{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.15177", "kind": "paper", "url": "https://arxiv.org/abs/2608.15177"}, {"kind": "website", "url": "https://anonymous.4open.science/r/FinFraudBench-B002"}], "authors": ["Yixuan Chen", "Hongyu Zhan", "Jie Sheng", "Weiyu Han", "Shuai Chen", "Tianyi Zhang", "Xiao Tan", "Jun Xia"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.15177", "source_url": "https://arxiv.org/abs/2608.15177"}, "categories": ["Finance", "Vision & 3D", "cs.LG"], "description": {"en": "FinFraudBench is a heterogeneous graph benchmark for financial fraud detection. It contains two datasets (CreditCard-Fraud and BankTrans-Fraud) with up to 8.99M nodes and 89.23M directed typed edges, preserving six financial entity types and fourteen edge types. The evaluation protocol covers ranking and imbalance-sensitive classification metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.15177", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.15177", "title": "FinFraudBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Jilin University", "Ant Group (China)", "Hong Kong University of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.15177", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.15177", "source_url": "https://openalex.org/W7203720923"}, "key": "claire-radar:2608.15177", "modality": null, "name": "FinFraudBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_finfraudbench_fc16410f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ae8c46498206a3b3573e1e5cfd356fb3784cd7cb0006dd216ae3a509bea51b9d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.15177"}, "publisher": null, "released": "2026-08-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.15177", "source_url": "https://arxiv.org/abs/2608.15177"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-15177", "source": "claire_radar", "source_benchmark_id": "2608.15177", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.15177", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "2c048e1de37db1a521f9da04691dc7aa1f62ad85fa6d9d6255a3cf86e4592c1c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FinFraudBench is a heterogeneous graph benchmark for financial fraud detection. It contains two datasets (CreditCard-Fraud and BankTrans-Fraud) with up to 8.99M nodes and 89.23M directed typed edges, preserving six financial entity types and fourteen edge types. The evaluation protocol covers ranking and imbalance-sensitive classification metrics.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address these gaps, we present FinFraudBench, a heterogeneous graph benchmark for financial fraud detection."}, "familyId": "bmf_8a9ae6e0eb11", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_finfraudbench_fc16410f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.15177", "paper": "https://arxiv.org/abs/2608.15177", "pdf": "https://arxiv.org/pdf/2608.15177", "project": "https://anonymous.4open.science/r/FinFraudBench-B002", "report": "https://arxiv.org/abs/2608.15177"}, "metrics": [], "motivation": "The increasing complexity of digital financial systems has reshaped financial fraud detection from isolated transaction classification into relational risk reasoning over interconnected financial entities.", "name": "FinFraudBench", "oneLine": "FinFraudBench is a heterogeneous graph benchmark for financial fraud detection. It contains two datasets (CreditCard-Fraud and BankTrans-Fraud) with up to 8.99M nodes and 89.23M directed typed edges, preserving six financial entity types and fourteen edge types. The evaluation protocol covers ranking and imbalance-sensitive classification metrics.", "paperTitle": "FinFraudBench: A Heterogeneous Graph Benchmark for Financial Fraud Detection", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.15177", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "FinFraudBench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://anonymous.4open.science/r/FinFraudBench-B002"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-15", "source": {"authors": ["Yixuan Chen", "Hongyu Zhan", "Jie Sheng", "Weiyu Han", "Shuai Chen", "Tianyi Zhang", "Xiao Tan", "Jun Xia"], "categories": ["cs.LG", "cs.AI"], "id": "2608.15177", "title": "FinFraudBench: A Heterogeneous Graph Benchmark for Financial Fraud Detection", "type": "arxiv", "url": "https://arxiv.org/abs/2608.15177"}, "sourceUpdatedAt": "2026-08-15T11:34:51Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Existing graph-based fraud detection benchmarks often oversimplify financial systems and lack realistic conditions. FinFraudBench provides large-scale heterogeneous graphs with natural fraud rates, enabling more realistic evaluation of fraud detection methods and comparison across models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
