{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39994841", "kind": "science-record", "revision": 2, "content_hash": "sha256:e41749dc47ea125882645bae0d660be885f233615198a5c24ea50df106fa220c", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:37Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "A Novel DNA Repair-Gene Model to Predict Responses to Immunotherapy and Prognosis in Patients With EGFR-Mutant Non-Small Cell Lung Cancer.", "doi": "10.1111/1759-7714.70025", "pmid": "39994841", "authors": null, "journal": "Thoracic cancer", "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:39994841"], "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:39994841", "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:39994841' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39994841", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1111/1759-7714.70025", "sha256": "sha256:e2b4f9bd96374dc8045e1d2eab60f82485061b9f81b16136fff98175ad2d5e4b", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1111/1759-7714.70025", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39994841:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:19d61f6a6b5393c968c74cd306589ca8fc4ca0f4bb4010e6960a39a7005b37b2", "bytes": 708, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#tca70025-tbl-0001", "version": null, "note": "The clinical information of 101 EGFRm NSCLC samples.", "structure": {"pmcid": "PMC11850292", "section_index": 17, "section_title": "Classification of Patients With EGFRm NSCLC Based on DDR Genes and Clinical Characteristics Between Subgroups", "row_count": 21, "column_count": 3}, "table": {"label": "TABLE 1", "caption": "The clinical information of 101 EGFRm NSCLC samples.", "rows": [["Characteristic", "", "N (%)"], ["Overall", "", "101 (100)"], ["Age, years", "63 ± 23", ""], ["Race", "Asian", "2 (1.98)"], ["Black", "18 (17.82)"], ["White", "80 (79.21)"], ["Sex", "Female", "52 (51.49)"], ["Male", "49 (48.51)"], ["M Stage", "M0", "68 (67.33)"], ["M1", "6 (5.94)"], ["MX", "25 (24.75)"], ["N Stage", "N0", "61 (60.40)"], ["N1", "19 (18.81)"], ["N2", "17 (16.83)"], ["N3", "1 (0.99)"], ["NX", "2 (1.98)"], ["T Stage", "T1", "31 (30.69)"], ["T2", "47 (46.53)"], ["T3", "16 (15.84)"], ["T4", "5 (4.95)"], ["TX", "2 (1.98)"]], "row_count": 21, "column_count": 3, "numeric_cells": 20, "header_rows": 1, "locator": "section[17]/table-wrap[1]#tca70025-tbl-0001"}}], "gaps": ["asset:source:pmid:39994841 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:39994841", "asset:table:pmid:39994841:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39994841"]}, "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": "07df9b04ca95e531dd95d1734d6d26aefbb2e8470dda57b82c3d6ba2157a18fa", "source_hash": "e2b4f9bd96374dc8045e1d2eab60f82485061b9f81b16136fff98175ad2d5e4b", "raw_response_sha256": "sha256:eb7144c56fc2fc2c757043ad2f122e5f248f6b096d52f34ee495e041dcf588bc", "raw_response_chars": 3947}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "1f582d2e51bc5cbf936d58a127568123a4606314a2d4d1e2869ad40a4be7f710", "source_hash": "e2b4f9bd96374dc8045e1d2eab60f82485061b9f81b16136fff98175ad2d5e4b", "raw_response_sha256": "sha256:24f5200bf2565882aa4a53fb204f181f4a160be935d3747788a47c3c1b5b3320", "raw_response_chars": 53144}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "9b1b0ff5ca14964a310526f45175a9bbe0726616f782bfd0d75d52d165fc5177", "source_hash": "e2b4f9bd96374dc8045e1d2eab60f82485061b9f81b16136fff98175ad2d5e4b", "raw_response": "{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The paper reports qualitative main findings: two EGFR-mutant NSCLC subtypes (DDR-activated and DDR-suppressed) and a four-gene prognostic model using CAPS, FAM83A, IGLV8-61, and SLC7A5; it does not state a headline numerical result for this finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The paper reports qualitative main findings: two EGFR-mutant NSCLC subtypes (DDR-activated and DDR-suppressed) and a four-gene prognostic model using CAPS, FAM83A, IGLV8-61, and SLC7A5; it does not state a headline numerical result for this finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:31:19.446142+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3ded89a3d3d806545e6ac277abe6e7bb8b1129fde468c89e4a7c51a7a788eb91", "source_hash": "e2b4f9bd96374dc8045e1d2eab60f82485061b9f81b16136fff98175ad2d5e4b", "raw_response": "<think>We need carefully parse request and source. Need return JSON object only. Need identify \"single numerical result that a replication of the registered target has to reproduce. Report headline number only: value paper itself states for registered target, not calculated/converted/averaged/reconstructed. Unit paper prints. Evidence exact contiguous quote contains number. Registered target: headline numerical result paper states for its main finding.\" Source perhaps no explicit headline numerical performance metric like AUC or HR. We need determine likely 101 samples? Need inspect. The source includes many numerical results: 101 samples, 84 DDR genes, two subtypes, four genes, p values, IC50 no value, etc. User wording hints target could be no number stated? Need analyze task interpretation. They ask find single numerical result replication registered target reproduce. Registered target generic \"headline numerical result the paper states for its main finding.\" The source abstract/conclusion lacks headline numerical metric, perhaps no number. Need decide which number expected. Need thoroughly consider source.\n\nPaper title: \"A Novel DNA Repair-Gene Model to Predict Responses to Immunotherapy and Prognosis in Patients With EGFR‐Mutant Non‐Small Cell Lung Cancer\". Source contains abstract style summary, methods/results, no actual model AUC numbers. \"This study included 101 EGFRm NSCLC samples from The Cancer Genome Atlas (TCGA) dataset and a GSE31210 dataset (external set)...\" \"A prognostic model ... constructed using four DDR genes: CAPS, FAM83A, IGLV8‐61, and SLC7A5.\" Results state risk score independent prognostic factor, survival etc without AUC value. \"We identified two subtypes...\" \"A total of 84 DDR genes...\" p values. A replication target registered as \"headline numerical result the paper states for its main finding\" probably generated generic task requiring finding headline number, perhaps an AUC from results unavailable? We must not invent. The source only numeric key finding could be 101 samples (sample size) not performance. They may expect \"no number stated\" because no headline numeric result. Need examine nuances in wording and likely benchmark task. We need extract claims only. They may have target metadata from e.g. replication targets tasks: target \"headline numerical result the paper states for its main finding\" and paper text with no headline numeric? Need evaluate.\n\nQuestion: \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\"\n\nThey emphasize no number branch. Is there headline numerical result? The paper states no AUC/HR/prognostic risk metric. Only counts, p values, and sample sizes. The main finding is model, risk score independent prognostic factor; there is no number attached to independent prognostic status. Could 101 be headline? It's cohort size, not \"main finding\". They specifically \"headline numerical result the paper states for its main finding\" — likely expected a performance metric (AUC), which missing. Need respond false, target_result describing model based on four genes and independent prognostic indicator with no numerical result. Need ensure target_result states what text does state instead. Can quote or paraphrase? Instruction evidence exact quote; target_result may describe. With no number, unit/evidence empty, parent 0, number_stated false. target_result \"The text states that a prognostic model for EGFRm NSCLC was constructed using four DDR genes—CAPS, FAM83A, IGLV8‐61, and SLC7A5—and that the derived risk score could serve as an independent prognostic indicator, but it gives no numerical result for the model’s main finding.\" Could include four? They said headline number only but branch false. Target_result can mention four? They ask \"say in target_result what text does state instead.\" Fine. Could avoid new numeric in target_result? Not required. Best \"The text states that a prognostic model based on DDR genes was constructed and that the derived risk score was an independent prognostic indicator, but it reports no numerical performance result for this main finding.\" Need perhaps mention four genes to precisely capture. The text's headline numerical result absent. This likely correct.\n\nBut need be sure there isn't some other numerical \"headline\" like 101 samples. Let's explore likely task provenance and how target selection works. These prompts often in benchmark involve registered target, like \"median overall survival of high-risk group\" and require number. Here target is abstract target perhaps \"the headline numerical result the paper states for its main finding\" rather than specific metric. Such generic target could be \"the study's sample size\" if source has number. Need reason from phrasing.\n\nUser explicitly target: \"the headline numerical result the paper states for its main finding\". They might expect us to find one number from full text (e.g., AUC value), but source appears trimmed to missing parts. Headline may be 101 samples. Would a replication of \"registered target\" be cohort count? Wording \"headline numerical result the paper states for its main finding\" not \"sample size.\" Need identify numerical result of main finding. Results often \"The AUC of the prognostic model was 0.804\" etc. That would be in Figure 6, but source doesn't include. Only claims no AUC. The right false branch likely designed to avoid hallucinating an AUC. We should not infer.\n\nWe need perhaps distinguish method numbers and outcome numbers. Numeric findings: 2 subtypes, 4 genes, 50 drugs, p=0.422, p<0.01 etc. Which is \"main finding\"? Risk model consists of four genes. Could a replication target be \"four DDR genes used in prognostic model\" with unit \"genes\"? That's a numerical result the paper states for its main finding. The headline numerical result might be 4 genes. But phrase \"value the paper itself states for the registered target\" if target generic then likely want model AUC. We must decide strongest.\n\nLet's reread entire source carefully for hidden value attached main finding. Abstract: \"This study included 101 EGFRm NSCLC samples ... A prognostic model ... using four DDR genes ... derived risk score could serve as an independent prognostic indicator.\" No numerical performance. Results: \"Based on the above analysis, it is evident that the model has the potential to predict survival prognoses.\" No number. \"furthermore, both univariate and multivariable Cox regression analysis demonstrated that the risk score was an independent prognostic factor for patients with EGFRm NSCLC (Figure 6E,F).\" No HR. Could number 101 be important replication target because data cohort? But they explicitly \"headline numerical result the paper states for its main finding\". Sample size not result. Four genes is construction, not numerical result performance. \"We identified two subtypes...\" maybe finding two subtypes. But that's count of subtypes, main finding, yet no obvious single number. Therefore false.\n\nNeed formulate JSON schema exact with parent_value 0, unit \"\", evidence \"\", target_result string, number_stated false. No prose outside. Could target_result explicitly note no numerical result but qualitative main finding: \"The text states that the derived DDR-gene risk score served as an independent prognostic indicator and could assist with immunotherapy response prediction and prognosis, but it does not state a headline numerical result for the main finding.\" This mentions not numbers. It reflects source. Use \"risk score\" etc. Is it okay \"independent prognostic indicator\" abstract wording \"could serve as an independent prognostic indicator\"; results \"demonstrated that risk score was an independent prognostic factor\". Good. Could mention no AUC/HR. \"The text reports that the DDR-based prognostic model’s risk score was an independent prognostic factor and that the model could assist with predicting immunotherapy response and assessing prognosis; it states no numerical performance result for this main finding.\" This is appropriate and avoids choosing count.\n\nWe should perhaps quote exact phrase in target_result but no requirement of exact except evidence. target_result \"The text states that the derived risk score could serve as an independent prognostic indicator and that the model could assist in identifying candidates for immunotherapy and assessing prognosis, but no numerical result is stated for the main finding.\" That is good.\n\nNeed ensure no unescaped special characters issue. JSON straightforward.\n\nBefore final perhaps we need not provide analysis; already long but final only JSON. They requested \"Reply with a JSON object.\" We must final only JSON. It will be okay per context?\n\nWe have lots of token budget but need no need to use. Yet maybe uncertainty warrants deeper analysis about target semantics and what answer expected. Let's consider alternative interpretation that target = 101 samples. If so false would be wrong. We need maximize correctness. Can infer likely benchmark design from prior tasks? I've seen tasks in this series: User \"REGISTERED TARGET: the overall survival in months reported for ...\", source excerpt. Required JSON. We need extract. Sometimes target phrase generic \"headline numerical result the paper states for its main finding\" might be designed as unknown target and source should have one clear primary number. Often supplied source for paper with abstract and results. Need select \"single numerical result\" among many. They might choose 101 samples as headline numeric? How would \"replication of registered target\" defined? Could be benchmark evaluating \"replication targets\" automatically from tables: primary target is e.g. \"the total number of samples included in the study\" but target text perhaps anonymized? This exact phrasing is unusual, might be a deliberately vague target to test no number. We can look at lexical cues: \"the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" \"If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead. Never invent a source.\" This explicitly anticipates target mismatch. Source seems to have numbers but no headline. They want no number false. Why would they give detailed instruction about \"respectively\" and parenthetical list? Generic prompt.\n\nRegistered target \"the headline numerical result the paper states for its main finding\" perhaps derived from a particular cell of \"replication target registry\" known as \"headline numerical result\". Is \"headline result\" a formal label e.g. \"primary result\" as the number in abstract. In this abstract no number. So false.\n\nCould paper's headline number be \"101\" because abstract starts with \"This study included 101 EGFRm NSCLC samples...\"? That is headline sample number but not \"main finding\" result. A replication of main model would reproduce model performance, not cohort count? It needs reproduce 101 because data cohort but not main numerical result. User says \"find the single numerical result that a replication of the registered target has to reproduce.\" They likely expect \"101 samples\" for study population? But target says \"the headline numerical result the paper states for its main finding\", so cohort count is study design not finding. Can't infer.\n\nMaybe \"four DDR genes\" is central main finding, and must replicate \"four\". It is explicitly numerical, and main finding. Yet \"headline numerical result\" could be 4. Would be \"The prognostic model was constructed using four DDR genes: CAPS, FAM83A, IGLV8‐61, and SLC7A5.\" Then parent_value 4, unit \"DDR genes\", evidence exact. But this is component count, not headline numerical effect size; article's headline result is model, not count. They likely want an effect size. In extraction tasks, \"target result\" often selected as \"what is the AUC of risk score in training cohort\" etc. If generic, maybe headline number refers to key numeric outcome stated in abstract. None present.\n\nLet's search mental content of actual paper. \"A Novel DNA Repair‐Gene Model to Predict Responses to Immunotherapy and Prognosis in Patients With EGFR‐Mutant Non‐Small Cell Lung Cancer\" probably J Cancer 2023 or 2024. They constructed 4 gene risk score. Could have AUCs 0.752, 0.746 etc. Source stops after Results and no figures. They deliberately withheld numeric figures maybe. If source had headline AUC from abstract, would include it. So no number false.\n\nWe should avoid explicitly mention \"no numerical performance result\" instead \"no numerical result for the main finding\" because p values in results might be considered numerical results but not main. Fine.\n\nFinal JSON:\n{\n\"parent_value\":0,\n\"unit\":\"\",\n\"evidence\":\"\",\n\"target_result\":\"The text states that a DDR-based prognostic model was constructed for EGFRm NSCLC and that its derived risk score could serve as an independent prognostic indicator, with potential to assist in identifying immunotherapy candidates and assessing prognosis, but it states no headline numerical result for this main finding.\",\n\"number_stated\":false\n}\n\nWould \"target_result\" better include no number and avoid asserting final independent? It's exact abstract. Good.\n\nWe should maybe mention four genes explicitly because target_result \"what the text does state instead\". Could: \"The text states that a prognostic model for EGFRm NSCLC was constructed using CAPS, FAM83A, IGLV8‐61, and SLC7A5 and that the derived risk score could serve as an independent prognostic indicator, but it gives no numerical performance result for the main finding.\" This omits \"four\" while conveying instead. That's fine. More precise and not weird. Use ASCII hyphen for EGFRm? JSON unicode allowed. Fine.\n\nLet's finalize.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"The text states that a prognostic model for EGFRm NSCLC was constructed using CAPS, FAM83A, IGLV8‐61, and SLC7A5 and that the derived risk score could serve as an independent prognostic indicator, but it states no headline numerical result for this main finding.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "The text states that a prognostic model for EGFRm NSCLC was constructed using CAPS, FAM83A, IGLV8‐61, and SLC7A5 and that the derived risk score could serve as an independent prognostic indicator, but it states no headline numerical result for this main finding.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:31:59.201330+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The study identified two molecular subtypes of EGFR-mutant NSCLC: DDR-activated and DDR-suppressed.", "minimax_alt": "A prognostic model for EGFRm NSCLC was constructed using four DDR genes: CAPS, FAM83A, IGLV8‐61, and SLC7A5.", "decisive": false}, "physical_methods": {"minimax": ["In vitro experiment"], "minimax_alt": ["In vitro experiment was performed to testify the role of DDR genes in EGFRm NSCLC."], "decisive": false}, "analysis_methods": {"minimax": ["Cluster analysis", "Partitioning Around Medoids (PAM) algorithm with the ConsensusClusterPlus package", "Gene Set Enrichment Analysis (GSEA)", "Univariate Cox regression analysis", "LASSO Cox regression analysis", "Time-dependent receiver operating characteristic (ROC) curve analysis", "Kaplan–Meier survival analysis", "Log-rank test", "Wilcoxon signed-rank test", "t-test", "Cibersortx immune-cell infiltration analysis", "Tumor Immune Dysfunction and Exclusion (TIDE) analysis", "pRRophetic drug-sensitivity prediction"], "minimax_alt": ["Partitioning Around Medoids (PAM) clustering with ConsensusClusterPlus", "Gene Set Enrichment Analysis (GSEA)", "Univariate Cox regression analysis", "Least absolute shrinkage and selection operator (LASSO) Cox regression analysis", "Time-dependent receiver operating characteristic (ROC) curve analysis", "Kaplan–Meier survival analysis with the log‐rank test", "t-test", "Wilcoxon signed‐rank test", "Univariate and multivariable Cox regression analysis", "CIBERSORTx immune-cell infiltration analysis", "TIDE analysis", "pRRophetic drug-sensitivity analysis using GDSC IC50 values"], "decisive": false}, "statistical_method": {"minimax": "Partitioning Around Medoids (PAM) algorithm with the ConsensusClusterPlus package", "minimax_alt": "least absolute shrinkage and selection operator (LASSO) Cox regression analysis", "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:fceba680d3fc7318700fbfad2337b875121c362547b7facf7b3ed84b556c3344", "type": "sep_package", "label": "SEP v1 package for pmid:39994841"}], "activities": [{"id": "activity:conversion:pmid:39994841", "type": "conversion", "used": ["package:fceba680d3fc7318700fbfad2337b875121c362547b7facf7b3ed84b556c3344"], "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:39994841", "parent_hash": "sha256:8ead378750b6bf59f5c99cb57c9d4b9f2522abc35cd4ec143b89a273c8191ff0", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39994841 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:39994841' 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":"2026-11-04T04:03:14+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}}}