{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IFFFKKEEWO523YN76RUL6YEBP4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2988b52dbb2d98e7850193f87431af48282a2efbb47e95cbc5a69c7fe45895b2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-02T13:14:30Z","title_canon_sha256":"6fb94dc7b65c3a0888ddd207f6d8d4a4dc92e723d10cf97e60d056e20af0f2f3"},"schema_version":"1.0","source":{"id":"2211.01095","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01095","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01095v3","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01095","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"IFFFKKEEWO52","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"IFFFKKEEWO523YN7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"IFFFKKEE","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:23f5ae2fd1fa41b3d1d886ede3a1c4fcc2f0a79917cfee575931da649e11b008","target":"graph","created_at":"2026-05-17T23:38:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments show that DPM-Solver++ can generate high-quality samples within only 15 to 20 steps for guided sampling by pixel-space and latent-space DPMs."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the combination of data-prediction formulation and thresholding, plus the multistep variant, reliably eliminates the instability observed in prior high-order solvers when guidance scale is large."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DPM-Solver++ generates high-quality guided samples from diffusion models in 15 to 20 steps"}],"snapshot_sha256":"c126f193e9d9447c50f649691bdb285e21a0491a25a0dbe8bf568caba049cfb7"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fab49c958ce80a0057f210f53de72bd2bc79983b390b015f135c2f6c79eeda0c"},"paper":{"abstract_excerpt":"Diffusion probabilistic models (DPMs) have achieved impressive success in high-resolution image synthesis, especially in recent large-scale text-to-image generation applications. An essential technique for improving the sample quality of DPMs is guided sampling, which usually needs a large guidance scale to obtain the best sample quality. The commonly-used fast sampler for guided sampling is DDIM, a first-order diffusion ODE solver that generally needs 100 to 250 steps for high-quality samples. Although recent works propose dedicated high-order solvers and achieve a further speedup for samplin","authors_text":"Cheng Lu, Chongxuan Li, Fan Bao, Jianfei Chen, Jun Zhu, Yuhao Zhou","cross_cats":["cs.CV"],"headline":"DPM-Solver++ generates high-quality guided samples from diffusion models in 15 to 20 steps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-02T13:14:30Z","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models"},"references":{"count":30,"internal_anchors":4,"resolved_work":30,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Estimating the optimal covariance with imperfect mean in diffusion probabilistic models","work_id":"d603de64-25fc-45d6-a2e3-facbb240bc7d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Classifier-free diffusion guidance","work_id":"fed77747-e4f2-4527-a3b8-a1822f33bbc2","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Gotta go fast when generating data with score-based models","work_id":"020cfe2a-ca4b-40ea-bc2d-53d06a2194b6","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"On fast sampling of diffusion probabilistic models","work_id":"28f4d037-fdd8-4254-92c7-3361c8b2633b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bilateral denoising diffusion models","work_id":"351c5468-87cd-4bbc-a9e6-f86d25051435","year":null}],"snapshot_sha256":"50ce1fc1a9eb6b73630276fbccaa434463a744ca3472d82f0e7193c38a802199"},"source":{"id":"2211.01095","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T07:50:42.794854Z","id":"9d033d3c-18b2-4189-adbc-48d57fd6ea7e","model_set":{"reader":"grok-4.3"},"one_line_summary":"DPM-Solver++ enables high-quality guided sampling of diffusion models in 15-20 steps via data-prediction ODE solving and multistep stabilization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DPM-Solver++ generates high-quality guided samples from diffusion models in 15 to 20 steps","strongest_claim":"Experiments show that DPM-Solver++ can generate high-quality samples within only 15 to 20 steps for guided sampling by pixel-space and latent-space DPMs.","weakest_assumption":"That the combination of data-prediction formulation and thresholding, plus the multistep variant, reliably eliminates the instability observed in prior high-order solvers when guidance scale is large."}},"verdict_id":"9d033d3c-18b2-4189-adbc-48d57fd6ea7e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11ce44d2aeb846280a444b456fd5b642bdb6d3f47cbdaf95651445bf0f14c071","target":"record","created_at":"2026-05-17T23:38:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2988b52dbb2d98e7850193f87431af48282a2efbb47e95cbc5a69c7fe45895b2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-02T13:14:30Z","title_canon_sha256":"6fb94dc7b65c3a0888ddd207f6d8d4a4dc92e723d10cf97e60d056e20af0f2f3"},"schema_version":"1.0","source":{"id":"2211.01095","kind":"arxiv","version":3}},"canonical_sha256":"414a552884b3bbade1bff468bf60817f3272773873f6e20d4c138d9d99a1c31f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"414a552884b3bbade1bff468bf60817f3272773873f6e20d4c138d9d99a1c31f","first_computed_at":"2026-05-17T23:38:48.596639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.596639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ru4000Yj7rQUyidLAfAJlcGJ5X4WpfW2ZCEkJIFTHSJ05M/seoRYl2duijt8kc+t3lnaZrfxT8bI+dJVvMNkBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.597229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.01095","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ce44d2aeb846280a444b456fd5b642bdb6d3f47cbdaf95651445bf0f14c071","sha256:23f5ae2fd1fa41b3d1d886ede3a1c4fcc2f0a79917cfee575931da649e11b008"],"state_sha256":"f074d3e42fd8bdea73a977384584451b52a5be230edc55bbf8d4a23a46270603"}