{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SXBFWGCMSGOHQDTGM5J5LRW3U5","short_pith_number":"pith:SXBFWGCM","schema_version":"1.0","canonical_sha256":"95c25b184c919c780e666753d5c6dba760dc3c50bea614817d99c67e7ad464a9","source":{"kind":"arxiv","id":"2410.16942","version":1},"attestation_state":"computed","paper":{"title":"DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashish Sirasao, Bin Wang, Dehua Tang, Dong Li, Emad Barsoum, Fan Jiang, Haowei Zhu, Ji Liu, Jintu Zheng, Jinzhang Peng, Jun-Hai Yong, Lu Tian, Mingjie Lu, Spandan Tiwari, Yu Wang","submitted_at":"2024-10-22T12:18:24Z","abstract_excerpt":"Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during inference. While traditional pruning methods have been employed to optimize these models, the retraining process necessitates large-scale training datasets and extensive computational costs to maintain generalization ability, making it neither convenient nor efficient. Recent studies attempt to utilize the similarity of features across adjacent denoising stages "},"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":"2410.16942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T12:18:24Z","cross_cats_sorted":[],"title_canon_sha256":"9f67b3513c07ecf4336f1aa3bea814975ba319ade27b41d0d4e9b62c0ccbeb81","abstract_canon_sha256":"4870d53b5e2614c798ec0a382517de5092374d1a027d5051cc336336dff354e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:09.077564Z","signature_b64":"z8fdNPqx5Qg956ZvQsxaYjsiNGTvMejQHksJBD4A1StbAuXnPXDBVKHqppdrSLAhXesODG5C4dRny7I61rgACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95c25b184c919c780e666753d5c6dba760dc3c50bea614817d99c67e7ad464a9","last_reissued_at":"2026-07-05T09:24:09.077060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:09.077060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashish Sirasao, Bin Wang, Dehua Tang, Dong Li, Emad Barsoum, Fan Jiang, Haowei Zhu, Ji Liu, Jintu Zheng, Jinzhang Peng, Jun-Hai Yong, Lu Tian, Mingjie Lu, Spandan Tiwari, Yu Wang","submitted_at":"2024-10-22T12:18:24Z","abstract_excerpt":"Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during inference. While traditional pruning methods have been employed to optimize these models, the retraining process necessitates large-scale training datasets and extensive computational costs to maintain generalization ability, making it neither convenient nor efficient. Recent studies attempt to utilize the similarity of features across adjacent denoising stages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16942","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/2410.16942/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":"2410.16942","created_at":"2026-07-05T09:24:09.077123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16942v1","created_at":"2026-07-05T09:24:09.077123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16942","created_at":"2026-07-05T09:24:09.077123+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXBFWGCMSGOH","created_at":"2026-07-05T09:24:09.077123+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXBFWGCMSGOHQDTG","created_at":"2026-07-05T09:24:09.077123+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXBFWGCM","created_at":"2026-07-05T09:24:09.077123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16211","citing_title":"Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5","json":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5.json","graph_json":"https://pith.science/api/pith-number/SXBFWGCMSGOHQDTGM5J5LRW3U5/graph.json","events_json":"https://pith.science/api/pith-number/SXBFWGCMSGOHQDTGM5J5LRW3U5/events.json","paper":"https://pith.science/paper/SXBFWGCM"},"agent_actions":{"view_html":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5","download_json":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5.json","view_paper":"https://pith.science/paper/SXBFWGCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16942&json=true","fetch_graph":"https://pith.science/api/pith-number/SXBFWGCMSGOHQDTGM5J5LRW3U5/graph.json","fetch_events":"https://pith.science/api/pith-number/SXBFWGCMSGOHQDTGM5J5LRW3U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5/action/storage_attestation","attest_author":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5/action/author_attestation","sign_citation":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5/action/citation_signature","submit_replication":"https://pith.science/pith/SXBFWGCMSGOHQDTGM5J5LRW3U5/action/replication_record"}},"created_at":"2026-07-05T09:24:09.077123+00:00","updated_at":"2026-07-05T09:24:09.077123+00:00"}