{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40703522", "kind": "science-record", "revision": 2, "content_hash": "sha256:16ff50f756d5758146326e794bb3e28d16fb308dba30a3c982f9a6eda8541321", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T14:01:44Z", "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 mast cell marker gene-related prognostic signature to predict prognosis and reveal the immune landscape in head and neck squamous cell carcinoma.", "doi": "10.3389/fimmu.2025.1538641", "pmid": "40703522", "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": 14.0, "unit": "mrgs", "tolerance": null, "source": "chars 1289-1495 of source sha256 f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d"}, "evidence": [{"asset": "source:pmid:40703522", "locator": "chars 1289-1495 of source sha256 f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d", "quote": "The 14-MRGs prognostic signature classified patients into high- and low-risk groups, and the overall survival (OS) of the low-risk group was significantly higher than that of the high-risk group (p < 0.05)."}]}], "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:40703522"], "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:40703522", "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:40703522' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40703522", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2025.1538641", "sha256": "sha256:f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2025.1538641", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40703522:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c52366537159dfe0e2f24d19fdedb195839d01b4bb2efb847bde030820aae113", "bytes": 1464, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T1", "version": null, "note": "Clinicopathologic information and subgroups of HNSCC patients.", "structure": {"pmcid": "PMC12283675", "section_index": 12, "section_title": "14-MRGs prognostic signature construction and validation", "row_count": 26, "column_count": 8}, "table": {"label": "Table 1", "caption": "Clinicopathologic information and subgroups of HNSCC patients.", "rows": [["Patient characteristics", "Training group", "Validation group", "Entire cohort", "P value"], ["n=322", "%", "n=194", "%", "n=516", "%"], ["Age", "", "", "", "", "", "", "0.113"], ["≤74", "287", "89.13", "159", "81.96", "446", "86.43", ""], [">74", "35", "10.87", "35", "18.04", "70", "13.57", ""], ["Gender", "", "", "", "", "", "", "0.960"], ["Female", "84", "26.08", "51", "26.29", "135", "26.16", ""], ["Male", "238", "73.92", "143", "73.71", "381", "73.84", ""], ["Stage", "", "", "", "", "", "", "0.110"], ["I", "16", "4.97", "11", "5.67", "27", "5.23", ""], ["II", "47", "14.60", "35", "18.04", "82", "15.89", ""], ["III", "53", "16.46", "40", "20.62", "93", "18.02", ""], ["IV", "206", "63.97", "108", "55.67", "314", "60.86", ""], ["T", "", "", "", "", "", "", "0.390"], ["T1", "31", "9.63", "20", "10.31", "51", "9.88", ""], ["T2", "95", "29.50", "61", "31.44", "156", "30.23", ""], ["T3", "73", "22.67", "48", "24.74", "121", "23.45", ""], ["T4", "123", "38.20", "65", "33.51", "188", "36.44", ""], ["N", "", "", "", "", "", "", "0.513"], ["N0", "135", "41.93", "86", "44.33", "221", "42.83", ""], ["N1", "49", "15.22", "31", "15.98", "80", "15.50", ""], ["N2", "131", "40.68", "73", "37.63", "204", "39.54", ""], ["N3", "7", "2.17", "4", "2.06", "11", "2.13", ""], ["Vital status", "", "", "", "", "", "", "0.896"], ["Alive", "184", "47.14", "112", "57.73", "296", "57.36", ""], ["Dead", "138", "42.86", "82", "42.27", "220", "42.64", ""]], "row_count": 26, "column_count": 8, "numeric_cells": 119, "header_rows": 2, "locator": "section[12]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:40703522:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5636d70cb7c51ad7f467eb3654e5eeb9e0971545b5b326a7e53193493731158d", "bytes": 930, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T2", "version": null, "note": "Fourteen MRGs associated with prognosis in HNSCC patients.", "structure": {"pmcid": "PMC12283675", "section_index": 12, "section_title": "14-MRGs prognostic signature construction and validation", "row_count": 15, "column_count": 4}, "table": {"label": "Table 2", "caption": "Fourteen MRGs associated with prognosis in HNSCC patients.", "rows": [["Gene", "Coefficient", "HR(95%CI)", "P value"], ["AREG", "0.405", "1.499 (1.004-2.240)", "0.048"], ["CD82", "0.733", "2.081 (1.410-3.070)", "0.000"], ["DAPK1", "0.885", "2.422 (1.387-4.230)", "0.002"], ["FDX1", "0.596", "1.815 (1.199-2.748)", "0.005"], ["GLUL", "0.853", "2.347 (1.405-3.918)", "0.001"], ["HS3ST1", "0.561", "1.752 (1.008-3.046)", "0.047"], ["LAT", "-0.749", "0.473 (0.275-0.813)", "0.007"], ["LIF", "0.893", "2.443 (1.574-3.792)", "0.000"], ["PTPN7", "-0.489", "0.613 (0.415-0.908)", "0.014"], ["RASGEF1B", "-0.542", "0.582 (0.389-0.871)", "0.008"], ["SLC18A2", "-0.620", "0.538 (0.339-0.854)", "0.009"], ["TBC1D14", "-0.731", "0.481 (0.325-0.713)", "0.000"], ["TMOD1", "0.550", "1.733 (1.144-2.623)", "0.009"], ["TPSD1", "-0.540", "0.583 (0.396-0.857)", "0.006"]], "row_count": 15, "column_count": 4, "numeric_cells": 46, "header_rows": 1, "locator": "section[12]/table-wrap[2]#T2"}}], "gaps": ["asset:source:pmid:40703522 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:40703522", "asset:table:pmid:40703522:1", "asset:table:pmid:40703522:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40703522"]}, "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": "405a5cd60ab6531b709bd23cec87d41921b2d171636b5eab2e30a2b47e1ed23b", "source_hash": "f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d", "raw_response_sha256": "sha256:df2ad3ec0af0584be6e04261f2761f7d491b9168e2baeac831b1579636e45e0c", "raw_response_chars": 3889}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "c81b0e3b6c05c9138e6500d1d029ae16693892a7571022b8ed609391b706d937", "source_hash": "f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d", "raw_response_sha256": "sha256:47707d99160e1a827656a0b88a1f185b0ecfc209359ec0ba7775b5aa5b8b51b2", "raw_response_chars": 60796}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "95d5b6fe906d5cbcfc8fc5b01b2525b6695164f1696648afa9c338a925851a4a", "source_hash": "f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d", "raw_response": "{\"parent_value\":14,\"unit\":\"MRGs\",\"evidence\":\"The 14-MRGs prognostic signature classified patients into high- and low-risk groups, and the overall survival (OS) of the low-risk group was significantly higher than that of the high-risk group (p < 0.05).\",\"target_result\":\"The paper’s main finding is a prognostic signature based on 14 mast cell marker genes.\",\"number_stated\":true}", "reading": {"parent_value": 14, "unit": "MRGs", "evidence": "The 14-MRGs prognostic signature classified patients into high- and low-risk groups, and the overall survival (OS) of the low-risk group was significantly higher than that of the high-risk group (p < 0.05).", "target_result": "The paper’s main finding is a prognostic signature based on 14 mast cell marker genes.", "number_stated": true, "source_locator": "chars 1289-1495 of source sha256 f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d"}, "recorded_at": "2026-10-31T15:22:12.727017+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "711dc979a13da0a3dc43a93bf599d6029a3cc301442eb025e564db401e40351c", "source_hash": "f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d", "raw_response": "<think>We need carefully identify single numerical result headline main finding registered target. Need JSON only. We must reason ambiguities. Source title novel mast cell marker gene-related prognostic signature ... abstract: 14-MRGs prognostic signature. Main finding likely 14-MRGs prognostic signature. User asks \"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 unit paper prints. Evidence exact contiguous quote contains number. Attribution may parenthetical list respectively words naming target directly. When how text links quote whole clause. If no number registered target false...\" We need decide headline numerical result main finding likely 14? Or areas under ROC 0.740 0.737 0.707? We need parse wording. \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\" Perhaps task built to identify main outcome e.g 14 MRGs? Need think deeply. We should extract main numerical result. Paper main finding is prognostic signature based on 14 mast cell related genes. Number 14. Unit? \"14-MRGs\" unit perhaps \"MRGs\" or \"mast cell marker genes\"? The paper prints \"14-MRGs\". They ask unit the paper prints, could unit empty because number is count? Could unit \"MRGs\". Headline number 14 with unit \"MRGs\" perhaps. Evidence exact quote from abstract includes linkage \"The 14-MRGs prognostic signature classified patients into high- and low-risk groups, and the overall survival (OS) of the low-risk group was significantly higher than that of the high-risk group (p < 0.05).\" Or conclusion \"We combined scRNA-seq data and bulk RNA-seq data to construct a 14-MRGs-based prognostic model capable of well predicting the prognosis of HNSCC patients.\" That directly target main finding. parent_value 14, unit \"MRGs\", evidence full sentence. target_result description maybe \"The paper states a 14-MRGs-based prognostic model for predicting HNSCC prognosis.\" number_stated true.\n\nBut is intended main finding 14-MRGs or AUC? Need not rush. We have huge token budget but can be concise final. Let's inspect instruction semantics: They designed prompt for numerical result extraction with target described vague \"the headline numerical result the paper states for its main finding\". Registered target might aim main finding e.g \"the areas under ROC curves 0.740, 0.737 and 0.707\" cannot single number? They explicitly single numerical result and number_stated false if no number. Maybe main finding is risk group OS higher and no effect size; then false? Need infer intended from source. It seems generic registered target phrase, perhaps benchmark tasks ask primary endpoint extraction with \"headline numerical result the paper itself states for its main finding\". We need choose likely. Many previous similar tasks? We have only prompt. Could reason based main result abstract and conclusion. Abstract states:\n\"We identified mast cell marker genes ... construct prognostic signature ...\"\n\"The 14-MRGs prognostic signature classified patients into high- and low-risk groups, and the overall survival (OS) of the low-risk group was significantly higher than that of the high-risk group (p < 0.05). The areas under the ROC curves of the nomogram were 0.740, 0.737 and 0.707 at 1-, 3-, and 5-year, and they also showed better detection efficacy in the validation group than other independent predictors...\"\n\"We combined ... construct a 14-MRGs-based prognostic model...\"\nThe primary finding perhaps 14 gene model, with 14 count. Headline numerical result is 14 genes. We can quote conclusion to attach. Unit \"MRGs\" printed. They want \"value paper itself states for registered target\" no computed etc. 14 directly stated. Should use exact contiguous quote sentence. Could use \"In this study, we applied scRNA-seq technology to identify MRGs, constructed a 14-MRGs prognostic model for HNSCC, and revealed the immune infiltration and landscape.\" That's clear names model number. unit \"MRGs\" (mast-cell-related genes). Evidence whole clause. parent_value 14.\n\nCould alternatively report AUC \"0.740\" no unit, first 1-year. They request \"single numerical result\" perhaps 0.740 with unit no unit. But target main finding could be \"prognostic performance of nomogram\" and AUC triple impossible one. They would likely use target \"one-year AUC\" if so. Instead target broad main finding, so unique number identifying model 14. I think correct.\n\nNeed decide target_result wording. Could state \"The paper's main finding is a 14-MRGs prognostic signature/model that separates patients into high- and low-risk groups, with longer overall survival in the low-risk group.\" Evidence selected exact sentence with 14. They request \"Report headline number only: ... value...\" Might imply target_result should be succinct just headline number and unit, no other numbers. Usually schema target_result maybe textual explanation. Could use \"14 MRGs\" or \"A prognostic signature based on 14 mast-cell-related genes.\" Better.\n\nUnit must unit paper prints. \"MRGs\" appears in hyphen \"14-MRGs\". Unit \"MRGs\" appropriate, not \"genes\" because paper abbreviates MRGs. Could write \"MRGs\" exactly. Evidence \"We combined scRNA-seq data and bulk RNA-seq data to construct a 14-MRGs-based prognostic model capable of well predicting the prognosis of HNSCC patients.\" Exact contiguous from source. Good.\n\nBut wait instruction \"The unit must be the unit the paper prints.\" Counts often unit absent; \"14-MRGs\" could \"MRGs\". We should output unit \"MRGs\" and value 14. Is \"14-MRGs\" an adjectival compound not unit? Still gene count unit MRGs. Can choose unit \"MRGs\". Main result may \"14\" count.\n\nMaybe \"14-MRGs\" headline number is number of selected model genes and not \"numerical result\" in sense result? They could consider number of model genes as core signature characteristic, so yes.\n\nNeed abide developer claims only source. Our target_result claims directly supported. If mention low-risk OS, evidence sentence perhaps includes. Could pick abstract full sentence to support all. Evidence:\n\"The 14-MRGs prognostic signature classified patients into high- and low-risk groups, and the overall survival (OS) of the low-risk group was significantly higher than that of the high-risk group (p < 0.05).\"\nThis attaches number directly to prognostic signature, supports main finding and survival. target_result \"A 14-MRGs prognostic signature that classifies HNSCC patients into high- and low-risk groups, with significantly higher overall survival in the low-risk group.\" Evidence has p value 0.05 but no issue exact contains multiple numbers though headline only 14. They say \"Report headline number only\" could not include p in target_result but evidence required quote includes p. Could avoid p by conclusion sentence with only 14 and HNSCC (no numeric). Good.\n\nEvidence sentence conclusion has 14-MRGs and no other numeric. Use that. \"We combined scRNA-seq data and bulk RNA-seq data to construct a 14-MRGs-based prognostic model capable of well predicting the prognosis of HNSCC patients.\" This exactly source. target_result \"A 14-MRGs-based prognostic model for predicting the prognosis of HNSCC patients.\" output JSON no markdown.\n\nDouble check source exact includes that exact sentence yes Abstract last and [Conclusion] first. \"14-MRGs-based\" yes. unit \"MRGs\" exact printed. parent_value 14.\n\nCould target_result \"The main finding is a prognostic signature based on 14 mast cell marker genes.\" MRG acronym defined \"prognostically relevant mast cell-related genes (MRGs)\" and title \"mast cell marker gene-related\". Use \"14-MRGs-based prognostic model\" exact term to avoid invented interpretation.\n\nWe should not mention ROC. Final.</think>\n\n{\"parent_value\":14,\"unit\":\"MRGs\",\"evidence\":\"We combined scRNA-seq data and bulk RNA-seq data to construct a 14-MRGs-based prognostic model capable of well predicting the prognosis of HNSCC patients.\",\"target_result\":\"A 14-MRGs-based prognostic model for predicting the prognosis of HNSCC patients.\",\"number_stated\":true}", "reading": {"parent_value": 14, "unit": "MRGs", "evidence": "We combined scRNA-seq data and bulk RNA-seq data to construct a 14-MRGs-based prognostic model capable of well predicting the prognosis of HNSCC patients.", "target_result": "A 14-MRGs-based prognostic model for predicting the prognosis of HNSCC patients.", "number_stated": true, "source_locator": "chars 2055-2209 of source sha256 f35adf1c21e8c24dd0e6048a641b6228756c7275132296eb3d12d670c62e857d"}, "recorded_at": "2026-10-31T15:22:31.335158+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The nomogram had areas under the ROC curves of 0.740, 0.737, and 0.707 at 1, 3, and 5 years, respectively.", "minimax_alt": "The nomogram's areas under the ROC curves were 0.740 at 1 year, 0.737 at 3 years, and 0.707 at 5 years.", "decisive": false}, "analysis_methods": {"minimax": ["single-cell RNA sequencing (scRNA-seq)", "Cox regression", "LASSO regression", "receiver operating characteristic (ROC) analysis", "calibration curves", "Kaplan-Meier survival curves", "log-rank test", "Wilcoxon test", "Spearman correlation analysis", "CIBERSORT deconvolution", "CIBERSORT-ABS", "XCELL", "TIMER", "QUANTISEQ", "MCPCOUNTER", "EPIC", "ESTIMATE", "Tumor immune dysfunction and exclusion (TIDE)", "oncoPredict"], "minimax_alt": ["single-cell RNA sequencing (scRNA-seq)", "bulk RNA-seq", "Cox regression", "LASSO regression", "receiver operating characteristic (ROC) curves", "calibration curves", "Kaplan-Meier survival curves", "log-rank tests", "C-index", "X-tile cut-off calculation"], "decisive": false}, "statistical_method": {"minimax": "receiver operating characteristic (ROC) analysis", "minimax_alt": "receiver operating characteristic (ROC) curves", "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:bf1075346e394eebd3871635bfee77f8441a9471b818f0b90c8454ec8a34692a", "type": "sep_package", "label": "SEP v1 package for pmid:40703522"}], "activities": [{"id": "activity:conversion:pmid:40703522", "type": "conversion", "used": ["package:bf1075346e394eebd3871635bfee77f8441a9471b818f0b90c8454ec8a34692a"], "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:40703522", "parent_hash": "sha256:f85b2486c7483ca88a429b2706047591dc38d5e16d58bf24180910b56ac57850", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40703522 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:40703522' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:15:57+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}