to identify \"parent_value\" corresponding to registered target, to use in replication workflows. \"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.\" Registered target often e.g., \"the AUC reported for [model]\". Here target: \"the headline numerical result the paper states for its main finding\". We need extract. \"headline number only\" perhaps means among multiple related values, select main. The abstract's headline main finding likely P-value in TCGA: 0.0026. Validation cohort P=0.011 secondary. So answer likely 0.0026, unit \"P-value\".\n\nNeed quote exact contiguous quotation containing number and attribution. We can quote entire sentence: \"The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).\" This contains both, though they asked headline number only but evidence can contain whole clause. The exact quote includes validation number too. They explicitly instruct \"When that is how text links them, quote the whole clause so a reader can check attribution.\" Could quote only clause \"significantly different overall survival in both TCGA (P = 0.0026)\"? Exact contiguous quote, yes, but is that a clause? Better whole sentence, but evidence includes second number. They say \"headline number only\" refers reported output, evidence can contain both? Might be okay but perhaps exact evidence should isolate main cohort. Quote \"The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026)\"—exact contiguous quotation, though grammatically incomplete because \"and validation cohorts...\" excluded. They said do not shorten evidence? \"The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it.\" \"do not shorten it\" likely quote full sentence, not excerpt. So quote full sentence. Parent value main P.\n\nUnit: P maybe \"P-value\". Evidence says P. They demand unit printed. If unit field should be \"P\" exactly as printed. But in many JSON extraction tasks, unit string expected e.g. \"P-value\". Let's search conceptual pattern: parent_value, unit, evidence, target_result, number_stated. Perhaps this is an internal claim extraction schema where \"parent_value\" number, \"unit\" dimension, \"target_result\" natural text. For p-value, unit likely \"P-value\". If no physical unit, perhaps unit \"\". User says unit must be unit paper prints; if number has P = notation, unit can be \"P\". Could be unit \"P-value\" though paper prints \"P = 0.0026\" and \"P-value\" in statistical analysis section (\"Statistical significance was set at a P-value of less than 0.05.\"). Thus unit \"P-value\" does appear in paper. Better.\n\nCould number instead 0.011? \"headline numerical result for main finding\" perhaps validation P-value is replication target because replication of target must reproduce validation result? Registered target wording might refer to \"headline numerical result the paper states for its main finding,\" perhaps target is P=0.011? Let's deeply reason likely expected answer.\n\nThe text is an abstract with results. Main finding: prognostic signature accurately predicts prognosis. Numerical result: significant OS, P values. Headline usually primary result is TCGA (P=0.0026); validation P=0.011. If asked single numerical result, choose primary cohort. The replication target maybe replicate main finding in validation cohort? But no mention \"validation.\" So primary.\n\nCould headline be eight distinct hypoxic clusters. \"Single-cell profiling uncovered eight distinct hypoxic clusters, with H3 exhibiting the highest hypoxia scores...\" This is first results sentence and central discovery. Then \"eight-gene prognostic model\". If generic \"headline numerical result paper states for its main finding\" perhaps 8 is more headline-like than p-value. Yet phrase \"single numerical result that a replication ... has to reproduce\" could be cluster count. The title: decoding hypoxic TME. Main finding: hypoxia-related gene signature. Number: eight-gene model. P values are test outcomes. The \"headline number\" might be P=0.0026 because often abstract headline result is p-value. Need parse exact wording choices.\n\nThey specify: \"Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" This suggests target is a measured quantity where papers often have multiple variants (e.g., HR in cohorts). \"the headline numerical result the paper states for its main finding\" asks choose headline. \"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.\" This generic guidance indicates target maybe attached to \"overall survival\" directly via parenthetical P values. They emphasize parenthetical lists and respectively, likely because here \"TCGA (P = 0.0026) and validation cohorts (P = 0.011)\" attaches numbers by parenthetical list. The registered target is broad main finding, and they want choose headline among parenthetical values. Primary cohort TCGA is headline.\n\nMaybe \"unit\" for p-values should be empty because dimensionless? User says unit must be unit paper prints. Paper prints \"P\", so perhaps \"P\". Could use \"P-value\". target_result should identify \"overall survival separation in TCGA\". number_stated true.\n\nLet's formulate JSON exactly, no markdown:\n{\n \"parent_value\": 0.0026,\n \"unit\": \"P-value\",\n \"evidence\": \"The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).\",\n \"target_result\": \"Overall survival difference between high- and low-risk groups in the TCGA cohort (P = 0.0026).\",\n \"number_stated\": true\n}\nWould target_result itself violate \"headline number only\"? No, likely expects description. Could say \"TCGA overall-survival significance for the eight-gene prognostic model.\" Unit perhaps \"P\". They request report headline number only perhaps target_result should just value? Schema demands string; perhaps target_result \"P = 0.0026\". Avoid extra number (e.g. eight) perhaps evidence has it anyway. \"headline number only\" means don't report validation P separately perhaps target_result can include only 0.0026. But evidence full sentence has 0.011 necessarily. Could quote exact contiguous excerpt that includes only target number but says do not shorten it. \"do not shorten it\" likely means no truncation of quote. Yet full sentence contains two numerical results, could create ambiguity. They instruct full clause for attribution, and full clause includes both P values. That's acceptable.\n\nWhat does \"parent_value\" perhaps mean unit for p-value? Could set unit \"P\". Maybe they want `unit: \"P\"` because exact printed unit. Let's look at common data extraction style. Parent value might refer to numeric parent in a hierarchy, e.g. \"mean 3.4 mg/L\". If dimensionless P, unit can be \"P-value\". A robust answer.\n\nNeed not mention 8 as parent. Evidence full sentence contains 8 though. Fine.\n\nCould quote the earlier abstract sentence exact:\n\"Single-cell profiling uncovered eight distinct hypoxic clusters, with H3 exhibiting the highest hypoxia scores and enrichment in glycoprotein metabolic and angiogenesis pathways. The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).\" But full paragraph? \"do not shorten it\" likely exact sentence enough.\n\nLet's ensure JSON escaping en dash etc valid Unicode. Use source punctuation. No extra prose.\n\nBefore final, let's investigate alternative 8. User says \"single numerical result that a replication of the registered target has to reproduce.\" Replication of main finding likely need reproduce P-value? A replication doesn't \"reproduce\" significance p exactly; it reproduces effect estimate more than p-value. But source only gives p-value, so numerical result to reproduce is P. They explicitly say if text states no number for target, false. Here likely main result number. They could target \"eight-gene prognostic model\" because replication must reproduce 8-gene signature. That is a concrete count. Which one is \"headline numerical result\"? Abstract says \"Single-cell profiling uncovered eight distinct hypoxic clusters...\" and \"The eight-gene prognostic model...\" There are headline counts of 8. Yet task singular perhaps one result. They may expect P=0.0026 as statistically headline.\n\nCould identify phrase \"headline number\" often in literature means primary endpoint value, not sample count. The main finding is survival stratification. Its headline statistical number is P = 0.0026. Validation P is corroborating. So yes.\n\nUnit: Could be \"P = 0.0026\" itself? Schema parent_value numeric and unit string. Maybe unit `\"P\"`; target_result `\"P = 0.0026\"`. If unit is \"P-value\", source section uses exact term \"P-value\" indeed. Paper prints it in statistical analysis but not attached to this result. User says unit must be unit the paper prints, not necessarily adjacent. P-value is dimensionless label. I'd use `\"P-value\"` conventional.\n\nNeed maybe `parent_value`: 0.0026 number. `target_result`: \"Overall survival stratification by the eight-gene prognostic model in TCGA.\" But includes \"eight\" another number not headline. Better \"Overall survival difference between the prognostic risk groups in the TCGA cohort (P = 0.0026).\" This contains number once. \"headline number only\" maybe don't describe \"difference\" inaccurately (p-value corresponds significance, not difference magnitude). Say \"Overall-survival significance for the prognostic risk groups in the TCGA cohort (P = 0.0026).\" Good.\n\nEvidence must exact contiguous quote. Full sentence exactly:\n\"The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).\"\nYes.\n\nShould we quote abstract/results duplicate? One occurrence enough. Exact.\n\nLet's answer JSON only.</think>\n\n{\"parent_value\":0.0026,\"unit\":\"P-value\",\"evidence\":\"The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).\",\"target_result\":\"Overall-survival significance for the prognostic risk groups in the TCGA cohort (P = 0.0026).\",\"number_stated\":true}", "reading": {"parent_value": 0.0026, "unit": "P-value", "evidence": "The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).", "target_result": "Overall-survival significance for the prognostic risk groups in the TCGA cohort (P = 0.0026).", "number_stated": true, "source_locator": "chars 1434-1624 of source sha256 f7098d6c3c23bafe508396432ebb067424840e43ddb21001810572ecda9b1f47"}, "recorded_at": "2026-10-31T15:36:15.858548+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in TCGA (P = 0.0026) and the validation cohort (P = 0.011).", "minimax_alt": "The eight-gene prognostic model stratified patients into high- and low-risk groups with significantly different overall survival in both TCGA (P = 0.0026) and validation cohorts (P = 0.011).", "decisive": false}, "physical_methods": {"minimax": ["In vitro GIPC2 knockdown assays in LS180 and HT-29 colorectal cancer cell lines", "Proliferation, migration, invasion, apoptosis, and EMT phenotype assays", "Western blot analysis"], "minimax_alt": ["In vitro assays in LS180 and HT-29 CRC cell lines", "GIPC2 knockdown", "Cell proliferation, migration, invasion, apoptosis, and EMT phenotype assessment", "Western blot analysis of cleaved caspase-3, Bcl-2, E-cadherin, and vimentin"], "decisive": false}, "analysis_methods": {"minimax": ["Single-cell RNA sequencing", "Weighted gene co-expression network analysis (WGCNA)", "Gene Ontology Biological Process and KEGG enrichment analysis", "CellChat cell-cell communication analysis", "SCENIC transcription-factor inference", "GRNBoost2 gene regulatory network reconstruction", "Univariate Cox regression", "Lasso regression", "Cox regression", "Kaplan-Meier survival analysis", "Pearson correlation", "Chi-squared test", "Wilcoxon rank-sum test", "T-test"], "minimax_alt": ["Single-cell RNA sequencing integration and clustering", "UMAP and t-SNE dimensionality reduction", "Weighted gene co-expression network analysis (WGCNA)", "Gene Ontology Biological Process (GOBP) and KEGG enrichment analysis using clusterProfiler", "CellChat cell-cell communication analysis", "SCENIC transcription-factor analysis", "GRNBoost2 gene regulatory network analysis", "Univariate Cox regression", "Lasso regression", "Cox regression models", "Kaplan-Meier survival curve analysis", "Pearson correlation coefficient", "Chi-squared test", "Wilcoxon rank-sum test", "T-test", "GDSCv2 drug sensitivity correlation analysis", "R 4.1.3"], "decisive": false}, "statistical_method": {"minimax": "Cox regression models and Kaplan-Meier survival curve analysis", "minimax_alt": "Cox regression models and Kaplan-Meier survival curve analysis using the survival package", "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:08287e9be44130a669062d30704824b518af4feca2c17f3f298109f91f5a002b", "type": "sep_package", "label": "SEP v1 package for pmid:40933995"}], "activities": [{"id": "activity:conversion:pmid:40933995", "type": "conversion", "used": ["package:08287e9be44130a669062d30704824b518af4feca2c17f3f298109f91f5a002b"], "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": "d3f14559-82fd-4407-8b75-dcc7b0a36757", "parent_hash": "08287e9be44130a669062d30704824b518af4feca2c17f3f298109f91f5a002b", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40933995 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:40933995' 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":"2026-11-04T00:30:00+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}}}