{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41483215", "kind": "science-record", "revision": 2, "content_hash": "sha256:f1b8e21ec1afa52a94ceb55fa880c4f3eacb58c0ab8ccb747da365397f5690c4", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Development and validation of a prognostic model based on T cell signature genes in colon cancer using single-cell RNA sequencing.", "doi": "10.1007/s10238-025-01994-4", "pmid": "41483215", "authors": null, "journal": "Clinical and experimental medicine", "year": 2026, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 7.0, "unit": "genes", "tolerance": null, "source": "chars 1121-1243 of source sha256 6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19"}, "evidence": [{"asset": "source:pmid:41483215", "locator": "chars 1121-1243 of source sha256 6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19", "quote": "A prognostic model was developed based on seven genes, encompassing UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2."}]}], "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:41483215"], "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:41483215", "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:41483215' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41483215", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s10238-025-01994-4", "sha256": "sha256:6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s10238-025-01994-4", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41483215:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1493376c525a73ccf17c785969b39659450f170c5433bb3fc3375b9f7a35219f", "bytes": 1033, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#Tab1", "version": null, "note": "Univariate and multivariate Cox regression analyses of each clinical variable", "structure": {"pmcid": "PMC12770019", "section_index": 19, "section_title": "Independent prognostic value of the risk model in the cohort", "row_count": 9, "column_count": 5}, "table": {"label": "Table 1", "caption": "Univariate and multivariate Cox regression analyses of each clinical variable", "rows": [["Dependent:Surv (time, status)", "all", "HR (univariable)", "HR (multivariable)"], ["Age", "Mean ± SD", "66.8 ± 12.9", "1.02 (1.00–1.04.00.04,p = 0.015)", "1.03 (1.01–1.05,p = 0.001)"], ["Gender", "Mean ± SD", "0.5 ± 0.5", "1.17 (0.79–1.74,p = 0.424)", ""], ["Race", "Mean ± SD", "4.2 ± 0.8", "0.91 (0.69–1.20,p = 0.511)", ""], ["M", "Mean ± SD", "0.3 ± 0.4", "3.37 (2.26–5.03,p < 0.001)", "1.83 (1.06–3.15,p = 0.030)"], ["N", "Mean ± SD", "0.6 ± 0.8", "1.98 (1.57–2.49,p < 0.001)", "1.24 (0.86–1.78,p = 0.249)"], ["T", "Mean ± SD", "2.9 ± 0.6", "2.80 (1.88–4.17,p < 0.001)", "1.79 (1.13–2.86,p = 0.014)"], ["Stage", "Mean ± SD", "2.4 ± 0.9", "2.18 (1.74–2.73,p < 0.001)", "1.32 (0.86–2.02,p = 0.201)"], ["Riskscore", "Mean ± SD", "1.2 ± 0.9", "1.80 (1.53–2.12,p < 0.001)", "1.54 (1.30–1.83,p < 0.001)"]], "row_count": 9, "column_count": 5, "numeric_cells": 22, "header_rows": 1, "locator": "section[19]/table-wrap[1]#Tab1"}}], "gaps": ["asset:source:pmid:41483215 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:41483215", "asset:table:pmid:41483215:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41483215"]}, "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": "826767af425496c0a88a64ad191ec1f3a6875bc9ff200d975afc38a3e8d98861", "source_hash": "6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19", "raw_response_sha256": "sha256:7549cb7a7b477751a51e18d2502ce3c108c390ffecf4518dcb9cc7b0e86edf2b", "raw_response_chars": 4210}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "8c869d9f92bbddf7cfb1e7eaed16a80d0db561ca94ae1861ecee5ed1e2e3ceb0", "source_hash": "6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19", "raw_response_sha256": "sha256:a03819e179a895bf2578da45aceb3fb230a4db29c52348501d51d94f87c35aaf", "raw_response_chars": 70864}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "d1029ae8dbbe22299a19ef75ce500ffe6a31c72eccbddba927656ffe3b498b97", "source_hash": "6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19", "raw_response": "{\"parent_value\":7,\"unit\":\"genes\",\"evidence\":\"A prognostic model was developed based on seven genes, encompassing UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2.\",\"target_result\":\"The prognostic model was developed based on seven genes.\",\"number_stated\":true}", "reading": {"parent_value": 7, "unit": "genes", "evidence": "A prognostic model was developed based on seven genes, encompassing UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2.", "target_result": "The prognostic model was developed based on seven genes.", "number_stated": true, "source_locator": "chars 1121-1243 of source sha256 6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19"}, "recorded_at": "2026-10-31T15:18:00.512055+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "74abdb650a75272ac60bc28af092122cb4a4f61c5948b9956d0197d47d814927", "source_hash": "6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19", "raw_response": "<think>We need answer JSON only. Need interpret \"single numerical result that a replication of registered target has to reproduce\", target headline numerical result paper states for main finding. Main finding prognostic model, likely AUC training cohort values? But asks single numerical result singular headline number. Need infer perhaps seven genes? Registered target \"the headline numerical result the paper itself states for its main finding\". Source abstract gives model based on seven genes; AUC 3,5,7 years 0.676, 0.715, 0.721. Which single numerical result headline? They insist one number, evidence exact contiguous quote containing number; attribution may attached list/respectively or direct words. Perhaps expected number is 0.715? Main result perhaps AUC? Need identify \"single numerical result\" likely title/abstract headline metric. We need decide.\n\nQuestion wording perhaps benchmark for extracting parent value from paper, registered target vague generic. \"the headline numerical result the paper itself states for its main finding.\" Usually want one headline number, maybe number of genes? \"A prognostic model was developed based on seven genes\" is headline main finding. Replication of registered target needs reproduce 7? But likely target asks main finding and number could be 0.715? Let's parse.\n\nThey explicitly explain attribution mechanisms:\n- number may be attached to target by parenthetical list\n- by word respectively\n- or words that name target directly.\n- If linked that way, quote whole clause.\nThis suggests source often presents multiple values and registered target disambiguates one. Here target is generic \"headline numerical result ... main finding\". We need choose perhaps \"seven\" as model result, since no specified cohort/time point. Yet parent_value numerical, unit maybe \"genes\". Evidence exact quote: \"A prognostic model was developed based on seven genes, encompassing...\" Target_result perhaps \"The prognostic model was developed based on seven genes.\" Number stated true; parent_value 7; unit \"genes\". But they request \"headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" The main finding is model based on seven genes. Single numerical result that replication must reproduce = 7 genes. However \"headline numerical result\" commonly efficacy metric (AUC), not sample size or dimensional model.\n\nCould be AUC highest 0.951 in GSE17537 at 7 years, but not headline? External validation shows \"consistent predictive performance\", yet one 0.951 stands out. But replication target would likely reproduce model's AUC at specific horizon, perhaps 0.721 in training at 7 years. Yet target does not specify which. Could report entire set? Schema only one number and says single numerical result. Need identify likely intended from abstract. Maybe \"the headline numerical result the paper itself states for its main finding\" = model's AUC. Abstract first reports 0.676, 0.715, 0.721 at 3,5,7 years. No single. Could choose seven genes because only singular number linked directly to model.\n\nLet's inspect exact request semantics: \"Read the supplied paper text and find the single numerical result that a replication of the registered target has to reproduce.\" Registered target given: \"the headline numerical result the paper itself states for its main finding\". Perhaps they expect answer based on target class, perhaps headline statistic. Main finding paper: prognostic model based on seven genes and AUC. What \"single numerical result\" likely headline? Could be 0.715, as AUC at 5 years is often standard headline performance. But source says at 3,5,7 years, and perhaps in full paper a conclusion sentence omitted? The supplied source includes abstract and methods snippets. We need not infer 5-year unless explicitly target. The only singular result is \"seven genes.\" Wording \"based on seven genes\" directly attaches count to main finding model. Thus likely answer 7 genes.\n\nNeed ensure parent_value number 7, unit paper prints. Paper says \"seven genes\", not numeral but number. Unit \"genes\". Evidence exact contiguous quotation: \"A prognostic model was developed based on seven genes, encompassing UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2.\" That's full clause perhaps sentence. Exact. target_result should concise identify. number_stated true. JSON valid. They ask \"headline number only\" perhaps target_result maybe \"7 genes\" rather than extra. Could say \"The prognostic model was developed based on seven genes.\" Schema parent_value etc.\n\nCould unit be \"genes\" exactly printed. yes.\n\nLet's consider whether \"headline numerical result\" may instead be \"0.721\" at 7 years. In abstract, AUC results are key headline numerical outcomes. Replication of registered target might reproduce model performance. But no target metric designated. Maybe benchmark source title/abstract asks identify \"single numerical result\", and perhaps they select main finding number based on generic registered target. Could be intended to choose strongest headline metric, perhaps 0.715? Let's reason through likely task generation.\n\nUser template: \"Read 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.\nREGISTERED TARGET: the headline numerical result the paper itself states for its main finding\"\n\nThis seems user explicitly asks abstractive extraction where target is semantically \"headline numerical result main finding\". Maybe expected to decide number from abstract. They emphasize \"number may be attached ... respectively\" likely because abstract AUC has lists. They might expect some one value selected as headline. Which? Maybe main finding is \"AUC values ...\" and three at 3, 5, 7 years; perhaps target singular means list? But schema parent_value singular, no arrays. Could \"headline\" refer first number in abstract (0.676)? Yet no.\n\nPotential intended answer perhaps 7 genes because it's literally single number and directly linked. Why mention parenthetical/respectively then generic boilerplate applies across tasks. The model based on seven genes is a \"single numerical result\" and replication has to reproduce gene count? A replication would have to identify same seven genes, not merely count 7. But target says headline numerical result, could count as headline model architecture. Yet replication target likely primary endpoint is AUC, not number of genes. Still only unambiguous singular headline number.\n\nCould report 0.715 as central 5-year AUC? But that is calculated selection of middle value, not paper naming it headline. 7-year is commonly primary? For colon cancer prognosis, 5-year AUC likely headline. Abstract reports all horizons, no indication one is headline. User says \"value the paper itself states for the registered target\"—we cannot arbitrarily select 5-year. If target is the main finding (model), all three AUC values are stated, violating single. Number of model genes directly attached to finding and singular. Thus 7 genes.\n\nNeed perhaps target_result \"The prognostic model was developed based on seven genes.\" evidence whole sentence. Unit exact maybe \"genes\". JSON only no markdown. Ensure evidence exact contiguous from source. Let's formulate.\n\nCould parent_value 7 (numeric not seven). Unit \"genes\". target_result perhaps \"The prognostic model was developed based on seven genes.\" This paraphrases but target_result can. Evidence exact.\n\nLet's answer.</think>\n\n{\"parent_value\":7,\"unit\":\"genes\",\"evidence\":\"A prognostic model was developed based on seven genes, encompassing UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2.\",\"target_result\":\"The prognostic model was developed based on seven genes.\",\"number_stated\":true}", "reading": {"parent_value": 7, "unit": "genes", "evidence": "A prognostic model was developed based on seven genes, encompassing UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2.", "target_result": "The prognostic model was developed based on seven genes.", "number_stated": true, "source_locator": "chars 1121-1243 of source sha256 6a41760af75f32faa9dbca16bfecf64dedd1bcaa806936a782a3539cb2c5be19"}, "recorded_at": "2026-10-31T15:18:12.142118+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A seven-gene prognostic model comprising UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2; the training-cohort AUC values at 3, 5, and 7 years were 0.676, 0.715, and 0.721, respectively.", "minimax_alt": "A prognostic model was developed based on seven genes, encompassing UBE2N, TUBA1C, FXR1, CBLB, YTHDC1, GPRIN3, and AGPAT2. The area under the ROC curve (AUC) for the training cohort at 3, 5, and 7 years reached 0.676, 0.715, and 0.721, respectively. External validation using three GEO datasets demonstrated consistent predictive performance of the model. The AUC values at 3, 5, and 7 years were 0.632, 0.617, and 0.582 in GSE39582, 0.689, 0.755, and 0.951 in GSE17537, and 0.667, 0.653, and 0.649 in GSE161158.", "decisive": false}, "analysis_methods": {"minimax": ["least absolute shrinkage and selection operator (LASSO) regression", "LASSO-Cox regression", "multivariate Cox proportional hazards modeling", "receiver operating characteristic (ROC) curve analysis"], "minimax_alt": ["Differential gene expression analysis", "single-cell RNA sequencing (scRNA-seq)", "intersectional analysis", "least absolute shrinkage and selection operator (LASSO) regression", "multivariate Cox proportional hazards models", "receiver operating characteristic (ROC) curves", "Cox regression and LASSO-Cox regression analyses", "KM survival curves and log-rank test"], "decisive": false}, "statistical_method": {"minimax": "receiver operating characteristic (ROC) curves", "minimax_alt": "LASSO regression and multivariate Cox proportional hazards models for prognostic-model development; receiver operating characteristic (ROC) curve analysis for AUC evaluation", "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:f39a0f06d0d86b1c40af9720c6d5a7230947a6daaec197cef8c69f2f12210165", "type": "sep_package", "label": "SEP v1 package for pmid:41483215"}], "activities": [{"id": "activity:conversion:pmid:41483215", "type": "conversion", "used": ["package:f39a0f06d0d86b1c40af9720c6d5a7230947a6daaec197cef8c69f2f12210165"], "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:41483215", "parent_hash": "sha256:90852dff032ee46960692a43ed30a67f052c45bd8204891c4d4c9ee0005304b5", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41483215 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:41483215' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:38:59+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}}}