{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40822974", "kind": "science-record", "revision": 2, "content_hash": "sha256:209721fbbadd2626105ffbed933445b4f7fd21a862cef407ad177f43329ea8d4", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:46Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Immune molecule diagnostics in colorectal cancer: CCL2 and CXCL11.", "doi": "10.1515/biol-2025-1147", "pmid": "40822974", "authors": null, "journal": "Open life sciences", "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": 45.0, "unit": "degs", "tolerance": null, "source": "chars 1031-1149 of source sha256 f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c"}, "evidence": [{"asset": "source:pmid:40822974", "locator": "chars 1031-1149 of source sha256 f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c", "quote": "A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes."}]}], "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:40822974"], "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:40822974", "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:40822974' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40822974", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1515/biol-2025-1147", "sha256": "sha256:f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1515/biol-2025-1147", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40822974:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2cbb2cf5b0b38ff6e9f97c56da667a8ac54c34722028d11de7ceabd9c4e4dff5", "bytes": 725, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#j_biol-2025-1147_tab_001", "version": null, "note": "Immune cell infiltration showed statistically significant differences among the four groups", "structure": {"pmcid": "PMC12355365", "section_index": 12, "section_title": "Landscape of immune cell infiltration in SSA and TSA", "row_count": 14, "column_count": 2}, "table": {"label": "Table 1", "caption": "Immune cell infiltration showed statistically significant differences among the four groups", "rows": [["Immune cells", "P values"], ["Activated mast cells", "1.53 × 10−13"], ["Resting mast cells", "1.82 × 10−16"], ["Activated dendritic cells", "0.01"], ["Resting dendritic cells", "1.73 × 10−7"], ["Macrophages", ""], ["M0", "1.72 × 10−8"], ["M1", "4.43 × 10−9"], ["M2", "1.28 × 10−5"], ["Regulatory T cells (Tregs)", "0.02"], ["Follicular Helper T cells", "0.003"], ["Activated memory T CD4 cells", "0.0002"], ["Plasma cells", "7.92 × 10−11"], ["Naive B cells", "0.01"]], "row_count": 14, "column_count": 2, "numeric_cells": 12, "header_rows": 1, "locator": "section[12]/table-wrap[1]#j_biol-2025-1147_tab_001"}}, {"id": "asset:table:pmid:40822974:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b9d6b405ba748ab2b1bae3c4b586a13a793a40fa5976d4a4b695b7a384712675", "bytes": 834, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#j_biol-2025-1147_tab_002", "version": null, "note": "Ten different algorithms for hub genes that had the highest scores by CytoHubba", "structure": {"pmcid": "PMC12355365", "section_index": 14, "section_title": "PPI network for key immune-related gene selection", "row_count": 11, "column_count": 6}, "table": {"label": "Table 2", "caption": "Ten different algorithms for hub genes that had the highest scores by CytoHubba", "rows": [["Algorithm", "Gene1", "Gene2", "Gene3", "Gene4", "Gene5"], ["MCC", "CXCL14", "CCL24", "CXCL12", "CCL19", "CXCL11"], ["DMNC", "CCL2", "CXCR4", "CXCL12", "CCL19", "CXCL11"], ["MNC", "CCL2", "CXCL11", "CXCR4", "CXCL12", "CCL19"], ["Degree", "CXCL11", "CCL2", "CXCR4", "CXCL3", "CCL19"], ["EPC", "CXCL11", "CCL2", "CXCR4", "CCL24", "LGR5"], ["BottleNeck", "CCL11", "CCL2", "CXCR4", "CCL24", "CXCL14"], ["EcCentricity", "CXCL11", "CCL2", "CXCR4", "CXCL14", "CXCL12"], ["Closeness", "CXCL11", "CCL2", "CXCR4", "CXCL14", "CXCL12"], ["Radiality", "CXCL11", "CCL2", "CXCL14", "RETNLB", "MX2"], ["Betweenness", "CCL2", "CXCL11", "RETNLB", "CXCR4", "CXCL14"]], "row_count": 11, "column_count": 6, "numeric_cells": 28, "header_rows": 1, "locator": "section[14]/table-wrap[1]#j_biol-2025-1147_tab_002"}}], "gaps": ["asset:source:pmid:40822974 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:40822974", "asset:table:pmid:40822974:1", "asset:table:pmid:40822974:2"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40822974"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "6b612d15a9fbd0ddcbb6b4de8e7be9039d448cf95d15c8f76959478ea05bbc6d", "source_hash": "f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c", "raw_response_sha256": "sha256:f0d0555ca96fad6b0524208e18e0e85b4a5b0201048cacc79773d56995380dc3", "raw_response_chars": 20076}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "611067995bdfbeef70b71c077d8d1d072238b1015edca8205da2ba038072ddcb", "source_hash": "f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c", "raw_response": "{\"parent_value\":45,\"unit\":\"DEGs\",\"evidence\":\"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\",\"target_result\":\"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified.\",\"number_stated\":true}", "reading": {"parent_value": 45, "unit": "DEGs", "evidence": "A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.", "target_result": "A total of 45 DEGs (34 upregulated, 11 downregulated) were identified.", "number_stated": true, "source_locator": "chars 1031-1149 of source sha256 f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c"}, "recorded_at": "2026-10-31T15:29:39.333755+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "60f4237f7b3a3fe8736d581eca4ad4f33b22fb4f3a85d73ceac1274fa1589401", "source_hash": "f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c", "raw_response": "<think>We need answer JSON only, extract claims source. Need determine single numerical result headline main finding registered target. Source gives \"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\" Need decide headline number 45 likely target numerical result. Unit DEGs. Need quote exact contiguous containing number and linking clause whole. User stresses value paper itself states main finding, no calc. This source abstract seems actual article maybe AUC values omitted. Headline numerical result likely 45 DEGs with breakdown. Need output parent_value 45 unit \"DEGs\" evidence full clause \"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\" target_result maybe \"45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\" number_stated true. Need deliberate if target is headline result for main finding \"CCL2 and CXCL11\" maybe diagnostic AUC missing. Only numbers abstract 45 (34 up 11 down), datasets, immune 22, etc. They ask single numerical result a replication registered target has to reproduce. They likely expect 45 DEGs? Main finding could be diagnostic AUC but no value in source. We should not false because number stated 45. Need parse wording \"the headline numerical result the paper states for its main finding.\" Which is 45 DEGs. The abstract source likely truncated actual AUCs and method counts. Their benchmark could expect false if target is AUC? Registered target generic. They likely extraction instruction target numerical result from source. Usually tasks ask to find headline numerical result main finding, and number stated is 45. We need ensure unit exact \"DEGs\" yes. Evidence contiguous full sentence. Could target_result \"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified.\" Parent 45. Could include key hubs. No invented source. JSON valid no code fences likely.\n\nNeed consider unit empty if no headline number? They say if no number for registered target false and what text states instead. Source states numerical result 45 DEGs. It's main finding discovery. Yes.\n\nWe should deliver only JSON object.</think>\n\n{\"parent_value\":45,\"unit\":\"DEGs\",\"evidence\":\"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\",\"target_result\":\"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\",\"number_stated\":true}", "reading": {"parent_value": 45, "unit": "DEGs", "evidence": "A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.", "target_result": "A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.", "number_stated": true, "source_locator": "chars 1031-1149 of source sha256 f45c60e81b4619b2d57eea50b6272aba1f4c3149a5e3080a3b39b14ad1e90e1c"}, "recorded_at": "2026-10-31T15:29:56.045369+00:00"}], "agreement": false, "disagreements": [], "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": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "reason": "a quoted statement is absent from the supplied text", "raw_response": "{\n  \"target_result\": \"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\",\n  \"work_type\": \"analysis_plus_physical_validation\",\n  \"physical_methods\": [\n    \"Immunohistochemistry\",\n    \"Grayscale quantification of stained tissue sections\",\n    \"Systematic sampling of minimum five sample points within identical regions of interest\"\n  ],\n  \"analysis_methods\": [\n    \"RNA sequencing\",\n    \"GEOquery\",\n    \"CIBERSORTx\",\n    \"CIBERSORT\",\n    \"limma differential expression analysis\",\n    \"Gene Ontology enrichment analysis\",\n    \"KEGG pathway enrichment analysis\",\n    \"clusterProfiler\",\n    \"STRING protein-protein interaction network analysis\",\n    \"Cytoscape sub-cluster analysis\",\n    \"Receiver operating characteristic analysis\",\n    \"Area under the curve estimation\",\n    \"Analysis of variance\",\n    \"Student's t-test\",\n    \"Pearson's correlation analysis\",\n    \"One-way ANOVA with post hoc Tukey's test\"\n  ],\n  \"statistical_method\": \"Differential expression analysis of immune-related genes was performed with the “limma” package.\",\n  \"method_evidence\": \"Differential expression analysis of immune-related genes was performed with the “limma” package.\",\n  \"repositories\": [\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE117606\",\n      \"data_description\": \"RNA sequencing data used to distinguish TSA from SSA.\",\n      \"evidence\": \"This study developed an immune molecule-based model to distinguish TSA from SSA using RNA sequencing data from the GEO datasets (GSE117606, GSE45270, GSE117607).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE45270\",\n      \"data_description\": \"RNA sequencing data used to distinguish TSA from SSA.\",\n      \"evidence\": \"This study developed an immune molecule-based model to distinguish TSA from SSA using RNA sequencing data from the GEO datasets (GSE117606, GSE45270, GSE117607).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE117607\",\n      \"data_description\": \"RNA sequencing data used to distinguish TSA from SSA.\",\n      \"evidence\": \"This study developed an immune molecule-based model to distinguish TSA from SSA using RNA sequencing data from the GEO datasets (GSE117606, GSE45270, GSE117607).\",\n      \"publicly_downloadable\": false\n    }\n  ],\n  \"availability_statement\": \"The paper identifies three GEO datasets, but the supplied text does not explicitly state whether the data can be downloaded without an application, embargo, or request, nor does it state that the data are available on request.\",\n  \"data_on_request\": false,\n  \"source_claims\": [\n    \"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\",\n    \"Their diagnostic potential was validated through receiver operating characteristic analysis in GEO datasets and clinical samples, while immunohistochemistry revealed decreased expression of CCL2 and CXCL11 in SSA compared to TSA and normal tissues, indicating their role in SSA pathogenesis and potential as molecular diagnostic markers.\",\n    \"The diagnostic value of CCL2 is superior to that of CXCL11, while the diagnostic value of CXCL11 requires further experimental verification.\",\n    \"CCL2 is highly promising as a potential diagnostic model for SSA and TSA; the potential diagnostic value of CXCL11 needs to be further verified.\",\n    \"The diagnostic value of gene expression in patients with SSAs was analyzed using receiver operating characteristic (ROC) curves, with the area under curve (AUC) being used to estimate the diagnostic value.\"\n  ],\n  \"missing_information\": [\n    \"No numerical AUC, sensitivity, specificity, confidence interval, or other numerical diagnostic-performance result is provided.\",\n    \"The paper does not provide a numerical headline result for the comparative diagnostic performance of CCL2 versus CXCL11.\",\n    \"The supplied text does not explicitly describe the public download conditions for the GEO datasets.\",\n    \"The supplied text does not state that any data are available on request.\"\n  ],\n  \"evidence_spans\": [\n    \"This study developed an immune molecule-based model to distinguish TSA from SSA using RNA sequencing data from the GEO datasets (GSE117606, GSE45270, GSE117607).\",\n    \"Differential expression analysis of immune-related genes was performed with the “limma” package.\",\n    \"A total of 45 DEGs (34 upregulated, 11 downregulated) were identified, with CCL2 and CXCL11 emerging as key hub genes.\",\n    \"Their diagnostic potential was validated through receiver operating characteristic analysis in GEO datasets and clinical samples, while immunohistochemistry revealed decreased expression of CCL2 and CXCL11 in SSA compared to TSA and normal tissues, indicating their role in SSA pathogenesis and potential as molecular diagnostic markers.\",\n    \"The diagnostic value of CCL2 is superior to that of CXCL11, while the diagnostic value of CXCL11 requires further experimental verification.\",\n    \"The diagnostic value of gene expression in patients with SSAs was analyzed using receiver operating characteristic (ROC) curves, with the area under curve (AUC) being used to estimate the diagnostic value.\",\n    \"Statistical comparison: Intergroup comparisons were conducted using one-way ANOVA with post hoc Tukey’s test. P-value <0.05 was considered statistically significant.\"\n  ]\n}"}]}}, {"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:6010d727f0d2313c701d9c97758875179d260c21911b2ff472618dce3575918a", "type": "sep_package", "label": "SEP v1 package for pmid:40822974"}], "activities": [{"id": "activity:conversion:pmid:40822974", "type": "conversion", "used": ["package:6010d727f0d2313c701d9c97758875179d260c21911b2ff472618dce3575918a"], "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:40822974", "parent_hash": "sha256:abf88830f9d30bbd9973a5580670171f57011ff6f44c6b68242613004ce9c418", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40822974 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:40822974' 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":"2026-11-04T02:53:13+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}}}