{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DMCSAJLDO6JM23ROOHIRGBBG67","short_pith_number":"pith:DMCSAJLD","schema_version":"1.0","canonical_sha256":"1b052025637792cd6e2e71d1130426f7fe5bde8879f564d704c0b9aaa617b58f","source":{"kind":"arxiv","id":"2412.00020","version":1},"attestation_state":"computed","paper":{"title":"Partitioning Message Passing for Graph Fraud Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.AI","authors_text":"Bingsheng He, Bryan Hooi, Guang Tan, Jia Chen, Rizal Fathony, Wei Zhuo, Zemin Liu","submitted_at":"2024-11-16T11:30:53Z","abstract_excerpt":"Label imbalance and homophily-heterophily mixture are the fundamental problems encountered when applying Graph Neural Networks (GNNs) to Graph Fraud Detection (GFD) tasks. Existing GNN-based GFD models are designed to augment graph structure to accommodate the inductive bias of GNNs towards homophily, by excluding heterophilic neighbors during message passing. In our work, we argue that the key to applying GNNs for GFD is not to exclude but to {\\em distinguish} neighbors with different labels. Grounded in this perspective, we introduce Partitioning Message Passing (PMP), an intuitive yet effec"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.00020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-16T11:30:53Z","cross_cats_sorted":["cs.LG","cs.SI"],"title_canon_sha256":"400f7fd1861066cb734298ab9f96903a7e79dac3b4b11b8dc5174696fc151f5c","abstract_canon_sha256":"4b705083056637552bc0fe89e642587a4ee13725b50dfa90f48b9d2b9e4c494c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:34.740683Z","signature_b64":"0+fbnrqRQ4GMDTP4VM2/n6AqcKTWJTYjUmkofj2bwRLpBAYVxyzCpny3h4Kjz0+sV85JJ2ijkx+9xLyDVvJeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b052025637792cd6e2e71d1130426f7fe5bde8879f564d704c0b9aaa617b58f","last_reissued_at":"2026-07-05T09:42:34.740143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:34.740143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partitioning Message Passing for Graph Fraud Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SI"],"primary_cat":"cs.AI","authors_text":"Bingsheng He, Bryan Hooi, Guang Tan, Jia Chen, Rizal Fathony, Wei Zhuo, Zemin Liu","submitted_at":"2024-11-16T11:30:53Z","abstract_excerpt":"Label imbalance and homophily-heterophily mixture are the fundamental problems encountered when applying Graph Neural Networks (GNNs) to Graph Fraud Detection (GFD) tasks. Existing GNN-based GFD models are designed to augment graph structure to accommodate the inductive bias of GNNs towards homophily, by excluding heterophilic neighbors during message passing. In our work, we argue that the key to applying GNNs for GFD is not to exclude but to {\\em distinguish} neighbors with different labels. Grounded in this perspective, we introduce Partitioning Message Passing (PMP), an intuitive yet effec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00020","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.00020/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.00020","created_at":"2026-07-05T09:42:34.740203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00020v1","created_at":"2026-07-05T09:42:34.740203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00020","created_at":"2026-07-05T09:42:34.740203+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMCSAJLDO6JM","created_at":"2026-07-05T09:42:34.740203+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMCSAJLDO6JM23RO","created_at":"2026-07-05T09:42:34.740203+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMCSAJLD","created_at":"2026-07-05T09:42:34.740203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30009","citing_title":"Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26040","citing_title":"L2IR: Revealing Latent Intent in Graph Fraud Detection","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29526","citing_title":"Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11749","citing_title":"Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detection","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12329","citing_title":"UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67","json":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67.json","graph_json":"https://pith.science/api/pith-number/DMCSAJLDO6JM23ROOHIRGBBG67/graph.json","events_json":"https://pith.science/api/pith-number/DMCSAJLDO6JM23ROOHIRGBBG67/events.json","paper":"https://pith.science/paper/DMCSAJLD"},"agent_actions":{"view_html":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67","download_json":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67.json","view_paper":"https://pith.science/paper/DMCSAJLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00020&json=true","fetch_graph":"https://pith.science/api/pith-number/DMCSAJLDO6JM23ROOHIRGBBG67/graph.json","fetch_events":"https://pith.science/api/pith-number/DMCSAJLDO6JM23ROOHIRGBBG67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67/action/storage_attestation","attest_author":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67/action/author_attestation","sign_citation":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67/action/citation_signature","submit_replication":"https://pith.science/pith/DMCSAJLDO6JM23ROOHIRGBBG67/action/replication_record"}},"created_at":"2026-07-05T09:42:34.740203+00:00","updated_at":"2026-07-05T09:42:34.740203+00:00"}