{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EDLEFVQOTCJWAGBUJOOCCATF7T","short_pith_number":"pith:EDLEFVQO","schema_version":"1.0","canonical_sha256":"20d642d60e98936018344b9c210265fcf31e6a47dc4017000914e7a38ef1e223","source":{"kind":"arxiv","id":"2411.02947","version":1},"attestation_state":"computed","paper":{"title":"Time-Causal VAE: Robust Financial Time Series Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.CP"],"primary_cat":"cs.LG","authors_text":"Beatrice Acciaio, Songyan Hou, Stephan Eckstein","submitted_at":"2024-11-05T09:44:15Z","abstract_excerpt":"We build a time-causal variational autoencoder (TC-VAE) for robust generation of financial time series data. Our approach imposes a causality constraint on the encoder and decoder networks, ensuring a causal transport from the real market time series to the fake generated time series. Specifically, we prove that the TC-VAE loss provides an upper bound on the causal Wasserstein distance between market distributions and generated distributions. Consequently, the TC-VAE loss controls the discrepancy between optimal values of various dynamic stochastic optimization problems under real and generate"},"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":"2411.02947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T09:44:15Z","cross_cats_sorted":["q-fin.CP"],"title_canon_sha256":"dbda745433aff390dd69a1ef9047be17de7d78284cd964fcf9c99ed36a09f1b8","abstract_canon_sha256":"941bea66c9f570fb7c4935ec6379d98ecdd15c752cedb4b885817ae6a3fe4501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:20.844823Z","signature_b64":"9RPU0kxK8umOTNLSHPx4BQ80Ff2/IA/nS4xQQfK2S+EeSBZ+v/8HzTGkfbEpQNqKMsLJZJnci/eMzez0YxYUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20d642d60e98936018344b9c210265fcf31e6a47dc4017000914e7a38ef1e223","last_reissued_at":"2026-07-05T09:31:20.844379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:20.844379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Causal VAE: Robust Financial Time Series Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.CP"],"primary_cat":"cs.LG","authors_text":"Beatrice Acciaio, Songyan Hou, Stephan Eckstein","submitted_at":"2024-11-05T09:44:15Z","abstract_excerpt":"We build a time-causal variational autoencoder (TC-VAE) for robust generation of financial time series data. Our approach imposes a causality constraint on the encoder and decoder networks, ensuring a causal transport from the real market time series to the fake generated time series. Specifically, we prove that the TC-VAE loss provides an upper bound on the causal Wasserstein distance between market distributions and generated distributions. Consequently, the TC-VAE loss controls the discrepancy between optimal values of various dynamic stochastic optimization problems under real and generate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02947","kind":"arxiv","version":1},"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/2411.02947/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":"2411.02947","created_at":"2026-07-05T09:31:20.844436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02947v1","created_at":"2026-07-05T09:31:20.844436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02947","created_at":"2026-07-05T09:31:20.844436+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDLEFVQOTCJW","created_at":"2026-07-05T09:31:20.844436+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDLEFVQOTCJWAGBU","created_at":"2026-07-05T09:31:20.844436+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDLEFVQO","created_at":"2026-07-05T09:31:20.844436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10466","citing_title":"UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T","json":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T.json","graph_json":"https://pith.science/api/pith-number/EDLEFVQOTCJWAGBUJOOCCATF7T/graph.json","events_json":"https://pith.science/api/pith-number/EDLEFVQOTCJWAGBUJOOCCATF7T/events.json","paper":"https://pith.science/paper/EDLEFVQO"},"agent_actions":{"view_html":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T","download_json":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T.json","view_paper":"https://pith.science/paper/EDLEFVQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02947&json=true","fetch_graph":"https://pith.science/api/pith-number/EDLEFVQOTCJWAGBUJOOCCATF7T/graph.json","fetch_events":"https://pith.science/api/pith-number/EDLEFVQOTCJWAGBUJOOCCATF7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T/action/storage_attestation","attest_author":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T/action/author_attestation","sign_citation":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T/action/citation_signature","submit_replication":"https://pith.science/pith/EDLEFVQOTCJWAGBUJOOCCATF7T/action/replication_record"}},"created_at":"2026-07-05T09:31:20.844436+00:00","updated_at":"2026-07-05T09:31:20.844436+00:00"}