{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PLUDRLGKYMOFQ3I3Y7PRCEQNWK","short_pith_number":"pith:PLUDRLGK","schema_version":"1.0","canonical_sha256":"7ae838accac31c586d1bc7df11120db2846f786b3ea97969b35f141ffe0a7741","source":{"kind":"arxiv","id":"2503.01581","version":2},"attestation_state":"computed","paper":{"title":"A Deep Learning Framework for Medium-Term Covariance Forecasting in Multi-Asset Portfolios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Ana Paula Serra, Jo\\~ao Gama, Pedro Reis","submitted_at":"2025-03-03T14:23:28Z","abstract_excerpt":"Accurate covariance forecasting is central to portfolio allocation, risk management, and asset pricing, yet many existing methods struggle at medium-term horizons, where shifting market regimes and slower dynamics predominate. We propose a deep learning framework that combines three-dimensional convolutional neural networks, bidirectional long short-term memory layers, and multi-head attention to capture complex spatio-temporal dependencies. Using daily data on 14 exchange-traded funds from 2017 through 2023, we find that our model reduces Euclidean and Frobenius distance metrics by up to 20\\%"},"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":"2503.01581","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CE","submitted_at":"2025-03-03T14:23:28Z","cross_cats_sorted":[],"title_canon_sha256":"064b605731661e1251955906805c34dc2a0f554378f9eafd728fe6917e8558ff","abstract_canon_sha256":"620b62d170fa5f4b3d1ffbf70f07fc73ab5cae76a118157c64740e374882bdd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:13.176488Z","signature_b64":"fRC1FWVvZtlp4aN9lomepeMyh65hK3pa1D/zD7O2aOCp0sTMAEKgug1X3uHRenXGeXcIIGS/pfM+Wo+AtzRIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae838accac31c586d1bc7df11120db2846f786b3ea97969b35f141ffe0a7741","last_reissued_at":"2026-05-21T01:04:13.175767Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:13.175767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Learning Framework for Medium-Term Covariance Forecasting in Multi-Asset Portfolios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CE","authors_text":"Ana Paula Serra, Jo\\~ao Gama, Pedro Reis","submitted_at":"2025-03-03T14:23:28Z","abstract_excerpt":"Accurate covariance forecasting is central to portfolio allocation, risk management, and asset pricing, yet many existing methods struggle at medium-term horizons, where shifting market regimes and slower dynamics predominate. We propose a deep learning framework that combines three-dimensional convolutional neural networks, bidirectional long short-term memory layers, and multi-head attention to capture complex spatio-temporal dependencies. Using daily data on 14 exchange-traded funds from 2017 through 2023, we find that our model reduces Euclidean and Frobenius distance metrics by up to 20\\%"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01581","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/2503.01581/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":"2503.01581","created_at":"2026-05-21T01:04:13.175870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01581v2","created_at":"2026-05-21T01:04:13.175870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01581","created_at":"2026-05-21T01:04:13.175870+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLUDRLGKYMOF","created_at":"2026-05-21T01:04:13.175870+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLUDRLGKYMOFQ3I3","created_at":"2026-05-21T01:04:13.175870+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLUDRLGK","created_at":"2026-05-21T01:04:13.175870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01918","citing_title":"End-to-End Large Portfolio Optimization for Variance Minimization with Neural Networks through Covariance Cleaning","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK","json":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK.json","graph_json":"https://pith.science/api/pith-number/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/graph.json","events_json":"https://pith.science/api/pith-number/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/events.json","paper":"https://pith.science/paper/PLUDRLGK"},"agent_actions":{"view_html":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK","download_json":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK.json","view_paper":"https://pith.science/paper/PLUDRLGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01581&json=true","fetch_graph":"https://pith.science/api/pith-number/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/graph.json","fetch_events":"https://pith.science/api/pith-number/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/action/storage_attestation","attest_author":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/action/author_attestation","sign_citation":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/action/citation_signature","submit_replication":"https://pith.science/pith/PLUDRLGKYMOFQ3I3Y7PRCEQNWK/action/replication_record"}},"created_at":"2026-05-21T01:04:13.175870+00:00","updated_at":"2026-05-21T01:04:13.175870+00:00"}