{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X42CA4KZX2BKOEITWYP6YJGKXG","short_pith_number":"pith:X42CA4KZ","schema_version":"1.0","canonical_sha256":"bf34207159be82a71113b61fec24cab98e89d20afdaa5dfc5fd6a39a71d398d1","source":{"kind":"arxiv","id":"2411.15113","version":1},"attestation_state":"computed","paper":{"title":"Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Samarth N Ramesh, Zhixue Zhao","submitted_at":"2024-11-22T18:29:37Z","abstract_excerpt":"As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on post-training pruning of Stable Diffusion 2, addressing the critical need for model compression in text-to-image domain. Our study tackles the pruning techniques for the previously unexplored multi-modal generation models, and particularly examines the pruning impact on the textual component and the image generation component separately. We conduct a comprehensive compa"},"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":"2411.15113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T18:29:37Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fb74ec9ed6cbc3e3c04f07f5aba89ed524b5f16202d08d01961e06d8c46d73c4","abstract_canon_sha256":"31f31111179620bab47f30f1cb06788e60c1f5aad9db6e3280841774f1b66f6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:16.491434Z","signature_b64":"jq6fAMaOF6vnuxh0dlTyXe7mLQD1PXDebTGHm2aDL4YYx5NkIzNvtrvH2orJejXlrAbHV1mQSUme9dr5eIfnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf34207159be82a71113b61fec24cab98e89d20afdaa5dfc5fd6a39a71d398d1","last_reissued_at":"2026-07-05T09:39:16.491088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:16.491088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Samarth N Ramesh, Zhixue Zhao","submitted_at":"2024-11-22T18:29:37Z","abstract_excerpt":"As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on post-training pruning of Stable Diffusion 2, addressing the critical need for model compression in text-to-image domain. Our study tackles the pruning techniques for the previously unexplored multi-modal generation models, and particularly examines the pruning impact on the textual component and the image generation component separately. We conduct a comprehensive compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15113","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/2411.15113/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":"2411.15113","created_at":"2026-07-05T09:39:16.491144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15113v1","created_at":"2026-07-05T09:39:16.491144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15113","created_at":"2026-07-05T09:39:16.491144+00:00"},{"alias_kind":"pith_short_12","alias_value":"X42CA4KZX2BK","created_at":"2026-07-05T09:39:16.491144+00:00"},{"alias_kind":"pith_short_16","alias_value":"X42CA4KZX2BKOEIT","created_at":"2026-07-05T09:39:16.491144+00:00"},{"alias_kind":"pith_short_8","alias_value":"X42CA4KZ","created_at":"2026-07-05T09:39:16.491144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06335","citing_title":"Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG","json":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG.json","graph_json":"https://pith.science/api/pith-number/X42CA4KZX2BKOEITWYP6YJGKXG/graph.json","events_json":"https://pith.science/api/pith-number/X42CA4KZX2BKOEITWYP6YJGKXG/events.json","paper":"https://pith.science/paper/X42CA4KZ"},"agent_actions":{"view_html":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG","download_json":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG.json","view_paper":"https://pith.science/paper/X42CA4KZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15113&json=true","fetch_graph":"https://pith.science/api/pith-number/X42CA4KZX2BKOEITWYP6YJGKXG/graph.json","fetch_events":"https://pith.science/api/pith-number/X42CA4KZX2BKOEITWYP6YJGKXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG/action/storage_attestation","attest_author":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG/action/author_attestation","sign_citation":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG/action/citation_signature","submit_replication":"https://pith.science/pith/X42CA4KZX2BKOEITWYP6YJGKXG/action/replication_record"}},"created_at":"2026-07-05T09:39:16.491144+00:00","updated_at":"2026-07-05T09:39:16.491144+00:00"}