{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39984646", "kind": "science-record", "revision": 2, "content_hash": "sha256:d51caaed7cd06c9fc29e70e8dbb4a1cc4a0e020b8b58f9dd11d12a78bc487c7d", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:36Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Predicting immunotherapy prognosis and targeted therapy sensitivity of colon cancer based on a CAF-related molecular signature.", "doi": "10.1038/s41598-025-90899-z", "pmid": "39984646", "authors": null, "journal": "Scientific reports", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 244.0, "unit": "genes", "tolerance": null, "source": "chars 847-957 of source sha256 54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e"}, "evidence": [{"asset": "source:pmid:39984646", "locator": "chars 847-957 of source sha256 54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e", "quote": "In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival."}]}], "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:39984646"], "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:39984646", "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:39984646' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39984646", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-90899-z", "sha256": "sha256:54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-90899-z", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39984646:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a08da19707a0a791eab0750e645ccc63fee556acba0fdcb6134bd013545dd31e", "bytes": 814, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Clinical characteristics of the colon cancer patients in three cohorts.", "structure": {"pmcid": "PMC11845748", "section_index": 3, "section_title": "Patients and data collection", "row_count": 14, "column_count": 4}, "table": {"label": "Table 1", "caption": "Clinical characteristics of the colon cancer patients in three cohorts.", "rows": [["", "TCGA-COAD (n = 446)", "GSE39582 (n = 562)", "ZHSU (n = 157)"], ["Status (%)"], ["Alive", "350 (78.5)", "371 (66.0)", "144 (91.7)"], ["Dead", "96 (21.5)", "191 (34.0)", "13 (8.3)"], ["Age (median, range)", "67.0 (31–90)", "66.9 (22–97)", "67.1 (25–95)"], ["Gender (%)"], ["Female", "212 (47.5)", "253 (45.0)", "52 (33.1)"], ["Male", "234 (52.5)", "309 (55.0)", "105 (66.9)"], ["TNM stage (%)"], ["I", "75 (16.8)", "32 (5.7)", "4 (2.6)"], ["II", "175 (39.2)", "262 (46.6)", "43 (27.4)"], ["III", "124 (27.8)", "204 (36.3)", "85 (54.1)"], ["IV", "61 (13.7)", "60 (10.7)", "25 (15.9)"], ["Unknown", "11 (2.5)", "4 (0.7)", "0 (0)"]], "row_count": 14, "column_count": 4, "numeric_cells": 33, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}], "gaps": ["asset:source:pmid:39984646 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:39984646", "asset:table:pmid:39984646:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39984646"]}, "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": "800b969d8afb49d6e4541734cc1f1bab2448ab0b3bb2182b60d6bdd9bbe58d0f", "source_hash": "54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e", "raw_response_sha256": "sha256:3f94617b9d2f03cd56c1c45b6bd8a47c6e83a52c646951760c9634838c1458b8", "raw_response_chars": 5195}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "ff357e0f3cdb18e3fa30c8bcb2c46c5c44213699f5c9fbf05c8b23190d12d2c4", "source_hash": "54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e", "raw_response_sha256": "sha256:8acf0d08e10afbb0a9d4bcfe37da2c9044f1670db5dcfacbda7af45b48450c51", "raw_response_chars": 53211}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "ca92fce1e20eeff2103ea769921cd221acd24eec9dc2a93ae917eaca7e868d96", "source_hash": "54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e", "raw_response": "{\"parent_value\":244,\"unit\":\"genes\",\"evidence\":\"In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival.\",\"target_result\":\"The paper states that 244 genes were correlated with CAF infiltration.\",\"number_stated\":true}", "reading": {"parent_value": 244, "unit": "genes", "evidence": "In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival.", "target_result": "The paper states that 244 genes were correlated with CAF infiltration.", "number_stated": true, "source_locator": "chars 847-957 of source sha256 54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e"}, "recorded_at": "2026-10-31T15:31:06.037845+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "564f4f8d5f607a8d92ec9010f9836adfcb88e4a19f3a4305371332b0194bfa00", "source_hash": "54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e", "raw_response": "<think>We need answer JSON only. Need identify headline numerical result for main finding from supplied source. Abstract has \"a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival. Notably, FSTL3, CRIP2, and SLC2A3 were selected for CAFscore.\" Registered target: headline numerical result paper states for main finding. Could be 244? Need infer task wording likely asks extract numerical result attached to target. Source text provided title/abstract/methods/conclusion, omitted results. Main finding is CAF molecular signature; numerical headline maybe 244 genes? Or three CAF-related genes? Need understand likely benchmark. They ask \"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 generic \"the headline numerical result the paper states for its main finding\". We need find main headline numeric result in source. Abstract: \"In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival. Notably, FSTL3, CRIP2, and SLC2A3 were selected for the CAFscore.\" Main finding is signature based on 3 genes; conclusion \"detecting three CAF-related genes\". Which is headline numerical result? Could be \"three\" but number format likely 3. Yet request numerical result replication has to reproduce, target main finding. The text directly states 244, 11, three genes. Which single headline result? Need distinguish perhaps headline number in abstract. \"a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival.\" Those are results. Then 3 selected. Maybe headline numerical result likely 244? Let's parse.\n\nThey may have generated target definition from paper's central result and ask extract one value. The registered target wording generic. Perhaps source includes the paper abstract and methods; central reported number is \"a total of 244 genes were correlated with CAF infiltration\". Main finding is CAF signature. The numerical result likely 244 genes. Evidence exact contiguous quote. Unit \"genes\". target_result perhaps \"244 genes were correlated with CAF infiltration\". number_stated true, parent_value 244.\n\nBut need be certain. Could target be OS hazard ratio? Source omitted detailed results, no HR value. If no number for target, false and state what text does state instead. Yet likely target designed so one clear number exists in supplied text. \"headline numerical result the paper states for its main finding\" points abstract. Which number is headline? 244 is likely first main quantitative finding, but maybe \"three CAF-related genes\" central final model. Need infer language.\n\nUser says \"Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" \"single numerical result that a replication of the registered target has to reproduce.\" Registered target perhaps interpreted as main finding, and asks headline number. There may be one headline numerical result prominently stated. The abstract states:\n- total 244 genes correlated CAF infiltration\n- 11 linked OS\n- FSTL3, CRIP2, SLC2A3 selected (implicitly 3)\n- no effect sizes.\n\nThe paper title main finding: CAF-related molecular signature for predicting prognosis and therapy sensitivity. Could replication target number be 3 genes? Conclusion says \"detecting three CAF-related genes in tumor tissue and calculating an individualized CAFscore, which was an independent risk factor for OS.\" This directly attaches number to main finding/model. \"headline numerical result\" might indeed be 3 CAF-related genes. But is \"three\" a numerical result? yes. They request unit printed; source prints \"three\" rather than \"3\", but parent_value must number 3. Unit could \"CAF-related genes\". Exact quote whole clause.\n\nYet \"single numerical result\" likely derived from structured extraction benchmark where a target paper has key metric. Target phrase \"the headline numerical result the paper states for its main finding\" intentionally vague, perhaps asks us to choose headline among multiple. Often these tasks in this dataset provide a registered target e.g., \"AUC for X\" and source text. Here registered target itself is generic because perhaps target was automatically described. Need inspect wording: \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". Could be an evaluator asking identify headline number from paper. We need likely select 244 genes. Main finding in title and abstract: identified 244 genes associated with CAF infiltration, constructed signature from 3 genes. What number would replication reproduce? If replicating \"headline numerical result\", perhaps number of CAF infiltration-associated genes = 244.\n\nLet's think of title/abstract article likely Scientific Reports 2025. Full abstract's first results sentence: \"In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival. Notably, FSTL3, CRIP2, and SLC2A3 were selected for the CAFscore.\" The abstract's most headline numerical finding might be 244. But conclusion foregrounds \"three CAF-related genes.\" Usually paper summary headline: \"244 genes correlated with CAF infiltration, 11 linked to OS; 3 genes selected.\" If asked single numerical result, perhaps \"a total of 244 genes\" because explicitly total and first key result. Main finding itself is perhaps identification of 244 CAF-related genes. \"headline numerical result\" might point to explicit \"total of 244\" more than count inferred from list (though conclusion says three). They explicitly say \"not a value you calculated\" perhaps to prevent counting three listed genes; though conclusion directly says \"three\". Also unit must unit paper prints. If target is main finding, 244 is printed directly.\n\nCould be 83 pairs of tumors/paracancer tissues: replication of main finding? No, methodological cohort count. Or version numbers, thresholds. Clearly exclude methods. Main numerical result from abstract likely 244.\n\nNeed output schema:\n{\n\"parent_value\":244,\n\"unit\":\"genes\",\n\"evidence\":\"In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival.\",\n\"target_result\":\"244 genes were correlated with CAF infiltration.\",\n\"number_stated\":true\n}\nExact contiguous quote yes. Should evidence perhaps quote clause only up to comma, but user says when links via wording, quote whole clause. \"In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival.\" Is this one sentence, contiguous. Fine. Unit paper prints \"genes\". Headline number only perhaps target_result should say number? \"The paper states that 244 genes were correlated with CAF infiltration.\" Fine.\n\nCould unit be \"genes correlated with CAF infiltration\" rather than genes? They request unit printed. \"genes\" exact. If 3, unit \"CAF-related genes\". Need decide.\n\nLet's investigate subtle clues: \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". If they wanted 244, target wording is broad. \"single numerical result that a replication ... has to reproduce\" Maybe target is a named metric in a benchmark and registration description intentionally says \"headline numerical result\". They want extract headline. In paper abstracts, headline results often phrased as \"a total of 244 genes...\" So yes.\n\n\"Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" For 244 directly stated. For 3, one could count names, but text explicitly says three in conclusion. Yet \"headline\" may imply central model gene count, explicitly conclusion. But source includes conclusion. Which one more headline?\n\nLet's assess article's main finding: \"Predicting immunotherapy prognosis and targeted therapy sensitivity ... based on a CAF-related molecular signature.\" The headline result perhaps model selected three genes. In results/abstract:\n- identify 244 CAF infiltration genes, 11 OS linked\n- select FSTL3, CRIP2, SLC2A3 for CAFscore\n- high score poor outcomes/resistance.\nIf asking number a replication of main finding needs, central signature has 3 genes. But target says \"headline numerical result the paper states for its main finding\" rather than \"size of the signature.\" A replication would need reproduce 244? Perhaps to replicate main finding broadly, first reproduce 244 associated genes. If target were \"headline numerical result\" and no metric specified, they probably expect number in paper's headline abstract result, likely 244.\n\nMaybe they expect false because no specific headline numerical result attached to registered target? But source text clearly gives candidates. Instruction says if text states no number for registered target, false. Is \"headline numerical result for main finding\" sufficiently defined to extract? We should make best judgment, not false.\n\nCould use evidence spanning abstract paragraph that establishes main finding and number, including three selected genes. But asks single number only. Need avoid evidence containing another number 11 if target 244? \"evidence exact contiguous quotation that contains the number\"; doesn't prohibit other numbers, but \"headline number only\" maybe evidence can include full clause. We can quote only first clause: \"In this study, a total of 244 genes were correlated with CAF infiltration\" — exact contiguous quotation but starts sentence and no period. They say don't shorten it? \"do not shorten it\" means quote whole clause perhaps. The wording: \"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.\" This seems quote whole clause, likely complete sentence is safest. It includes 11 though target_result only 244. Is that violating \"headline number only\"? They likely mean don't report ancillary numbers in parent_value/result, evidence necessarily may contain more. Maybe choose narrower clause ending comma? Whole grammatical clause \"a total of 244 genes were correlated with CAF infiltration\" could suffice, but source text includes \"In this study,\". Quote exact \"In this study, a total of 244 genes were correlated with CAF infiltration\" (not complete sentence but full independent clause). Better no extra 11.\n\nBut perhaps if evidence for 3, quote \"Our study identified high-risk colon cancer patients by detecting three CAF-related genes in tumor tissue and calculating an individualized CAFscore, which was an independent risk factor for OS.\" This directly attaches three to model, main finding. This is compelling: registered target main finding = molecular signature; headline numerical result = three genes. The 244 is an intermediate discovery count, whereas \"headline result\" is final signature of three genes and independent risk factor. Hmm.\n\nLet's search mentally common abstract's key result. Scientific Reports abstracts often conclude:\n\"In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival. Notably, FSTL3, CRIP2, and SLC2A3 were selected for the CAFscore. A higher CAFscore...\" The headline numerical claim likely 244 because first sentence explicitly quantified. If asked \"single numerical result that replication of registered target has to reproduce\" perhaps they have an article-level QA benchmark where target is a numeric finding. They may formulate \"headline numerical result\" when no explicit metric. Usually answer likely first quantitative result in abstract. The user explicitly says \"the value the paper itself states for the registered target\". Registered target perhaps manually registered as \"the headline numerical result the paper states for its main finding\". This is tautological and asks identify. They might expect \"244 genes\". The phrase \"headline\" indicates prominent first numeric result.\n\nLet's see if \"three\" is written as word, whereas task likely expects numerical digit extracted. They ask \"number_stated\" and parent_value number. Both okay. But exact quote with \"three\" qualifies numerical result. They may expect digit likely source benchmark has answer 244. Methods contain lots digits; abstract selection solves.\n\nCould headline be \"11 linked to overall survival\" because this is closest to prognosis main finding? Title predicts immunotherapy prognosis and sensitivity. But 244 is broad discovery, 11 prognostic. The main finding model uses 3. No single unambiguous \"headline number\" unless conventional first quantitative result. The strongest explicitly stated count is 244. So use that.\n\nNeed JSON valid, no markdown. target_result likely concise. Unit exactly \"genes\". Evidence exact contiguous from source. We could include full sentence. The user says \"Report the headline number only\" perhaps target_result should just describe target and number, not mention 11. Evidence can include 11 due quote full sentence. But if they inspect evidence, there are two numbers; target attribution clear. Better quote clause with only 244:\n\"In this study, a total of 244 genes were correlated with CAF infiltration\"\nThis is an exact contiguous substring and complete clause, no ellipsis. It does not include terminal punctuation but quotation can omit punctuation? Exact yes. They said quote whole clause; that's whole main clause. \"In this study,\" introductory modifier. Good.\n\ntarget_result: \"244 genes were correlated with CAF infiltration.\" This repeats number. JSON only.\n\nCould unit perhaps \"genes correlated with CAF infiltration\" to be more meaningful, but paper prints unit as \"genes\"; use \"genes\". Let's answer.</think>\n\n{\"parent_value\":244,\"unit\":\"genes\",\"evidence\":\"In this study, a total of 244 genes were correlated with CAF infiltration\",\"target_result\":\"244 genes were correlated with CAF infiltration.\",\"number_stated\":true}", "reading": {"parent_value": 244, "unit": "genes", "evidence": "In this study, a total of 244 genes were correlated with CAF infiltration", "target_result": "244 genes were correlated with CAF infiltration.", "number_stated": true, "source_locator": "chars 847-920 of source sha256 54ee0bbd886a67c7dcc40fef3c73c53b69e3a0e777305dc5de187695a46d932e"}, "recorded_at": "2026-10-31T15:31:23.511606+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A total of 244 genes were correlated with CAF infiltration, 11 were linked to overall survival, and three genes—FSTL3, CRIP2, and SLC2A3—were selected to construct the CAFscore; high CAFscore identified high-risk colon cancer patients and was an independent risk factor for overall survival.", "minimax_alt": "In this study, a total of 244 genes were correlated with CAF infiltration, with 11 linked to overall survival. Notably, FSTL3, CRIP2, and SLC2A3 were selected for the CAFscore.", "decisive": false}, "work_type": {"minimax": "analysis_plus_physical_validation", "minimax_alt": "analysis_only_for_target", "decisive": true}, "physical_methods": {"minimax": ["Immunohistochemistry (IHC) scoring", "Immunofluorescence (IF) staining"], "minimax_alt": [], "decisive": false}, "analysis_methods": {"minimax": ["Weighted gene co-expression network analysis (WGCNA)", "Univariate Cox regression", "Least absolute shrinkage and selection operator (LASSO) regression", "Kaplan-Meier method", "Log-rank test", "Cox proportional hazard models", "Wilcoxon test", "Paired sample t-test", "Chi-squared test", "Spearman correlation analysis", "ROC analysis", "DeLong method", "Single-cell RNA sequencing analysis"], "minimax_alt": ["Weighted gene co-expression network analysis (WGCNA)", "Univariate Cox regression", "Least absolute shrinkage and selection operator (LASSO) regression"], "decisive": false}, "statistical_method": {"minimax": "Cox proportional hazard models", "minimax_alt": "Weighted gene co-expression network analysis (WGCNA), univariate Cox regression, and least absolute shrinkage and selection operator (LASSO) regression.", "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:57dde5c1ef49f5aabd15726cb1e4b6c985a0bd6b1a0644a8d82654afaafc9c98", "type": "sep_package", "label": "SEP v1 package for pmid:39984646"}], "activities": [{"id": "activity:conversion:pmid:39984646", "type": "conversion", "used": ["package:57dde5c1ef49f5aabd15726cb1e4b6c985a0bd6b1a0644a8d82654afaafc9c98"], "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:39984646", "parent_hash": "sha256:732ba62ad159d441dd947018dfa2848bb1957c79b83ecf70bc75ac85df9cd3d7", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39984646 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:39984646' 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":"2026-11-04T01:43:37+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}}}