{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TYGB5ZRLHGV7FBWSYDD43FBL5F","short_pith_number":"pith:TYGB5ZRL","schema_version":"1.0","canonical_sha256":"9e0c1ee62b39abf286d2c0c7cd942be95860095e166a3865b7d163441676cafd","source":{"kind":"arxiv","id":"2308.02157","version":1},"attestation_state":"computed","paper":{"title":"Improved Order Analysis and Design of Exponential Integrator for Diffusion Models Sampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaming Song, Qinsheng Zhang, Yongxin Chen","submitted_at":"2023-08-04T06:30:40Z","abstract_excerpt":"Efficient differential equation solvers have significantly reduced the sampling time of diffusion models (DMs) while retaining high sampling quality. Among these solvers, exponential integrators (EI) have gained prominence by demonstrating state-of-the-art performance. However, existing high-order EI-based sampling algorithms rely on degenerate EI solvers, resulting in inferior error bounds and reduced accuracy in contrast to the theoretically anticipated results under optimal settings. This situation makes the sampling quality extremely vulnerable to seemingly innocuous design choices such as"},"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":"2308.02157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-04T06:30:40Z","cross_cats_sorted":[],"title_canon_sha256":"971f0bf358091e0ca5046dd423885df20262ff16d811cb99ac2d295425167bfa","abstract_canon_sha256":"35ee82c625e1ea07665a2de9809702d323eeac6a5be073efdfdbc678f0fcbe76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:38.501642Z","signature_b64":"mUEXSQr20D5ctZE8WS85mexgjqc9fIl6NuZEkG1OD3h0w6O20R/LzyDkzOtBkruMFinfWmA8VdPd81LAfLHoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e0c1ee62b39abf286d2c0c7cd942be95860095e166a3865b7d163441676cafd","last_reissued_at":"2026-07-05T06:37:38.501240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:38.501240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Order Analysis and Design of Exponential Integrator for Diffusion Models Sampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaming Song, Qinsheng Zhang, Yongxin Chen","submitted_at":"2023-08-04T06:30:40Z","abstract_excerpt":"Efficient differential equation solvers have significantly reduced the sampling time of diffusion models (DMs) while retaining high sampling quality. Among these solvers, exponential integrators (EI) have gained prominence by demonstrating state-of-the-art performance. However, existing high-order EI-based sampling algorithms rely on degenerate EI solvers, resulting in inferior error bounds and reduced accuracy in contrast to the theoretically anticipated results under optimal settings. This situation makes the sampling quality extremely vulnerable to seemingly innocuous design choices such as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02157","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/2308.02157/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":"2308.02157","created_at":"2026-07-05T06:37:38.501292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02157v1","created_at":"2026-07-05T06:37:38.501292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02157","created_at":"2026-07-05T06:37:38.501292+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYGB5ZRLHGV7","created_at":"2026-07-05T06:37:38.501292+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYGB5ZRLHGV7FBWS","created_at":"2026-07-05T06:37:38.501292+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYGB5ZRL","created_at":"2026-07-05T06:37:38.501292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02137","citing_title":"ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04575","citing_title":"Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2601.18681","citing_title":"ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F","json":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F.json","graph_json":"https://pith.science/api/pith-number/TYGB5ZRLHGV7FBWSYDD43FBL5F/graph.json","events_json":"https://pith.science/api/pith-number/TYGB5ZRLHGV7FBWSYDD43FBL5F/events.json","paper":"https://pith.science/paper/TYGB5ZRL"},"agent_actions":{"view_html":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F","download_json":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F.json","view_paper":"https://pith.science/paper/TYGB5ZRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02157&json=true","fetch_graph":"https://pith.science/api/pith-number/TYGB5ZRLHGV7FBWSYDD43FBL5F/graph.json","fetch_events":"https://pith.science/api/pith-number/TYGB5ZRLHGV7FBWSYDD43FBL5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F/action/storage_attestation","attest_author":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F/action/author_attestation","sign_citation":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F/action/citation_signature","submit_replication":"https://pith.science/pith/TYGB5ZRLHGV7FBWSYDD43FBL5F/action/replication_record"}},"created_at":"2026-07-05T06:37:38.501292+00:00","updated_at":"2026-07-05T06:37:38.501292+00:00"}