{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UCFNUPMXXMGCU2ZRSZJWNZAP5X","short_pith_number":"pith:UCFNUPMX","schema_version":"1.0","canonical_sha256":"a08ada3d97bb0c2a6b31965366e40fedd46a20c479cd37a161646e84f0c72eda","source":{"kind":"arxiv","id":"2305.10924","version":3},"attestation_state":"computed","paper":{"title":"Structural Pruning for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Gongfan Fang, Xinchao Wang, Xinyin Ma","submitted_at":"2023-05-18T12:38:21Z","abstract_excerpt":"Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails significant computational overhead during both training and inference. To tackle this challenge, we present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones, without the need for extensive re-training. The essence of Diff-Pruning is encapsulated in a Taylor expansion over pruned timesteps, a proce"},"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":"2305.10924","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-18T12:38:21Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ef3d95ece3f307c079bd4337ec848039613935cbe1af1bb302520de390aa9b2c","abstract_canon_sha256":"cf22f6087e831e453bcb96d909c74a52f7b356f402c831396096a0dc615e1a1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:54.933223Z","signature_b64":"TMph7X31uBdYZaX8SGs4UdrFNMIcghf+z4ldvpd7WSFqlOClhHmMXZj+mSao/1SnjHJxhXaOVlVTCUjmxTodDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a08ada3d97bb0c2a6b31965366e40fedd46a20c479cd37a161646e84f0c72eda","last_reissued_at":"2026-07-05T06:55:54.932843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:54.932843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structural Pruning for Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Gongfan Fang, Xinchao Wang, Xinyin Ma","submitted_at":"2023-05-18T12:38:21Z","abstract_excerpt":"Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails significant computational overhead during both training and inference. To tackle this challenge, we present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones, without the need for extensive re-training. The essence of Diff-Pruning is encapsulated in a Taylor expansion over pruned timesteps, a proce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10924","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/2305.10924/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":"2305.10924","created_at":"2026-07-05T06:55:54.932898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10924v3","created_at":"2026-07-05T06:55:54.932898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10924","created_at":"2026-07-05T06:55:54.932898+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCFNUPMXXMGC","created_at":"2026-07-05T06:55:54.932898+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCFNUPMXXMGCU2ZR","created_at":"2026-07-05T06:55:54.932898+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCFNUPMX","created_at":"2026-07-05T06:55:54.932898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27089","citing_title":"TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and Editing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26769","citing_title":"ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12575","citing_title":"High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21042","citing_title":"Dynamic Video Generation: Shaping Video Generation Across Time and Space","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05398","citing_title":"2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05449","citing_title":"DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28049","citing_title":"Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12668","citing_title":"OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X","json":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X.json","graph_json":"https://pith.science/api/pith-number/UCFNUPMXXMGCU2ZRSZJWNZAP5X/graph.json","events_json":"https://pith.science/api/pith-number/UCFNUPMXXMGCU2ZRSZJWNZAP5X/events.json","paper":"https://pith.science/paper/UCFNUPMX"},"agent_actions":{"view_html":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X","download_json":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X.json","view_paper":"https://pith.science/paper/UCFNUPMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10924&json=true","fetch_graph":"https://pith.science/api/pith-number/UCFNUPMXXMGCU2ZRSZJWNZAP5X/graph.json","fetch_events":"https://pith.science/api/pith-number/UCFNUPMXXMGCU2ZRSZJWNZAP5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X/action/storage_attestation","attest_author":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X/action/author_attestation","sign_citation":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X/action/citation_signature","submit_replication":"https://pith.science/pith/UCFNUPMXXMGCU2ZRSZJWNZAP5X/action/replication_record"}},"created_at":"2026-07-05T06:55:54.932898+00:00","updated_at":"2026-07-05T06:55:54.932898+00:00"}