{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RIBRMRJ2DGF7RWWMJPZF5MBCBR","short_pith_number":"pith:RIBRMRJ2","schema_version":"1.0","canonical_sha256":"8a0316453a198bf8dacc4bf25eb0220c4cfa4cf4d6369aba071aab2d0562a626","source":{"kind":"arxiv","id":"2406.10354","version":2},"attestation_state":"computed","paper":{"title":"SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Barbora Barancikova, Cristopher Salvi, Zhuoyue Huang","submitted_at":"2024-06-14T18:04:06Z","abstract_excerpt":"Score-based diffusion models have recently emerged as state-of-the-art generative models for a variety of data modalities. Nonetheless, it remains unclear how to adapt these models to generate long multivariate time series. Viewing a time series as the discretisation of an underlying continuous process, we introduce SigDiffusion, a novel diffusion model operating on log-signature embeddings of the data. The forward and backward processes gradually perturb and denoise log-signatures while preserving their algebraic structure. To recover a signal from its log-signature, we provide new closed-for"},"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":"2406.10354","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T18:04:06Z","cross_cats_sorted":[],"title_canon_sha256":"73067211187b047f6b61ce8c798aa28a661bf74c5c6947572203a629c4de3317","abstract_canon_sha256":"c3a10a32cd41811300fae9b65f62ba57becb3ad3a8b63ec3580c0957f219c38d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:37.699584Z","signature_b64":"9ntJJtAlmA6FQTK4QU6yXbO0Cx5quYUuznx3RACH8bAe5uzu7YWpZ7Rdrqw1sxODdGV5OldjjOb9bdL8LWL6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a0316453a198bf8dacc4bf25eb0220c4cfa4cf4d6369aba071aab2d0562a626","last_reissued_at":"2026-07-05T10:20:37.699004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:37.699004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Barbora Barancikova, Cristopher Salvi, Zhuoyue Huang","submitted_at":"2024-06-14T18:04:06Z","abstract_excerpt":"Score-based diffusion models have recently emerged as state-of-the-art generative models for a variety of data modalities. Nonetheless, it remains unclear how to adapt these models to generate long multivariate time series. Viewing a time series as the discretisation of an underlying continuous process, we introduce SigDiffusion, a novel diffusion model operating on log-signature embeddings of the data. The forward and backward processes gradually perturb and denoise log-signatures while preserving their algebraic structure. To recover a signal from its log-signature, we provide new closed-for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10354","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/2406.10354/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":"2406.10354","created_at":"2026-07-05T10:20:37.699078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10354v2","created_at":"2026-07-05T10:20:37.699078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10354","created_at":"2026-07-05T10:20:37.699078+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIBRMRJ2DGF7","created_at":"2026-07-05T10:20:37.699078+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIBRMRJ2DGF7RWWM","created_at":"2026-07-05T10:20:37.699078+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIBRMRJ2","created_at":"2026-07-05T10:20:37.699078+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/RIBRMRJ2DGF7RWWMJPZF5MBCBR","json":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR.json","graph_json":"https://pith.science/api/pith-number/RIBRMRJ2DGF7RWWMJPZF5MBCBR/graph.json","events_json":"https://pith.science/api/pith-number/RIBRMRJ2DGF7RWWMJPZF5MBCBR/events.json","paper":"https://pith.science/paper/RIBRMRJ2"},"agent_actions":{"view_html":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR","download_json":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR.json","view_paper":"https://pith.science/paper/RIBRMRJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10354&json=true","fetch_graph":"https://pith.science/api/pith-number/RIBRMRJ2DGF7RWWMJPZF5MBCBR/graph.json","fetch_events":"https://pith.science/api/pith-number/RIBRMRJ2DGF7RWWMJPZF5MBCBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR/action/storage_attestation","attest_author":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR/action/author_attestation","sign_citation":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR/action/citation_signature","submit_replication":"https://pith.science/pith/RIBRMRJ2DGF7RWWMJPZF5MBCBR/action/replication_record"}},"created_at":"2026-07-05T10:20:37.699078+00:00","updated_at":"2026-07-05T10:20:37.699078+00:00"}