{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M5NOE5V7YPCYJAHTVAKIQ46DZ2","short_pith_number":"pith:M5NOE5V7","schema_version":"1.0","canonical_sha256":"675ae276bfc3c58480f3a8148873c3ce8f6e60670a20a5e8e4586abd98840d74","source":{"kind":"arxiv","id":"2501.00826","version":3},"attestation_state":"computed","paper":{"title":"LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-fin.TR","authors_text":"Jiahua Xu, Paolo Tasca, Yang Liu, Yebo Feng, Yichen Luo","submitted_at":"2025-01-01T13:08:17Z","abstract_excerpt":"Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the breadth of modality-specific inputs needed for robust decision-making. We propose a multi-agent system (MAS) framework in which three modality-specialised agents, a Crypto Agent for mar"},"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":"2501.00826","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.TR","submitted_at":"2025-01-01T13:08:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"69a67c6836cdb79aa46ad4351ac576f439427493bc925bb7beff36ba12b033f2","abstract_canon_sha256":"e38e6dc9af49b36d59b20680495822b2546a72b1228b3a96d3e31484c396447f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:29.149042Z","signature_b64":"eK7c2XNTx+QuieM1rTP0xdwlpEAP7C6FCo1YR/GXyGS67ni8kgqe7UChsbaj/Yknw932zo/KYKKbqzvWuyknCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675ae276bfc3c58480f3a8148873c3ce8f6e60670a20a5e8e4586abd98840d74","last_reissued_at":"2026-06-19T16:10:29.148620Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:29.148620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-fin.TR","authors_text":"Jiahua Xu, Paolo Tasca, Yang Liu, Yebo Feng, Yichen Luo","submitted_at":"2025-01-01T13:08:17Z","abstract_excerpt":"Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the breadth of modality-specific inputs needed for robust decision-making. We propose a multi-agent system (MAS) framework in which three modality-specialised agents, a Crypto Agent for mar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00826","kind":"arxiv","version":3},"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/2501.00826/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":"2501.00826","created_at":"2026-06-19T16:10:29.148675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00826v3","created_at":"2026-06-19T16:10:29.148675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00826","created_at":"2026-06-19T16:10:29.148675+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5NOE5V7YPCY","created_at":"2026-06-19T16:10:29.148675+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5NOE5V7YPCYJAHT","created_at":"2026-06-19T16:10:29.148675+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5NOE5V7","created_at":"2026-06-19T16:10:29.148675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.26235","citing_title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12632","citing_title":"Calibration-Aware Policy Optimization for Reasoning LLMs","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15367","citing_title":"SoK: Security of Autonomous LLM Agents in Agentic Commerce","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2","json":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2.json","graph_json":"https://pith.science/api/pith-number/M5NOE5V7YPCYJAHTVAKIQ46DZ2/graph.json","events_json":"https://pith.science/api/pith-number/M5NOE5V7YPCYJAHTVAKIQ46DZ2/events.json","paper":"https://pith.science/paper/M5NOE5V7"},"agent_actions":{"view_html":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2","download_json":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2.json","view_paper":"https://pith.science/paper/M5NOE5V7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00826&json=true","fetch_graph":"https://pith.science/api/pith-number/M5NOE5V7YPCYJAHTVAKIQ46DZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/M5NOE5V7YPCYJAHTVAKIQ46DZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2/action/storage_attestation","attest_author":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2/action/author_attestation","sign_citation":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2/action/citation_signature","submit_replication":"https://pith.science/pith/M5NOE5V7YPCYJAHTVAKIQ46DZ2/action/replication_record"}},"created_at":"2026-06-19T16:10:29.148675+00:00","updated_at":"2026-06-19T16:10:29.148675+00:00"}