{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UVEZQUFJAT5TC73UWFPOAEGV3G","short_pith_number":"pith:UVEZQUFJ","canonical_record":{"source":{"id":"2605.12782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:52:24Z","cross_cats_sorted":[],"title_canon_sha256":"b9ecab29fa58d4af76737e05eeb0a04e8196f20494e9ca4ac9dc4dd96ba1f886","abstract_canon_sha256":"4aed37072389e5aa6d4416af3113d46209b89f2529568b41dc2eee7c807be123"},"schema_version":"1.0"},"canonical_sha256":"a5499850a904fb317f74b15ee010d5d9bc65b4332180b87de5be37da05c01237","source":{"kind":"arxiv","id":"2605.12782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12782","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12782v1","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12782","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"UVEZQUFJAT5T","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UVEZQUFJAT5TC73U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UVEZQUFJ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UVEZQUFJAT5TC73UWFPOAEGV3G","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:52:24Z","cross_cats_sorted":[],"title_canon_sha256":"b9ecab29fa58d4af76737e05eeb0a04e8196f20494e9ca4ac9dc4dd96ba1f886","abstract_canon_sha256":"4aed37072389e5aa6d4416af3113d46209b89f2529568b41dc2eee7c807be123"},"schema_version":"1.0"},"canonical_sha256":"a5499850a904fb317f74b15ee010d5d9bc65b4332180b87de5be37da05c01237","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:13.127609Z","signature_b64":"Ok5aDpgWGEgc4PzUxcmz3DJB80K9JELC1DKiFB/6PdlB+79HT75lgPS3LUmSr1vzTnazaKovisISAcy6CDXCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5499850a904fb317f74b15ee010d5d9bc65b4332180b87de5be37da05c01237","last_reissued_at":"2026-05-18T03:09:13.126929Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:13.126929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12782","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2AIDHYqn6n5f04idFwnB3WTW5xW0QEyyJGaBWy6qAQLCxpLMrTKtDo1cHGQDqiHKy3FJB483w6eUdXW33E79Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:41:01.472471Z"},"content_sha256":"77092858f8a7946bd8a761702507028fb7183253451cd02bf7ed25a28842a33a","schema_version":"1.0","event_id":"sha256:77092858f8a7946bd8a761702507028fb7183253451cd02bf7ed25a28842a33a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UVEZQUFJAT5TC73UWFPOAEGV3G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Graph neural networks that model transaction relationships improve fraud risk ranking and probability calibration.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiawei Wang, Ruobing Yan, Yilun Wu, Yuhan Wang, Yunfei Nie, Zouxiaowei Ma","submitted_at":"2026-05-12T21:52:24Z","abstract_excerpt":"Financial transaction fraud prevention faces challenges such as complex relationship structures, concealed behavioral patterns, and dynamically changing data distribution. Discrimination models relying solely on independent sample features are insufficient to fully characterize the risks of group collaboration and chain transfers within transaction networks. This paper proposes a graph neural network representation learning and risk discrimination framework for financial transaction fraud prevention. It integrates transaction records and identity information into node attributes and constructs"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The proposed method outperforms other methods in risk ranking and probability calibration quality, validating the effectiveness of graph structure modeling and representation learning collaboration in financial transaction fraud prevention.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the transaction graph constructed from shared attributes and interaction consistency accurately captures real inter-transaction relationships without introducing substantial noise or selection bias that affects fraud patterns.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A graph neural network model for financial fraud detection that incorporates transaction graphs, message passing, weighted supervision, and structural regularization outperforms baselines in risk ranking and probability calibration on a public dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Graph neural networks that model transaction relationships improve fraud risk ranking and probability calibration.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6621f5cf26febf4544be875db181be1b41b4d55b635fbdf9031677c087f8f570"},"source":{"id":"2605.12782","kind":"arxiv","version":1},"verdict":{"id":"b1b59836-8101-4ced-a86d-a3ec318e5f4e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:39:31.263761Z","strongest_claim":"The proposed method outperforms other methods in risk ranking and probability calibration quality, validating the effectiveness of graph structure modeling and representation learning collaboration in financial transaction fraud prevention.","one_line_summary":"A graph neural network model for financial fraud detection that incorporates transaction graphs, message passing, weighted supervision, and structural regularization outperforms baselines in risk ranking and probability calibration on a public dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the transaction graph constructed from shared attributes and interaction consistency accurately captures real inter-transaction relationships without introducing substantial noise or selection bias that affects fraud patterns.","pith_extraction_headline":"Graph neural networks that model transaction relationships improve fraud risk ranking and probability calibration."},"references":{"count":2,"sample":[{"doi":"","year":2022,"title":"bib2\"><number>[2]</number>Tian Y, Liu G. Transaction fraud detection via spatial-temporal-aware graph transformer[J]. arXiv preprint arXiv:2307.05121, 2023.</bib> <bib id=","work_id":"b51b53b6-5bcc-4ac1-9bb7-8771e5f6feea","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"ASA-GNN: Adaptive sampling and aggregation-based graph neural network for transaction fraud detection[J]","work_id":"64f541e9-be2f-46a5-b9eb-4474cb39f706","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":2,"snapshot_sha256":"65d0a2ab78af6b6d571f7e846c19eac0209258c5c5c05216cb852ec9a64e6cda","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"},"verdict_id":"b1b59836-8101-4ced-a86d-a3ec318e5f4e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QUcV/rBbGAWd67/WxZKAQcZyeXlu0qUPAdAp/PDaIdCvL04gOrnWo+ZXpKoUe7HAu1DuL+XTDTEr+PN2Kv1FDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:41:01.473428Z"},"content_sha256":"582a0b84fedada6261b2ad04aa67babcbdce74618c24aa1e65cda7e5e1aee470","schema_version":"1.0","event_id":"sha256:582a0b84fedada6261b2ad04aa67babcbdce74618c24aa1e65cda7e5e1aee470"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVEZQUFJAT5TC73UWFPOAEGV3G/bundle.json","state_url":"https://pith.science/pith/UVEZQUFJAT5TC73UWFPOAEGV3G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVEZQUFJAT5TC73UWFPOAEGV3G/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T03:41:01Z","links":{"resolver":"https://pith.science/pith/UVEZQUFJAT5TC73UWFPOAEGV3G","bundle":"https://pith.science/pith/UVEZQUFJAT5TC73UWFPOAEGV3G/bundle.json","state":"https://pith.science/pith/UVEZQUFJAT5TC73UWFPOAEGV3G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVEZQUFJAT5TC73UWFPOAEGV3G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UVEZQUFJAT5TC73UWFPOAEGV3G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4aed37072389e5aa6d4416af3113d46209b89f2529568b41dc2eee7c807be123","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:52:24Z","title_canon_sha256":"b9ecab29fa58d4af76737e05eeb0a04e8196f20494e9ca4ac9dc4dd96ba1f886"},"schema_version":"1.0","source":{"id":"2605.12782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12782","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12782v1","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12782","created_at":"2026-05-18T03:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"UVEZQUFJAT5T","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UVEZQUFJAT5TC73U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UVEZQUFJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:582a0b84fedada6261b2ad04aa67babcbdce74618c24aa1e65cda7e5e1aee470","target":"graph","created_at":"2026-05-18T03:09:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The proposed method outperforms other methods in risk ranking and probability calibration quality, validating the effectiveness of graph structure modeling and representation learning collaboration in financial transaction fraud prevention."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the transaction graph constructed from shared attributes and interaction consistency accurately captures real inter-transaction relationships without introducing substantial noise or selection bias that affects fraud patterns."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A graph neural network model for financial fraud detection that incorporates transaction graphs, message passing, weighted supervision, and structural regularization outperforms baselines in risk ranking and probability calibration on a public dataset."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Graph neural networks that model transaction relationships improve fraud risk ranking and probability calibration."}],"snapshot_sha256":"6621f5cf26febf4544be875db181be1b41b4d55b635fbdf9031677c087f8f570"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Financial transaction fraud prevention faces challenges such as complex relationship structures, concealed behavioral patterns, and dynamically changing data distribution. Discrimination models relying solely on independent sample features are insufficient to fully characterize the risks of group collaboration and chain transfers within transaction networks. This paper proposes a graph neural network representation learning and risk discrimination framework for financial transaction fraud prevention. It integrates transaction records and identity information into node attributes and constructs","authors_text":"Jiawei Wang, Ruobing Yan, Yilun Wu, Yuhan Wang, Yunfei Nie, Zouxiaowei Ma","cross_cats":[],"headline":"Graph neural networks that model transaction relationships improve fraud risk ranking and probability calibration.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:52:24Z","title":"Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization"},"references":{"count":2,"internal_anchors":0,"resolved_work":2,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"bib2\"><number>[2]</number>Tian Y, Liu G. Transaction fraud detection via spatial-temporal-aware graph transformer[J]. arXiv preprint arXiv:2307.05121, 2023.</bib> <bib id=","work_id":"b51b53b6-5bcc-4ac1-9bb7-8771e5f6feea","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"ASA-GNN: Adaptive sampling and aggregation-based graph neural network for transaction fraud detection[J]","work_id":"64f541e9-be2f-46a5-b9eb-4474cb39f706","year":2021}],"snapshot_sha256":"65d0a2ab78af6b6d571f7e846c19eac0209258c5c5c05216cb852ec9a64e6cda"},"source":{"id":"2605.12782","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:39:31.263761Z","id":"b1b59836-8101-4ced-a86d-a3ec318e5f4e","model_set":{"reader":"grok-4.3"},"one_line_summary":"A graph neural network model for financial fraud detection that incorporates transaction graphs, message passing, weighted supervision, and structural regularization outperforms baselines in risk ranking and probability calibration on a public dataset.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Graph neural networks that model transaction relationships improve fraud risk ranking and probability calibration.","strongest_claim":"The proposed method outperforms other methods in risk ranking and probability calibration quality, validating the effectiveness of graph structure modeling and representation learning collaboration in financial transaction fraud prevention.","weakest_assumption":"That the transaction graph constructed from shared attributes and interaction consistency accurately captures real inter-transaction relationships without introducing substantial noise or selection bias that affects fraud patterns."}},"verdict_id":"b1b59836-8101-4ced-a86d-a3ec318e5f4e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:77092858f8a7946bd8a761702507028fb7183253451cd02bf7ed25a28842a33a","target":"record","created_at":"2026-05-18T03:09:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4aed37072389e5aa6d4416af3113d46209b89f2529568b41dc2eee7c807be123","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T21:52:24Z","title_canon_sha256":"b9ecab29fa58d4af76737e05eeb0a04e8196f20494e9ca4ac9dc4dd96ba1f886"},"schema_version":"1.0","source":{"id":"2605.12782","kind":"arxiv","version":1}},"canonical_sha256":"a5499850a904fb317f74b15ee010d5d9bc65b4332180b87de5be37da05c01237","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5499850a904fb317f74b15ee010d5d9bc65b4332180b87de5be37da05c01237","first_computed_at":"2026-05-18T03:09:13.126929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:13.126929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ok5aDpgWGEgc4PzUxcmz3DJB80K9JELC1DKiFB/6PdlB+79HT75lgPS3LUmSr1vzTnazaKovisISAcy6CDXCCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:13.127609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77092858f8a7946bd8a761702507028fb7183253451cd02bf7ed25a28842a33a","sha256:582a0b84fedada6261b2ad04aa67babcbdce74618c24aa1e65cda7e5e1aee470"],"state_sha256":"80db1b4604e12bdeacb00909364591c9b2d7709cb162d719ccfc880d50668e7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PVCMOks068ALiySddbsjVOdLd7YEigilnR0GCEPhi/NU16ufLXuktotfDimmvoUOBSNDMb7ASBreIjrzgr+GAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:41:01.477394Z","bundle_sha256":"3aa3546fb0cdda216e47c3c86f95224812ee5aa5a81ccd093ed074e62e4b97f1"}}