{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UGHINK45M22HQOWPPOFG5VTRWF","short_pith_number":"pith:UGHINK45","schema_version":"1.0","canonical_sha256":"a18e86ab9d66b4783acf7b8a6ed671b16d8c337057789e7554b997a1e1992b52","source":{"kind":"arxiv","id":"2108.00981","version":3},"attestation_state":"computed","paper":{"title":"PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bohlke-Schneider Michael, Flunkert Valentin, Gasthaus Jan, Januschowski Tim, Jeha Paul, Kapoor Shubham, Mercado Pedro, Singh Nirwan Rajbir","submitted_at":"2021-08-02T15:30:15Z","abstract_excerpt":"Realistic synthetic time series data of sufficient length enables practical applications in time series modeling tasks, such as forecasting, but remains a challenge. In this paper we present PSA-GAN, a generative adversarial network (GAN) that generates long time series samples of high quality using progressive growing of GANs and self-attention. We show that PSA-GAN can be used to reduce the error in two downstream forecasting tasks over baselines that only use real data. We also introduce a Frechet-Inception Distance-like score, Context-FID, assessing the quality of synthetic time series sam"},"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":"2108.00981","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-02T15:30:15Z","cross_cats_sorted":[],"title_canon_sha256":"4dbef1edd1b556c8dc6d5d64f168c927056683e02baa77349054f43fe53aa3ff","abstract_canon_sha256":"6ab1eed6c8e0bb38464a6788caab358520ac714df93f0041655c6a0e87020990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:58.128018Z","signature_b64":"+K/VcAcF7ia/CR5eCifYMTN0CnW00nsQPENghubXbbSxpLc9NJQA+7JjqwWZxr2AFd7gc9N0G2jG9jI7/t0bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18e86ab9d66b4783acf7b8a6ed671b16d8c337057789e7554b997a1e1992b52","last_reissued_at":"2026-07-05T04:08:58.127580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:58.127580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bohlke-Schneider Michael, Flunkert Valentin, Gasthaus Jan, Januschowski Tim, Jeha Paul, Kapoor Shubham, Mercado Pedro, Singh Nirwan Rajbir","submitted_at":"2021-08-02T15:30:15Z","abstract_excerpt":"Realistic synthetic time series data of sufficient length enables practical applications in time series modeling tasks, such as forecasting, but remains a challenge. In this paper we present PSA-GAN, a generative adversarial network (GAN) that generates long time series samples of high quality using progressive growing of GANs and self-attention. We show that PSA-GAN can be used to reduce the error in two downstream forecasting tasks over baselines that only use real data. We also introduce a Frechet-Inception Distance-like score, Context-FID, assessing the quality of synthetic time series sam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00981","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/2108.00981/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":"2108.00981","created_at":"2026-07-05T04:08:58.127636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00981v3","created_at":"2026-07-05T04:08:58.127636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00981","created_at":"2026-07-05T04:08:58.127636+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGHINK45M22H","created_at":"2026-07-05T04:08:58.127636+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGHINK45M22HQOWP","created_at":"2026-07-05T04:08:58.127636+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGHINK45","created_at":"2026-07-05T04:08:58.127636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.05020","citing_title":"Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF","json":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF.json","graph_json":"https://pith.science/api/pith-number/UGHINK45M22HQOWPPOFG5VTRWF/graph.json","events_json":"https://pith.science/api/pith-number/UGHINK45M22HQOWPPOFG5VTRWF/events.json","paper":"https://pith.science/paper/UGHINK45"},"agent_actions":{"view_html":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF","download_json":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF.json","view_paper":"https://pith.science/paper/UGHINK45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00981&json=true","fetch_graph":"https://pith.science/api/pith-number/UGHINK45M22HQOWPPOFG5VTRWF/graph.json","fetch_events":"https://pith.science/api/pith-number/UGHINK45M22HQOWPPOFG5VTRWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF/action/storage_attestation","attest_author":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF/action/author_attestation","sign_citation":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF/action/citation_signature","submit_replication":"https://pith.science/pith/UGHINK45M22HQOWPPOFG5VTRWF/action/replication_record"}},"created_at":"2026-07-05T04:08:58.127636+00:00","updated_at":"2026-07-05T04:08:58.127636+00:00"}