{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EDDI3FLFBPTD4CRANQIILQ42O7","short_pith_number":"pith:EDDI3FLF","schema_version":"1.0","canonical_sha256":"20c68d95650be63e0a206c1085c39a77c49f8addc69e95f1d70036072278e3e7","source":{"kind":"arxiv","id":"2402.17376","version":3},"attestation_state":"computed","paper":{"title":"Accelerating Diffusion Sampling with Optimized Time Steps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Enze Xie, Fei Chen, Shifeng Zhang, Shuchen Xue, Tianyang Hu, Zhaoqiang Liu, Zhenguo Li","submitted_at":"2024-02-27T10:13:30Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization p"},"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":"2402.17376","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T10:13:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7e74350c05c38766cbb8e79574301a463da428026f4d4f6f73bf96c0428ce1a0","abstract_canon_sha256":"8bb2899253e8bec5d72c3a18f184568ff0d2515d9fe5356e2ed007afe0b40ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:31.413700Z","signature_b64":"FKVIPqCxqcn/wJJmHVdULyHcZfMIn8bMvhX1hstwadEPvwQDtwmjUrovy1pTW6MLAoA8c/Uhkmsd+rLYnjoYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20c68d95650be63e0a206c1085c39a77c49f8addc69e95f1d70036072278e3e7","last_reissued_at":"2026-07-05T08:39:31.413240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:31.413240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Diffusion Sampling with Optimized Time Steps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Enze Xie, Fei Chen, Shifeng Zhang, Shuchen Xue, Tianyang Hu, Zhaoqiang Liu, Zhenguo Li","submitted_at":"2024-02-27T10:13:30Z","abstract_excerpt":"Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17376","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/2402.17376/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":"2402.17376","created_at":"2026-07-05T08:39:31.413302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17376v3","created_at":"2026-07-05T08:39:31.413302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17376","created_at":"2026-07-05T08:39:31.413302+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDDI3FLFBPTD","created_at":"2026-07-05T08:39:31.413302+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDDI3FLFBPTD4CRA","created_at":"2026-07-05T08:39:31.413302+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDDI3FLF","created_at":"2026-07-05T08:39:31.413302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16126","citing_title":"Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\\\"odinger Samplers","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7","json":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7.json","graph_json":"https://pith.science/api/pith-number/EDDI3FLFBPTD4CRANQIILQ42O7/graph.json","events_json":"https://pith.science/api/pith-number/EDDI3FLFBPTD4CRANQIILQ42O7/events.json","paper":"https://pith.science/paper/EDDI3FLF"},"agent_actions":{"view_html":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7","download_json":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7.json","view_paper":"https://pith.science/paper/EDDI3FLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17376&json=true","fetch_graph":"https://pith.science/api/pith-number/EDDI3FLFBPTD4CRANQIILQ42O7/graph.json","fetch_events":"https://pith.science/api/pith-number/EDDI3FLFBPTD4CRANQIILQ42O7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7/action/storage_attestation","attest_author":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7/action/author_attestation","sign_citation":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7/action/citation_signature","submit_replication":"https://pith.science/pith/EDDI3FLFBPTD4CRANQIILQ42O7/action/replication_record"}},"created_at":"2026-07-05T08:39:31.413302+00:00","updated_at":"2026-07-05T08:39:31.413302+00:00"}