{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F3G3GP55ZQP63K4JC2XGKC6527","short_pith_number":"pith:F3G3GP55","schema_version":"1.0","canonical_sha256":"2ecdb33fbdcc1fedab8916ae650bddd7f712ad19c80db83657b92df623499726","source":{"kind":"arxiv","id":"2509.24144","version":2},"attestation_state":"computed","paper":{"title":"From Headlines to Holdings: Deep Learning for Smarter Portfolio Decisions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-fin.CP","q-fin.ST","stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Jiawei Lou, Jinghe Zhang, Yun Lin","submitted_at":"2025-09-29T00:42:24Z","abstract_excerpt":"Deep learning offers new tools for portfolio optimization. We present an end-to-end framework that directly learns portfolio weights by combining Long Short-Term Memory (LSTM) networks to model temporal patterns, Graph Attention Networks (GAT) to capture evolving inter-stock relationships, and sentiment analysis of financial news to reflect market psychology. Unlike prior approaches, our model unifies these elements in a single pipeline that produces daily allocations. It avoids the traditional two-step process of forecasting asset returns and then applying mean--variance optimization (MVO), a"},"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":"2509.24144","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-fin.PM","submitted_at":"2025-09-29T00:42:24Z","cross_cats_sorted":["q-fin.CP","q-fin.ST","stat.ML"],"title_canon_sha256":"32d25a24925e90c17ee642f4bc51d1c4e982d4bbebf589378adad2b30720379c","abstract_canon_sha256":"d31f5305b166c5919dc090b297f47ff8d6c3ca50605efd57fe6d610567eaf99f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:51.278283Z","signature_b64":"lVXGUf7fVHShpTBRCNOzFI/exHxD6olB20AgyWot9wMzjlZs/leg8xfdZUtRr1/i70PeAW9eExf6rwACzBQUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ecdb33fbdcc1fedab8916ae650bddd7f712ad19c80db83657b92df623499726","last_reissued_at":"2026-05-27T01:04:51.277439Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:51.277439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Headlines to Holdings: Deep Learning for Smarter Portfolio Decisions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-fin.CP","q-fin.ST","stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Jiawei Lou, Jinghe Zhang, Yun Lin","submitted_at":"2025-09-29T00:42:24Z","abstract_excerpt":"Deep learning offers new tools for portfolio optimization. We present an end-to-end framework that directly learns portfolio weights by combining Long Short-Term Memory (LSTM) networks to model temporal patterns, Graph Attention Networks (GAT) to capture evolving inter-stock relationships, and sentiment analysis of financial news to reflect market psychology. Unlike prior approaches, our model unifies these elements in a single pipeline that produces daily allocations. It avoids the traditional two-step process of forecasting asset returns and then applying mean--variance optimization (MVO), a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24144","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/2509.24144/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":"2509.24144","created_at":"2026-05-27T01:04:51.277531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24144v2","created_at":"2026-05-27T01:04:51.277531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24144","created_at":"2026-05-27T01:04:51.277531+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3G3GP55ZQP6","created_at":"2026-05-27T01:04:51.277531+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3G3GP55ZQP63K4J","created_at":"2026-05-27T01:04:51.277531+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3G3GP55","created_at":"2026-05-27T01:04:51.277531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527","json":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527.json","graph_json":"https://pith.science/api/pith-number/F3G3GP55ZQP63K4JC2XGKC6527/graph.json","events_json":"https://pith.science/api/pith-number/F3G3GP55ZQP63K4JC2XGKC6527/events.json","paper":"https://pith.science/paper/F3G3GP55"},"agent_actions":{"view_html":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527","download_json":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527.json","view_paper":"https://pith.science/paper/F3G3GP55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24144&json=true","fetch_graph":"https://pith.science/api/pith-number/F3G3GP55ZQP63K4JC2XGKC6527/graph.json","fetch_events":"https://pith.science/api/pith-number/F3G3GP55ZQP63K4JC2XGKC6527/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527/action/storage_attestation","attest_author":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527/action/author_attestation","sign_citation":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527/action/citation_signature","submit_replication":"https://pith.science/pith/F3G3GP55ZQP63K4JC2XGKC6527/action/replication_record"}},"created_at":"2026-05-27T01:04:51.277531+00:00","updated_at":"2026-05-27T01:04:51.277531+00:00"}