{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39958209", "kind": "science-record", "revision": 2, "content_hash": "sha256:c5e2dba34c412fddc9c6a2ece32cc6afbbd0cf0a0121979bc2efc32b2d3d9a5a", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:34Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "MS4A15 gene expression as a prognostic marker for clinical outcomes in lung adenocarcinoma.", "doi": "10.21037/tlcr-24-623", "pmid": "39958209", "authors": null, "journal": "Translational lung cancer research", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39958209"], "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:39958209", "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:39958209' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39958209", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/tlcr-24-623", "sha256": "sha256:284b4434737b226836152a23f657b8837623bae555a18bfcdce7be06e7522af4", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/tlcr-24-623", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39958209:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ff5a1fb184ba343a61e2a0651d4daead9af8022e68485f449e58e74010a1e371", "bytes": 1528, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#t1", "version": null, "note": "Association between MS4A15 expression and the clinicopathologic features of LUAD patients", "structure": {"pmcid": "PMC11826265", "section_index": 17, "section_title": "Association between MS4A15 expression and clinical features", "row_count": 34, "column_count": 4}, "table": {"label": "Table 1", "caption": "Association between MS4A15 expression and the clinicopathologic features of LUAD patients", "rows": [["Characteristic", "Low expression of MS4A15 (n=267)", "High expression of MS4A15 (n=268)", "P"], ["Gender, n (%)", "", "", "0.002"], ["Female", "124 (23.2)", "162 (30.3)", ""], ["Male", "143 (26.7)", "106 (19.8)", ""], ["Age, n (%)", "", "", "0.02"], ["≤65 years", "142 (27.5)", "113 (21.9)", ""], [">65 years", "118 (22.9)", "143 (27.7)", ""], ["Age, years, median [IQR]", "64 [58.75, 72]", "67 [59, 73]", "0.06"], ["Smoker, n (%)", "", "", "0.008"], ["No", "26 (5.0)", "49 (9.4)", ""], ["Yes", "232 (44.5)", "214 (41.1)", ""], ["T stage, n (%)", "", "", "0.005"], ["T1", "68 (12.8)", "107 (20.1)", ""], ["T2", "160 (30.1)", "129 (24.2)", ""], ["T3", "26 (4.9)", "23 (4.3)", ""], ["T4", "11 (2.1)", "8 (1.5)", ""], ["N stage, n (%)", "", "", "0.09"], ["N0", "166 (32.0)", "182 (35.1)", ""], ["N1", "48 (9.2)", "47 (9.1)", ""], ["N2", "45 (8.7)", "29 (5.6)", ""], ["N3", "2 (0.4)", "0", ""], ["M stage, n (%)", "", "", "0.61"], ["M0", "190 (49.2)", "171 (44.3)", ""], ["M1", "15 (3.9)", "10 (2.6)", ""], ["Pathologic stage, n (%)", "", "", "0.04"], ["Stage I", "137 (26.0)", "157 (29.8)", ""], ["Stage II", "58 (11.0)", "65 (12.3)", ""], ["Stage III", "52 (9.9)", "32 (6.1)", ""], ["Stage IV", "16 (3.0)", "10 (1.9)", ""], ["Primary therapy outcome, n (%)", "", "", "0.005"], ["PD", "47 (10.5)", "24 (5.4)", ""], ["SD", "15 (3.4)", "22 (4.9)", ""], ["PR", "1 (0.2)", "5 (1.1)", ""], ["CR", "156 (35.0)", "176 (39.5)", ""]], "row_count": 34, "column_count": 4, "numeric_cells": 63, "header_rows": 1, "locator": "section[17]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:39958209:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a5512366bab8b2da672e75f9d9a4c5f12b7be4e165d1d2850d06a80a399ecd24", "bytes": 989, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#t2", "version": null, "note": "The relationship between the clinicopathological factors of LUAD patients and MS4A15 expression using a logistic analysis", "structure": {"pmcid": "PMC11826265", "section_index": 17, "section_title": "Association between MS4A15 expression and clinical features", "row_count": 10, "column_count": 4}, "table": {"label": "Table 2", "caption": "The relationship between the clinicopathological factors of LUAD patients and MS4A15 expression using a logistic analysis", "rows": [["Characteristics", "Total (N)", "Odds ratio (95% CI)", "P value"], ["Gender (male vs. female)", "535", "0.567 (0.402–0.799)", "0.001"], ["Age (>65 vs. ≤65 years)", "516", "1.523 (1.077–2.158)", "0.02"], ["Smoker (no vs. yes)", "521", "2.043 (1.236–3.446)", "0.006"], ["Race (Black or African American vs. White)", "461", "0.809 (0.457–1.422)", "0.46"], ["Pathologic stage (stage III–IV vs. stage I–II)", "527", "0.543 (0.351–0.831)", "0.005"], ["T stage (T3–4 vs. T1–2)", "532", "0.809 (0.483–1.347)", "0.42"], ["N stage (N2–3 vs. N0–1)", "519", "0.577 (0.347–0.944)", "0.03"], ["M stage (M1 vs. M0)", "386", "0.741 (0.314–1.675)", "0.48"], ["Primary therapy outcome (PD vs. PR & CR)", "409", "0.443 (0.256–0.750)", "0.003"]], "row_count": 10, "column_count": 4, "numeric_cells": 31, "header_rows": 1, "locator": "section[17]/table-wrap[2]#t2"}}], "gaps": ["asset:source:pmid:39958209 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:39958209", "asset:table:pmid:39958209:1", "asset:table:pmid:39958209:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39958209"]}, "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": "67ea4a752f7c9717331266efa921cda58e0e1366ffa0043b71dcec2deb0d0719", "source_hash": "284b4434737b226836152a23f657b8837623bae555a18bfcdce7be06e7522af4", "raw_response_sha256": "sha256:0be345ef36b38e5479d83ef1e6ea3aa1d7f0adb76cb246f7b1a067c1656e61b9", "raw_response_chars": 4270}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "d9683f4534b8befcc6528ccd67263e9b674b0a13a0119247980007722da20930", "source_hash": "284b4434737b226836152a23f657b8837623bae555a18bfcdce7be06e7522af4", "raw_response_sha256": "sha256:83a55e337805b337bab98b783bd13a11ff18cd7132becb25e3240484e3dfe06d", "raw_response_chars": 57368}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "4ed35c5c76744787538a0486af5019f82f16054c8fe8ef08b8836a58fa0cba9a", "source_hash": "284b4434737b226836152a23f657b8837623bae555a18bfcdce7be06e7522af4", "raw_response": "{\"parent_value\":0.863,\"unit\":\"area under the curve\",\"evidence\":\"The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.\",\"target_result\":\"The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.\",\"number_stated\":true}", "reading": {"parent_value": 0.863, "unit": "area under the curve", "evidence": "The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.", "target_result": "The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.", "number_stated": true, "source_locator": "chars 2539-2616 of source sha256 284b4434737b226836152a23f657b8837623bae555a18bfcdce7be06e7522af4"}, "recorded_at": "2026-10-31T15:24:39.083384+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "08ac05d2e0337129330180d03f7124616e3fce1c333bf117936931b8c7b3f01c", "source_hash": "284b4434737b226836152a23f657b8837623bae555a18bfcdce7be06e7522af4", "raw_response": "<think>We need answer JSON only. Need identify single numerical result replication registered target headline numerical result paper states for main finding. Need exact contiguous quote with number, unit printed. Candidates AUC 0.863, perhaps main finding prognostic marker no numeric hazard ratio. Headline numerical result likely 0.863, area under curve. Need unit as paper prints. \"The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.\" Unit perhaps \"area under the curve\" dimensionless. Required unit string. They say unit must be unit paper prints. It prints \"The area under the curve ... was 0.863.\" Could unit be empty? But number stated true likely unit perhaps \"area under the curve\" or \"AUC\"? Need infer desired extraction style.\n\nTarget is generic: headline numerical result paper states for main finding. Source abstract's only headline numerical result is AUC 0.863. Evidence exact contiguous quote. parent_value 0.863. Unit could be \"area under the curve\" perhaps the measured metric, though no physical unit. Maybe \"AUC\" is common unit? Paper doesn't literally use abbreviation AUC in quoted sentence, though earlier \"receiver operating characteristic (ROC)\". It says \"The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.\" The unit perhaps \"area under the curve\" (dimensionless). target_result can say \"The area under the ROC curve for MS4A15 effectiveness was 0.863.\" They demand headline number only perhaps means JSON fields, but target_result likely concise textual result.\n\nNeed exact quotation evidence whole clause. Could quote sentence exactly. Ensure no paraphrase. Unit must be paper prints. \"area under the curve of the ROC curve\" maybe awkward. We can set unit \"area under the curve of the ROC curve\" but unit is not really unit. Maybe unit string \"AUC\" despite source doesn't print acronym. User says unit must be unit paper prints, likely numerical results tasks expect units like years, months, etc. For AUC, dimensionless and no unit. But schema demands string; can use \"\". Yet instruction only says if no number, leave unit and evidence empty. Thus if number stated likely expect unit nonempty? Not necessarily schema only. They say \"unit must be the unit the paper prints.\" If dimensionless metric, perhaps unit \"area under the curve\" as paper wording. Need determine likely benchmark expects unit \"AUC\" perhaps extraction convention.\n\nLet's parse task framing. \"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.\"\n\nThis seems general extraction benchmark where target registered perhaps verbal, source may or may not numeric. Here target: headline numerical result paper states for its main finding. Need pick single number. The main numerical finding could 0.863 AUC. Other numbers: 1605 DEGs, 82 pathways, 24 immune cell types, cutoff 50%, thresholds, versions, datasets. Clearly headline result in abstract = AUC 0.863. Unit? The paper prints metric \"area under the curve of the ROC curve for MS4A15 effectiveness\". Could represent unit as \"area under the curve of the ROC curve\". But \"unit\" likely \"AUC\" because that's the measure. Yet paper prints ROC and area under curve, though not acronym AUC. They insist unit must be unit paper prints perhaps don't transform 0.863 to 86.3%. So \"area under the curve of the ROC curve\" or perhaps empty string. We need provide exact unit as source's printed wording maybe \"area under the curve\". Let's think expected schema likely evaluated by LLM or exact fields? parent_value 0.863. unit probably \"area under the curve of the ROC curve\" or \"AUC\". Evidence exact sentence. target_result perhaps \"Area under the ROC curve for MS4A15 effectiveness: 0.863.\" Could they expect no unit since AUC is dimensionless? They ask unit must be unit paper prints. There is no conventional physical unit. In similar tasks, for AUC likely unit \"AUC\" accepted. Need ensure no invented source. \"AUC\" acronym does not appear in source at all? Search source: receiver operating characteristic (ROC), area under curve. No \"AUC\". So if unit must be as paper prints, avoid AUC. Could set unit \"area under the curve of the ROC curve for MS4A15 effectiveness\" exactly as printed. But that's metric descriptor, not unit. Perhaps unit could be \"\" because dimensionless. Yet they specifically require unit field and only tell empty if no number stated, implying for stated number unit should be populated. So likely they consider measurement unit to be \"area under the curve\". Could put \"area under the curve of the ROC curve\". Better exact printed phrase.\n\nNeed \"headline number only\" perhaps target_result should just \"0.863\" and unit separate. But they ask target_result when no number say what text states instead. For stated case, likely target_result textual description. Maybe \"0.863 (area under the ROC curve for MS4A15 effectiveness).\" Yet evidence does attribution. We can make target_result \"Area under the ROC curve for MS4A15 effectiveness was 0.863.\" This repeats.\n\nExact quote:\n\"The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.\"\nYes.\n\nJSON valid. Unit string maybe \"area under the curve of the ROC curve\". Is capitalization relevant? Unit perhaps \"area under the curve of the ROC curve for MS4A15 effectiveness\" exact. Let's formulate.\n\nCould there be concern headline main finding is expression differential but no numeric result, whereas AUC is a secondary metric and not headline? The registered target phrasing explicitly asks \"the headline numerical result the paper states for its main finding\", perhaps the source's abstract has one numerical result. likely 0.863.\n\nMaybe the headline result in paper title/main claim is MS4A15 downregulated, and no exact number stated for expression change. But instruction asks single numerical result replication target has to reproduce. They might expect AUC because only reported headline metric. The text says \"The area under the curve ... 0.863.\" likely selected target. Yes.\n\nUnit: AUC dimensionless. Could label \"area under the curve (AUC)\" but AUC not printed, though expansion printed. They say \"unit must be the unit the paper prints\", likely okay to use phrase exactly. Let's use \"area under the curve of the ROC curve\" exact contiguous phrase. target_result perhaps \"The ROC area under the curve for MS4A15 effectiveness was 0.863.\" No need exact quote there.\n\nNeed output only JSON.</think>\n\n{\"parent_value\":0.863,\"unit\":\"area under the curve of the ROC curve\",\"evidence\":\"The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.\",\"target_result\":\"The area under the ROC curve for MS4A15 effectiveness was 0.863.\",\"number_stated\":true}", "reading": {"parent_value": 0.863, "unit": "area under the curve of the ROC curve", "evidence": "The area under the curve of the ROC curve for MS4A15 effectiveness was 0.863.", "target_result": "The area under the ROC curve for MS4A15 effectiveness was 0.863.", "number_stated": true, "source_locator": "chars 2539-2616 of source sha256 284b4434737b226836152a23f657b8837623bae555a18bfcdce7be06e7522af4"}, "recorded_at": "2026-10-31T15:24:58.167781+00:00"}], "agreement": false, "disagreements": {"physical_methods": {"minimax": ["Real-time quantitative polymerase chain reaction (RT-qPCR) was performed to validate the messenger RNA transcription level in vitro."], "minimax_alt": ["Cell culture of A549 and NHBE cells", "Real-time quantitative polymerase chain reaction (RT-qPCR)"], "decisive": false}, "analysis_methods": {"minimax": ["Differential Expression analysis of Sequencing data version 2 (DESeq2)", "ClusteProfiler package for Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, and gene set enrichment analyses", "Gene set variation analysis (GSVA)", "Wilcoxon rank-sum test", "Logistic regression analysis", "Receiver operating characteristic (ROC) curve analysis", "Kaplan-Meier analysis", "Spearman correlation analysis", "Real-time quantitative polymerase chain reaction (RT-qPCR)"], "minimax_alt": ["Differential Expression analysis of Sequencing data version 2 (DESeq2)", "Gene Ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analyses using ClusteProfiler", "Gene set enrichment analysis using ClusteProfiler", "Gene set variation analysis (GSVA) using single-sample gene set enrichment analysis (ssGSEA)", "Spearman correlation", "Wilcoxon rank-sum test", "Logistic regression", "Receiver operating characteristic (ROC) curve analysis", "Kaplan-Meier analysis"], "decisive": false}, "unit": {"minimax": "area under the curve", "minimax_alt": "area under the curve of the ROC curve", "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:05ef46f68ee8df57e10912dbf40911ef8eb04cb9425a81e199ee07a623b12a90", "type": "sep_package", "label": "SEP v1 package for pmid:39958209"}], "activities": [{"id": "activity:conversion:pmid:39958209", "type": "conversion", "used": ["package:05ef46f68ee8df57e10912dbf40911ef8eb04cb9425a81e199ee07a623b12a90"], "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:39958209", "parent_hash": "sha256:23c78823e4ee50b535e567d0d851af1fb95e708768a60bf0fc1ab3c281e4a492", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39958209 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:39958209' 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":"2026-11-04T02:48:41+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}}}