{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZTA4WRULRYUNALMJBJKONR3623","short_pith_number":"pith:ZTA4WRUL","schema_version":"1.0","canonical_sha256":"ccc1cb468b8e28d02d890a54e6c77ed6c4ae62ca53a8d442c45f657a62d1fab3","source":{"kind":"arxiv","id":"2503.18940","version":2},"attestation_state":"computed","paper":{"title":"Training-free Diffusion Acceleration with Bottleneck Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Cui, Ling Yang, Shanchuan Lin, Xing Wang, Xin Xia, Xuefeng Xiao, Ye Tian, Yunhai Tong, Yuxi Ren","submitted_at":"2025-03-24T17:59:02Z","abstract_excerpt":"Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This computational burden primarily arises from the quadratic complexity of self-attention with respect to image or video resolution. While existing acceleration methods often compromise output quality or necessitate costly retraining, we observe that most diffusion models are pre-trained at lower resolutions, presenting an opportunity to exploit these low-resolution priors for more efficient inference without degrading "},"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":"2503.18940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"c1e4d26f001eb5de153b7377eae62ed943da4deb9d79be26d824e2cc68ee9c51","abstract_canon_sha256":"3a2bf29543b139bbdfceb9330bfe3deb42914af0219728e9c94d8bec77322148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:18.703076Z","signature_b64":"QJVtuxZeyQtEZvccyyzsy7hRgAU/dHg6CRBQxLQRhsCTbO52NvA5lfsP5y0SzRxCxypP3zttRBhJSPXwWliRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccc1cb468b8e28d02d890a54e6c77ed6c4ae62ca53a8d442c45f657a62d1fab3","last_reissued_at":"2026-07-05T10:40:18.702490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:18.702490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-free Diffusion Acceleration with Bottleneck Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Cui, Ling Yang, Shanchuan Lin, Xing Wang, Xin Xia, Xuefeng Xiao, Ye Tian, Yunhai Tong, Yuxi Ren","submitted_at":"2025-03-24T17:59:02Z","abstract_excerpt":"Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This computational burden primarily arises from the quadratic complexity of self-attention with respect to image or video resolution. While existing acceleration methods often compromise output quality or necessitate costly retraining, we observe that most diffusion models are pre-trained at lower resolutions, presenting an opportunity to exploit these low-resolution priors for more efficient inference without degrading "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18940","kind":"arxiv","version":2},"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/2503.18940/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":"2503.18940","created_at":"2026-07-05T10:40:18.702554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18940v2","created_at":"2026-07-05T10:40:18.702554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18940","created_at":"2026-07-05T10:40:18.702554+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTA4WRULRYUN","created_at":"2026-07-05T10:40:18.702554+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTA4WRULRYUNALMJ","created_at":"2026-07-05T10:40:18.702554+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTA4WRUL","created_at":"2026-07-05T10:40:18.702554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.21002","citing_title":"SURF: Signature-Retained Fast Video Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18736","citing_title":"Spectral Progressive Diffusion for Efficient Image and Video Generation","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18736","citing_title":"Spectral Progressive Diffusion for Efficient Image and Video Generation","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14267","citing_title":"Image Restoration via Diffusion Models with Dynamic Resolution","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02152","citing_title":"SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09227","citing_title":"Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623","json":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623.json","graph_json":"https://pith.science/api/pith-number/ZTA4WRULRYUNALMJBJKONR3623/graph.json","events_json":"https://pith.science/api/pith-number/ZTA4WRULRYUNALMJBJKONR3623/events.json","paper":"https://pith.science/paper/ZTA4WRUL"},"agent_actions":{"view_html":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623","download_json":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623.json","view_paper":"https://pith.science/paper/ZTA4WRUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18940&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTA4WRULRYUNALMJBJKONR3623/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTA4WRULRYUNALMJBJKONR3623/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623/action/storage_attestation","attest_author":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623/action/author_attestation","sign_citation":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623/action/citation_signature","submit_replication":"https://pith.science/pith/ZTA4WRULRYUNALMJBJKONR3623/action/replication_record"}},"created_at":"2026-07-05T10:40:18.702554+00:00","updated_at":"2026-07-05T10:40:18.702554+00:00"}