{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QBRS2F2JP37K4EKMJJFH4WUUVI","short_pith_number":"pith:QBRS2F2J","schema_version":"1.0","canonical_sha256":"80632d17497efeae114c4a4a7e5a94aa169ee611ae550c27c9847a23ad8734de","source":{"kind":"arxiv","id":"2501.09464","version":1},"attestation_state":"computed","paper":{"title":"Pruning for Sparse Diffusion Models based on Gradient Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ben Wan, Jia Wang, Tianyi Zheng, Yuxiao Wang, Zhaoyu Chen","submitted_at":"2025-01-16T10:55:05Z","abstract_excerpt":"Diffusion Models (DMs) have impressive capabilities among generation models, but are limited to slower inference speeds and higher computational costs. Previous works utilize one-shot structure pruning to derive lightweight DMs from pre-trained ones, but this approach often leads to a significant drop in generation quality and may result in the removal of crucial weights. Thus we propose a iterative pruning method based on gradient flow, including the gradient flow pruning process and the gradient flow pruning criterion. We employ a progressive soft pruning strategy to maintain the continuity "},"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":"2501.09464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T10:55:05Z","cross_cats_sorted":[],"title_canon_sha256":"8d421c10dc3ad6c657b52d6f7b1844cd3f1d86b66c14bcbba9e082504e72f342","abstract_canon_sha256":"adbf99b4c661370b414b5362880f987f6da206c7969799ab9f6d728762f73470"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:47.466861Z","signature_b64":"b2WofiR5Y1fEUmfY1L85FkONwbpr6iOaMW8/4Ee0EkKCOnW9bXJl4Kz0IRpXGU0fFBJz3LG62V3FhSkxB8EMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80632d17497efeae114c4a4a7e5a94aa169ee611ae550c27c9847a23ad8734de","last_reissued_at":"2026-07-05T10:01:47.466268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:47.466268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pruning for Sparse Diffusion Models based on Gradient Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ben Wan, Jia Wang, Tianyi Zheng, Yuxiao Wang, Zhaoyu Chen","submitted_at":"2025-01-16T10:55:05Z","abstract_excerpt":"Diffusion Models (DMs) have impressive capabilities among generation models, but are limited to slower inference speeds and higher computational costs. Previous works utilize one-shot structure pruning to derive lightweight DMs from pre-trained ones, but this approach often leads to a significant drop in generation quality and may result in the removal of crucial weights. Thus we propose a iterative pruning method based on gradient flow, including the gradient flow pruning process and the gradient flow pruning criterion. We employ a progressive soft pruning strategy to maintain the continuity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09464","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/2501.09464/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":"2501.09464","created_at":"2026-07-05T10:01:47.466356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09464v1","created_at":"2026-07-05T10:01:47.466356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09464","created_at":"2026-07-05T10:01:47.466356+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBRS2F2JP37K","created_at":"2026-07-05T10:01:47.466356+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBRS2F2JP37K4EKM","created_at":"2026-07-05T10:01:47.466356+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBRS2F2J","created_at":"2026-07-05T10:01:47.466356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI","json":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI.json","graph_json":"https://pith.science/api/pith-number/QBRS2F2JP37K4EKMJJFH4WUUVI/graph.json","events_json":"https://pith.science/api/pith-number/QBRS2F2JP37K4EKMJJFH4WUUVI/events.json","paper":"https://pith.science/paper/QBRS2F2J"},"agent_actions":{"view_html":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI","download_json":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI.json","view_paper":"https://pith.science/paper/QBRS2F2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09464&json=true","fetch_graph":"https://pith.science/api/pith-number/QBRS2F2JP37K4EKMJJFH4WUUVI/graph.json","fetch_events":"https://pith.science/api/pith-number/QBRS2F2JP37K4EKMJJFH4WUUVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI/action/storage_attestation","attest_author":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI/action/author_attestation","sign_citation":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI/action/citation_signature","submit_replication":"https://pith.science/pith/QBRS2F2JP37K4EKMJJFH4WUUVI/action/replication_record"}},"created_at":"2026-07-05T10:01:47.466356+00:00","updated_at":"2026-07-05T10:01:47.466356+00:00"}