{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ASM3GWCEE2M3UJGQSB3M55TUQI","short_pith_number":"pith:ASM3GWCE","schema_version":"1.0","canonical_sha256":"0499b358442699ba24d09076cef674823fde2e5da4e9fded65fcaf7367ab43c5","source":{"kind":"arxiv","id":"2307.12667","version":2},"attestation_state":"computed","paper":{"title":"TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fredrik Heintz, Md Fahim Sikder, Resmi Ramachandranpillai","submitted_at":"2023-07-24T10:14:51Z","abstract_excerpt":"The generation of high-quality, long-sequenced time-series data is essential due to its wide range of applications. In the past, standalone Recurrent and Convolutional Neural Network-based Generative Adversarial Networks (GAN) were used to synthesize time-series data. However, they are inadequate for generating long sequences of time-series data due to limitations in the architecture. Furthermore, GANs are well known for their training instability and mode collapse problem. To address this, we propose TransFusion, a diffusion, and transformers-based generative model to generate high-quality lo"},"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":"2307.12667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-24T10:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"3a2abc08798fc596b6b11f50dcd4e439f7554976c9601aa2f085d9663fa7f0ce","abstract_canon_sha256":"71abec0a241fbd3b115ea792f83f1a61b0d78eeb384b5e90750cccee01341512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:38.939356Z","signature_b64":"mM851Z9/1/r/T8mQ3krOvXcgJpeNvJBnd+crcgttC0svTB4e6+BGf6jcQ5v3cVRK6p4oyySniw4eqD6pq5i+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0499b358442699ba24d09076cef674823fde2e5da4e9fded65fcaf7367ab43c5","last_reissued_at":"2026-07-05T08:11:38.938869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:38.938869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fredrik Heintz, Md Fahim Sikder, Resmi Ramachandranpillai","submitted_at":"2023-07-24T10:14:51Z","abstract_excerpt":"The generation of high-quality, long-sequenced time-series data is essential due to its wide range of applications. In the past, standalone Recurrent and Convolutional Neural Network-based Generative Adversarial Networks (GAN) were used to synthesize time-series data. However, they are inadequate for generating long sequences of time-series data due to limitations in the architecture. Furthermore, GANs are well known for their training instability and mode collapse problem. To address this, we propose TransFusion, a diffusion, and transformers-based generative model to generate high-quality lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12667","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/2307.12667/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":"2307.12667","created_at":"2026-07-05T08:11:38.938923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.12667v2","created_at":"2026-07-05T08:11:38.938923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12667","created_at":"2026-07-05T08:11:38.938923+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASM3GWCEE2M3","created_at":"2026-07-05T08:11:38.938923+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASM3GWCEE2M3UJGQ","created_at":"2026-07-05T08:11:38.938923+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASM3GWCE","created_at":"2026-07-05T08:11:38.938923+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03324","citing_title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI","json":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI.json","graph_json":"https://pith.science/api/pith-number/ASM3GWCEE2M3UJGQSB3M55TUQI/graph.json","events_json":"https://pith.science/api/pith-number/ASM3GWCEE2M3UJGQSB3M55TUQI/events.json","paper":"https://pith.science/paper/ASM3GWCE"},"agent_actions":{"view_html":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI","download_json":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI.json","view_paper":"https://pith.science/paper/ASM3GWCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.12667&json=true","fetch_graph":"https://pith.science/api/pith-number/ASM3GWCEE2M3UJGQSB3M55TUQI/graph.json","fetch_events":"https://pith.science/api/pith-number/ASM3GWCEE2M3UJGQSB3M55TUQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI/action/storage_attestation","attest_author":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI/action/author_attestation","sign_citation":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI/action/citation_signature","submit_replication":"https://pith.science/pith/ASM3GWCEE2M3UJGQSB3M55TUQI/action/replication_record"}},"created_at":"2026-07-05T08:11:38.938923+00:00","updated_at":"2026-07-05T08:11:38.938923+00:00"}