{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40722520", "kind": "science-record", "revision": 2, "content_hash": "sha256:61b1b645930befa37ab07f9279c72a88e4154251b998bb8d67a619a68e45522e", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T14:01:45Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integrated Meta-Analysis Identifies Keratin Family Genes and Associated Genes as Key Biomarkers and Therapeutic Targets in Metastatic Cutaneous Melanoma.", "doi": "10.3390/diagnostics15141770", "pmid": "40722520", "authors": null, "journal": "Diagnostics (Basel, Switzerland)", "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": 11.0, "unit": "hub genes", "tolerance": null, "source": "chars 11258-11503 of source sha256 dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76"}, "evidence": [{"asset": "source:pmid:40722520", "locator": "chars 11258-11503 of source sha256 dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76", "quote": "In this study, through extensive bioinformatics and meta-analysis, we identified 80 DEGs associated with the transition from primary melanoma to metastatic cutaneous melanoma, revealing 11 potential melanoma-associated hub genes—mostly keratins."}]}], "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:40722520"], "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:40722520", "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:40722520' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40722520", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/diagnostics15141770", "sha256": "sha256:dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/diagnostics15141770", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40722520:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:80145a203e3d792db1e898dfb2c6ebc63b7a4a09dc9ebdbb12788a11e4704b5e", "bytes": 624, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#diagnostics-15-01770-t001", "version": null, "note": "Core attributes of the four datasets considered in the integrated metastatic melanoma meta-analysis.", "structure": {"pmcid": "PMC12293645", "section_index": 3, "section_title": "2.1. Data Selection and Preprocessing (Inclusion-Exclusion Criteria)", "row_count": 6, "column_count": 4}, "table": {"label": "Table 1", "caption": "Core attributes of the four datasets considered in the integrated metastatic melanoma meta-analysis.", "rows": [["", "", "Melanoma"], ["GEO Name", "Platform", "Primary", "Metastatic"], ["GSE7553 [23]", "GPL570 (Affymetrix Human Genome U133 Plus 2.0)", "46", "12"], ["GSE15605 [24]", "GPL570 (Affymetrix Human Genome U133 Plus 2.0)", "31", "52"], ["GSE46517 [25]", "GPL96 (Affymetrix Human Genome U133A)", "31", "73"], ["GSE8401 [26]", "GPL96 (Affymetrix Human Genome U133A)", "14", "40"]], "row_count": 6, "column_count": 4, "numeric_cells": 16, "header_rows": 1, "locator": "section[3]/table-wrap[1]#diagnostics-15-01770-t001"}}, {"id": "asset:table:pmid:40722520:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6be9104163ad77e8612181469996a52f261c1a5f1661f99dec38df8d0571e082", "bytes": 1077, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#diagnostics-15-01770-t002", "version": null, "note": "Summary of drug–gene interactions retrieved from DGIdb database for the identified hub genes in melanoma metastasis.", "structure": {"pmcid": "PMC12293645", "section_index": 19, "section_title": "3.7. Drug-Gene Network Analysis", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Summary of drug–gene interactions retrieved from DGIdb database for the identified hub genes in melanoma metastasis.", "rows": [["Gene", "Drug", "Approval Status", "Indication", "Interaction Score"], ["PI3", "PROGESTERONE", "Approved", "Pre-term birth risk reduction", "1.77"], ["KRT10", "EPIDERMAL GROWTH FACTOR", "Not Approved", "Not available", "11.60"], ["DSP", "COMPOUND 66 [PMID: 19788238]", "Not Approved", "Not available", "1.58"], ["DSP", "ENALAPRIL MALEATE", "Approved", "Antihypertensive agent", "1.83"], ["DSP", "NINTEDANIB ESYLATE", "Approved", "Antineoplastic agent", "1.39"], ["CDH1", "FOSBRETABULIN TROMETHAMINE", "Not Approved", "Not available", "13.05"], ["CDH1", "ANTISERUM", "Not Approved", "Not available", "0.75"], ["CDH1", "BICALUTAMIDE", "Approved", "Antineoplastic agent", "1.31"], ["CDH1", "PANCREATIC PROTEOLYTIC ENZYMES", "Not Approved", "Not available", "6.53"], ["FLG", "PROPIONIBACTERIUM ACNES", "Not Approved", "Not available", "52.20"]], "row_count": 11, "column_count": 5, "numeric_cells": 12, "header_rows": 1, "locator": "section[19]/table-wrap[1]#diagnostics-15-01770-t002"}}, {"id": "asset:table:pmid:40722520:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:16e6951e1f1b42a887882817fcec7e6593df7114fa2299e9cf08ad9d50a76c2e", "bytes": 790, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[2]#diagnostics-15-01770-t003", "version": null, "note": "Structural druggability evaluation of hub genes using the AlphaFold-predicted structures and ProteinPlus (DoGSiteScorer). A druggability score above 0.6 indicates high-confidence targets for structure-based drug design.", "structure": {"pmcid": "PMC12293645", "section_index": 19, "section_title": "3.7. Drug-Gene Network Analysis", "row_count": 12, "column_count": 4}, "table": {"label": "Table 3", "caption": "Structural druggability evaluation of hub genes using the AlphaFold-predicted structures and ProteinPlus (DoGSiteScorer). A druggability score above 0.6 indicates high-confidence targets for structure-based drug design.", "rows": [["Pockets", "Gene", "Druggability_Score", "Volume"], ["P 0", "CDH1", "0.80", "1903.56"], ["P 0", "DSP", "0.82", "792.39"], ["P 0", "FLG", "0.80", "3880.47"], ["P 0", "PI3", "0.84", "760.04"], ["P 0", "S100A7", "0.76", "615.68"], ["P 0", "SPRR1B", "0.26", "109.65"], ["P 0", "KRT5", "0.58", "113.20"], ["P 0", "KRT6A", "0.71", "374.28"], ["P 0", "KRT6B", "0.78", "1058.92"], ["P 0", "KRT10", "0.60", "396.39"], ["P 0", "KRT16", "0.80", "1059.57"]], "row_count": 12, "column_count": 4, "numeric_cells": 36, "header_rows": 1, "locator": "section[19]/table-wrap[2]#diagnostics-15-01770-t003"}}], "gaps": ["asset:source:pmid:40722520 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:40722520", "asset:table:pmid:40722520:1", "asset:table:pmid:40722520:2", "asset:table:pmid:40722520:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40722520"]}, "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": "df6b3e3ae9cdd5f9822f3dad278730a009ccf12802644eb5bdedf626484786e6", "source_hash": "dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76", "raw_response_sha256": "sha256:e6961ad2fb560514b8104dc966617b689d68ef57b2f481cc6627d917076e16f1", "raw_response_chars": 6560}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "6cedba3ca86f49a3f90c6036ae1eb0b8a96dd7773f30df9302c6bb6d4b116573", "source_hash": "dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76", "raw_response_sha256": "sha256:215347f38b78b9935e7719866062d0339b0fad547188e82b13a3fab97892a941", "raw_response_chars": 78514}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "326482fd7976894edeef5c48ceabcb9644218f4fe3bd770aca8cfc208c4b97d9", "source_hash": "dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76", "raw_response": "{\"parent_value\":11,\"unit\":\"hub genes\",\"evidence\":\"In this study, through extensive bioinformatics and meta-analysis, we identified 80 DEGs associated with the transition from primary melanoma to metastatic cutaneous melanoma, revealing 11 potential melanoma-associated hub genes—mostly keratins.\",\"target_result\":\"The paper identifies 11 potential melanoma-associated hub genes, mostly keratins.\",\"number_stated\":true}", "reading": {"parent_value": 11, "unit": "hub genes", "evidence": "In this study, through extensive bioinformatics and meta-analysis, we identified 80 DEGs associated with the transition from primary melanoma to metastatic cutaneous melanoma, revealing 11 potential melanoma-associated hub genes—mostly keratins.", "target_result": "The paper identifies 11 potential melanoma-associated hub genes, mostly keratins.", "number_stated": true, "source_locator": "chars 11258-11503 of source sha256 dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76"}, "recorded_at": "2026-10-31T15:23:33.960755+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "cfdad3c5debcb74a9384621708b8daf2bff87ea00d5cea573e0ea774dea63972", "source_hash": "dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76", "raw_response": "<think>We need answer JSON only. Need determine headline numerical result main finding. Registered target vague: \"the headline numerical result the paper states for its main finding.\" Need identify likely 11 hub genes? Main finding perhaps \"eleven hub genes\" / conclusion \"80 DEGs ... revealing 11 potential melanoma-associated hub genes—mostly keratins.\" User says single numerical result replication target reproduce, headline number only, value paper itself states for registered target, unit printed. Evidence exact contiguous quote containing number, attribution may attached target. Need parse likely expected parent_value=11, unit maybe \"hub genes\". Evidence quote exact clause from conclusions linking main finding and number: \"In this study, through extensive bioinformatics and meta-analysis, we identified 80 DEGs associated with the transition from primary melanoma to metastatic cutaneous melanoma, revealing 11 potential melanoma-associated hub genes—mostly keratins.\" Could quote whole clause because multiple numbers 80 and 11, attribution. Or abstract Results: \"We identified a total of eleven hub genes associated with melanoma progression.\" Number is word \"eleven\", but parent_value number, unit paper prints. Yet request numerical result, evidence contains number perhaps eleven spelled word. \"Report headline number only: value paper itself states... unit must be unit paper prints.\" Unit could be \"hub genes\". But parent_value schema number. Evidence exact quote contains the number. \"eleven\" counts as number perhaps. Headline likely 11 hub genes. Could quote abstract exact. But \"number\" perhaps numeric notation 11 in conclusion. Better evidence exact contiguous quote: \"In this study, through extensive bioinformatics and meta-analysis, we identified 80 DEGs associated with the transition from primary melanoma to metastatic cutaneous melanoma, revealing 11 potential melanoma-associated hub genes—mostly keratins.\" This has another number 80, but asks single numerical result and whole clause attribution. Could instead quote \"revealing 11 potential melanoma-associated hub genes—mostly keratins.\" Is that a clause and exact contiguous. It directly names target. They say headline number only likely parent_value 11, unit \"hub genes\". target_result maybe \"11 hub genes associated with melanoma progression\" or concise. Need perhaps unit string \"hub genes\". They want headline number only perhaps evidence etc.\n\nCould there be another headline result: 17/33 gene ratio for most enriched pathway? Main finding identified keratin family genes and associated genes biomarkers. Headline numerical result likely 11 hub genes. The prompt often target classification perhaps asks \"headline numerical result the paper states for its main finding\" designed ambiguous. Need extract main headline. Abstract says identified total of eleven hub genes associated progression. Conclusion reinforces 80 DEGs, 11 hub genes. Which is headline numerical result? The title/main finding is genes; number 11. \"headline numerical result\" likely \"11 hub genes.\" Need ensure unit printed exactly? Paper prints \"hub genes\" as unit. Maybe unit should be \"hub genes\" and parent_value 11. Evidence exact quote with numeral 11: conclusion exact sentence. target_result likely \"11 potential melanoma-associated hub genes\". Could state \"11 potential melanoma-associated hub genes—mostly keratins\". Number stated true.\n\nNeed only JSON. Ensure Unicode em dash okay. Evidence exact quote. Is quote whole clause? \"revealing 11 potential melanoma-associated hub genes—mostly keratins.\" exact contiguous yes. Does attribution clearly target? Yes. Could include \"In this study...\" but contains 80 competing headline. Better direct clause from conclusion. Unit paper prints? \"potential melanoma-associated hub genes\" perhaps unit. Usually unit is \"hub genes\". Prompt says unit must be unit paper prints. We should use \"hub genes\" exactly printed. parent_value 11.\n\nLet's formulate valid JSON.</think>\n\n{\"parent_value\":11,\"unit\":\"hub genes\",\"evidence\":\"revealing 11 potential melanoma-associated hub genes—mostly keratins.\",\"target_result\":\"11 potential melanoma-associated hub genes, mostly keratins\",\"number_stated\":true}", "reading": {"parent_value": 11, "unit": "hub genes", "evidence": "revealing 11 potential melanoma-associated hub genes—mostly keratins.", "target_result": "11 potential melanoma-associated hub genes, mostly keratins", "number_stated": true, "source_locator": "chars 11434-11503 of source sha256 dbe0cba1ae6a1453bdf78565aa1317752979d1d38c9b70efa05d9491e21dff76"}, "recorded_at": "2026-10-31T15:23:50.966796+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "The main finding was 80 metastasis-associated differentially expressed genes, with 11 potential melanoma-associated hub genes, mostly keratins.", "minimax_alt": "A total of eleven hub genes associated with melanoma progression, mostly members of the keratin gene family.", "decisive": false}, "analysis_methods": {"minimax": ["Integrated meta-analysis", "limma", "edgeR", "ComBat batch-effect correction", "RobustRankAggreg (RRA)", "DExMA", "Fisher’s method", "EPIC immune-cell deconvolution", "Spearman correlation", "GO/KEGG functional enrichment analysis", "Benjamini-Hochberg false discovery rate", "Protein-protein interaction network analysis", "Topological hub-gene identification using Betweenness, MCC, Degree, and Bottleneck", "TCGA-SKCM validation", "DGIdb drug-gene interaction analysis", "ProteinPlus and AlphaFold structural druggability analysis"], "minimax_alt": ["Quantile normalization and filtering of lowly expressed genes", "limma differential-expression analysis", "edgeR differential-expression analysis", "ComBat batch-effect correction", "RobustRankAggreg (RRA) using aggregateRanks", "DExMA metaAnalysisDE", "Fisher’s method for integrated meta-analysis", "Protein-protein interaction network construction", "Betweenness, MCC, Degree, and Bottleneck topological methods for hub-gene identification", "EPIC immune-cell deconvolution via immunedeconv", "Spearman correlation", "GO and KEGG enrichment analysis via clusterProfiler and enrichplot", "Benjamini-Hochberg false-discovery-rate correction", "TCGA-SKCM cohort validation", "DGIdb drug-gene interaction analysis", "Cytoscape drug-gene network construction", "AlphaFold protein-structure retrieval and ProteinPlus DogSiteScore druggability assessment"], "decisive": false}, "statistical_method": {"minimax": "Fisher’s method", "minimax_alt": "Hub-gene identification using four topological methods: Betweenness, MCC, Degree, and Bottleneck.", "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:19ad7947f7c6056d7fe8e380deed6d6d95d2e8f87141e58200bb13b1da46bcf5", "type": "sep_package", "label": "SEP v1 package for pmid:40722520"}], "activities": [{"id": "activity:conversion:pmid:40722520", "type": "conversion", "used": ["package:19ad7947f7c6056d7fe8e380deed6d6d95d2e8f87141e58200bb13b1da46bcf5"], "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:40722520", "parent_hash": "sha256:e7bf378b5f100e12433bd8907778511f40c458c568b9b1de67985496703a6815", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40722520 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:40722520' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:34:37+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}