{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:COJWI5OZOTTQYJ2I66FUVN64PT","short_pith_number":"pith:COJWI5OZ","schema_version":"1.0","canonical_sha256":"13936475d974e70c2748f78b4ab7dc7cca15f83d400caba5fa71cc1d4bd6985b","source":{"kind":"arxiv","id":"2310.13268","version":3},"attestation_state":"computed","paper":{"title":"DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng Lu, Jianfei Chen, Jun Zhu, Kaiwen Zheng","submitted_at":"2023-10-20T04:23:12Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) have exhibited excellent performance for high-fidelity image generation while suffering from inefficient sampling. Recent works accelerate the sampling procedure by proposing fast ODE solvers that leverage the specific ODE form of DPMs. However, they highly rely on specific parameterization during inference (such as noise/data prediction), which might not be the optimal choice. In this work, we propose a novel formulation towards the optimal parameterization during sampling that minimizes the first-order discretization error of the ODE solution. Based on s"},"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":"2310.13268","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-20T04:23:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b7cade7f3c1121f826ae3c0f04bf30b5371515da46b2c52c4aaaca07831b6c46","abstract_canon_sha256":"f0da054b4492b84055daeddd6f8451fa8d81de9e386a5ad4981e8062608302e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:06.221443Z","signature_b64":"IjrnAJwjpFUxe+A1JEkWXYVeJmYmYTq+NxCfLzEh1BCxOIpXWNQO1Wy62ArFLesURPRXKIlSO8qA4fTzZKopDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13936475d974e70c2748f78b4ab7dc7cca15f83d400caba5fa71cc1d4bd6985b","last_reissued_at":"2026-07-05T07:06:06.220939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:06.220939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng Lu, Jianfei Chen, Jun Zhu, Kaiwen Zheng","submitted_at":"2023-10-20T04:23:12Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) have exhibited excellent performance for high-fidelity image generation while suffering from inefficient sampling. Recent works accelerate the sampling procedure by proposing fast ODE solvers that leverage the specific ODE form of DPMs. However, they highly rely on specific parameterization during inference (such as noise/data prediction), which might not be the optimal choice. In this work, we propose a novel formulation towards the optimal parameterization during sampling that minimizes the first-order discretization error of the ODE solution. Based on s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13268","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/2310.13268/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":"2310.13268","created_at":"2026-07-05T07:06:06.221012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13268v3","created_at":"2026-07-05T07:06:06.221012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13268","created_at":"2026-07-05T07:06:06.221012+00:00"},{"alias_kind":"pith_short_12","alias_value":"COJWI5OZOTTQ","created_at":"2026-07-05T07:06:06.221012+00:00"},{"alias_kind":"pith_short_16","alias_value":"COJWI5OZOTTQYJ2I","created_at":"2026-07-05T07:06:06.221012+00:00"},{"alias_kind":"pith_short_8","alias_value":"COJWI5OZ","created_at":"2026-07-05T07:06:06.221012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27947","citing_title":"SANTS: A State-Adaptive Scheduler for World Action Models","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT","json":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT.json","graph_json":"https://pith.science/api/pith-number/COJWI5OZOTTQYJ2I66FUVN64PT/graph.json","events_json":"https://pith.science/api/pith-number/COJWI5OZOTTQYJ2I66FUVN64PT/events.json","paper":"https://pith.science/paper/COJWI5OZ"},"agent_actions":{"view_html":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT","download_json":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT.json","view_paper":"https://pith.science/paper/COJWI5OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13268&json=true","fetch_graph":"https://pith.science/api/pith-number/COJWI5OZOTTQYJ2I66FUVN64PT/graph.json","fetch_events":"https://pith.science/api/pith-number/COJWI5OZOTTQYJ2I66FUVN64PT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT/action/storage_attestation","attest_author":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT/action/author_attestation","sign_citation":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT/action/citation_signature","submit_replication":"https://pith.science/pith/COJWI5OZOTTQYJ2I66FUVN64PT/action/replication_record"}},"created_at":"2026-07-05T07:06:06.221012+00:00","updated_at":"2026-07-05T07:06:06.221012+00:00"}