{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IRROIFYJ2LORWDJ7JF3VRRSWZC","short_pith_number":"pith:IRROIFYJ","schema_version":"1.0","canonical_sha256":"4462e41709d2dd1b0d3f497758c656c8b0d30d25da0946b651fe6877b7e98d23","source":{"kind":"arxiv","id":"2510.17848","version":2},"attestation_state":"computed","paper":{"title":"RISKTAGGER: Evidence-Guided LLM Agent for Post-Incident Forensic Analysis of Money Laundering in Web3","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CR","authors_text":"Dan Lin, Jiachi Chen, Jiajing Wu, Weipeng Zou, Xiapu Luo, Yanli Ding, Zhiyin Wu, Zibin Zheng","submitted_at":"2025-10-12T08:54:28Z","abstract_excerpt":"Cryptocurrency money-laundering forensic analysis after Web3 incidents faces challenges such as fragmented evidence, expanding transaction paths, and cross-chain discontinuity. Existing Web3 AML methods largely rely on manual clues and heuristic or graph-search-based tracing, with outputs limited to lists of suspicious addresses and lacking path-level evidence and verifiable explanations. Directly applying general-purpose large language models to raw transaction flows also struggles to ensure evidence constraints and result verifiability. To address these limitations, this paper presents RISKT"},"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":"2510.17848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-10-12T08:54:28Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"34ea0f0df3a33e7efeb59cd316150db819d48b4941eb8da381fb661096b97c39","abstract_canon_sha256":"5ffab7d8bd6ad35972093394ae929641df88e8972f67ab5a1f5dc8efcab1ada1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:20.256038Z","signature_b64":"vL9D/HbpOubBTgJcrTZWO/H6ofhJ2Gpk4fcPK/fHqc+0KYS73AFwezZXZlky36BXLkPqlGvBwOtuxjiuSuARAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4462e41709d2dd1b0d3f497758c656c8b0d30d25da0946b651fe6877b7e98d23","last_reissued_at":"2026-07-14T00:18:20.255102Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:20.255102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RISKTAGGER: Evidence-Guided LLM Agent for Post-Incident Forensic Analysis of Money Laundering in Web3","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CR","authors_text":"Dan Lin, Jiachi Chen, Jiajing Wu, Weipeng Zou, Xiapu Luo, Yanli Ding, Zhiyin Wu, Zibin Zheng","submitted_at":"2025-10-12T08:54:28Z","abstract_excerpt":"Cryptocurrency money-laundering forensic analysis after Web3 incidents faces challenges such as fragmented evidence, expanding transaction paths, and cross-chain discontinuity. Existing Web3 AML methods largely rely on manual clues and heuristic or graph-search-based tracing, with outputs limited to lists of suspicious addresses and lacking path-level evidence and verifiable explanations. Directly applying general-purpose large language models to raw transaction flows also struggles to ensure evidence constraints and result verifiability. To address these limitations, this paper presents RISKT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.17848","kind":"arxiv","version":2},"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/2510.17848/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":"2510.17848","created_at":"2026-07-14T00:18:20.255544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.17848v2","created_at":"2026-07-14T00:18:20.255544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.17848","created_at":"2026-07-14T00:18:20.255544+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRROIFYJ2LOR","created_at":"2026-07-14T00:18:20.255544+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRROIFYJ2LORWDJ7","created_at":"2026-07-14T00:18:20.255544+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRROIFYJ","created_at":"2026-07-14T00:18:20.255544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.12329","citing_title":"UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC","json":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC.json","graph_json":"https://pith.science/api/pith-number/IRROIFYJ2LORWDJ7JF3VRRSWZC/graph.json","events_json":"https://pith.science/api/pith-number/IRROIFYJ2LORWDJ7JF3VRRSWZC/events.json","paper":"https://pith.science/paper/IRROIFYJ"},"agent_actions":{"view_html":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC","download_json":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC.json","view_paper":"https://pith.science/paper/IRROIFYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.17848&json=true","fetch_graph":"https://pith.science/api/pith-number/IRROIFYJ2LORWDJ7JF3VRRSWZC/graph.json","fetch_events":"https://pith.science/api/pith-number/IRROIFYJ2LORWDJ7JF3VRRSWZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC/action/storage_attestation","attest_author":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC/action/author_attestation","sign_citation":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC/action/citation_signature","submit_replication":"https://pith.science/pith/IRROIFYJ2LORWDJ7JF3VRRSWZC/action/replication_record"}},"created_at":"2026-07-14T00:18:20.255544+00:00","updated_at":"2026-07-14T00:18:20.255544+00:00"}