{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HZMBNDPF3SGDD77EEBXY3MVAYB","short_pith_number":"pith:HZMBNDPF","schema_version":"1.0","canonical_sha256":"3e58168de5dc8c31ffe4206f8db2a0c0713ed56c242be279c9196c103f6b3505","source":{"kind":"arxiv","id":"2404.14507","version":1},"attestation_state":"computed","paper":{"title":"Align Your Steps: Optimizing Sampling Schedules in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amirmojtaba Sabour, Karsten Kreis, Sanja Fidler","submitted_at":"2024-04-22T18:18:41Z","abstract_excerpt":"Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed, relying on many sequential function evaluations through large neural networks. Sampling from DMs can be seen as solving a differential equation through a discretized set of noise levels known as the sampling schedule. While past works primarily focused on deriving efficient solvers, little attention has been given to finding optimal sampling schedules, and the entire literature relies on hand-crafted heu"},"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":"2404.14507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-22T18:18:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1afcc084de0d730df07c1fa9291166eae0e73be194d6103cff67ac4b3dbc55d5","abstract_canon_sha256":"353c8bed2415a600a7d7cb9b35bc2bd2bea5de22c057d2d6401b56283ae7d0b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:06.143399Z","signature_b64":"xKLA+WSnpMsilcwVi8lnoXqtc5u1SBuWeWmr6bEWDcu+icP377Ln+f+7NByX284fHyL8Kq1CWxI3QuZhjU8AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e58168de5dc8c31ffe4206f8db2a0c0713ed56c242be279c9196c103f6b3505","last_reissued_at":"2026-07-05T08:11:06.142916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:06.142916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align Your Steps: Optimizing Sampling Schedules in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Amirmojtaba Sabour, Karsten Kreis, Sanja Fidler","submitted_at":"2024-04-22T18:18:41Z","abstract_excerpt":"Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed, relying on many sequential function evaluations through large neural networks. Sampling from DMs can be seen as solving a differential equation through a discretized set of noise levels known as the sampling schedule. While past works primarily focused on deriving efficient solvers, little attention has been given to finding optimal sampling schedules, and the entire literature relies on hand-crafted heu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14507","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/2404.14507/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":"2404.14507","created_at":"2026-07-05T08:11:06.142976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14507v1","created_at":"2026-07-05T08:11:06.142976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14507","created_at":"2026-07-05T08:11:06.142976+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZMBNDPF3SGD","created_at":"2026-07-05T08:11:06.142976+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZMBNDPF3SGDD77E","created_at":"2026-07-05T08:11:06.142976+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZMBNDPF","created_at":"2026-07-05T08:11:06.142976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13496","citing_title":"Budget-Constrained Step-Level Diffusion Caching","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27947","citing_title":"SANTS: A State-Adaptive Scheduler for World Action Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16126","citing_title":"Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\\\"odinger Samplers","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22177","citing_title":"Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB","json":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB.json","graph_json":"https://pith.science/api/pith-number/HZMBNDPF3SGDD77EEBXY3MVAYB/graph.json","events_json":"https://pith.science/api/pith-number/HZMBNDPF3SGDD77EEBXY3MVAYB/events.json","paper":"https://pith.science/paper/HZMBNDPF"},"agent_actions":{"view_html":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB","download_json":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB.json","view_paper":"https://pith.science/paper/HZMBNDPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14507&json=true","fetch_graph":"https://pith.science/api/pith-number/HZMBNDPF3SGDD77EEBXY3MVAYB/graph.json","fetch_events":"https://pith.science/api/pith-number/HZMBNDPF3SGDD77EEBXY3MVAYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB/action/storage_attestation","attest_author":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB/action/author_attestation","sign_citation":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB/action/citation_signature","submit_replication":"https://pith.science/pith/HZMBNDPF3SGDD77EEBXY3MVAYB/action/replication_record"}},"created_at":"2026-07-05T08:11:06.142976+00:00","updated_at":"2026-07-05T08:11:06.142976+00:00"}