{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B4ASGIDASTGFXOWR6WZZPVLCPV","short_pith_number":"pith:B4ASGIDA","schema_version":"1.0","canonical_sha256":"0f0123206094cc5bbad1f5b397d5627d583ee4d7454d48aea7abecb93d278ba8","source":{"kind":"arxiv","id":"2410.14919","version":4},"attestation_state":"computed","paper":{"title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Huang, Huangjie Zheng, Mingyuan Zhou, Yi Gu, Zhendong Wang","submitted_at":"2024-10-19T00:33:51Z","abstract_excerpt":"Score identity Distillation (SiD) is a data-free method that has achieved SOTA performance in image generation by leveraging only a pretrained diffusion model, without requiring any training data. However, its ultimate performance is constrained by how accurate the pretrained model captures the true data scores at different stages of the diffusion process. In this paper, we introduce SiDA (SiD with Adversarial Loss), which not only enhances generation quality but also improves distillation efficiency by incorporating real images and adversarial loss. SiDA utilizes the encoder from the generato"},"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":"2410.14919","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T00:33:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"356b48fc24b351956246262ad8d897cc35c805d1c6ceebeca6d197244d9a108b","abstract_canon_sha256":"834b2f339376128a1d7ba9be6404c4192e24080d8688f45e0da42bab5c438ebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:45.113886Z","signature_b64":"yafnFjp3OrKXe9gt3aJ2wQKSclT8cPxlsie7g1HtPaDzf+Cp+fHds+rZcVcPIWCnymCbHRi3RR3aV1olCQ3MDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f0123206094cc5bbad1f5b397d5627d583ee4d7454d48aea7abecb93d278ba8","last_reissued_at":"2026-07-05T09:53:45.113410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:45.113410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Huang, Huangjie Zheng, Mingyuan Zhou, Yi Gu, Zhendong Wang","submitted_at":"2024-10-19T00:33:51Z","abstract_excerpt":"Score identity Distillation (SiD) is a data-free method that has achieved SOTA performance in image generation by leveraging only a pretrained diffusion model, without requiring any training data. However, its ultimate performance is constrained by how accurate the pretrained model captures the true data scores at different stages of the diffusion process. In this paper, we introduce SiDA (SiD with Adversarial Loss), which not only enhances generation quality but also improves distillation efficiency by incorporating real images and adversarial loss. SiDA utilizes the encoder from the generato"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14919","kind":"arxiv","version":4},"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/2410.14919/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":"2410.14919","created_at":"2026-07-05T09:53:45.113468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14919v4","created_at":"2026-07-05T09:53:45.113468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14919","created_at":"2026-07-05T09:53:45.113468+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4ASGIDASTGF","created_at":"2026-07-05T09:53:45.113468+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4ASGIDASTGFXOWR","created_at":"2026-07-05T09:53:45.113468+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4ASGIDA","created_at":"2026-07-05T09:53:45.113468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06335","citing_title":"Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25042","citing_title":"Unbiased Diffusion Variational Inversion via Principled Posterior Matching","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03139","citing_title":"Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV","json":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV.json","graph_json":"https://pith.science/api/pith-number/B4ASGIDASTGFXOWR6WZZPVLCPV/graph.json","events_json":"https://pith.science/api/pith-number/B4ASGIDASTGFXOWR6WZZPVLCPV/events.json","paper":"https://pith.science/paper/B4ASGIDA"},"agent_actions":{"view_html":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV","download_json":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV.json","view_paper":"https://pith.science/paper/B4ASGIDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14919&json=true","fetch_graph":"https://pith.science/api/pith-number/B4ASGIDASTGFXOWR6WZZPVLCPV/graph.json","fetch_events":"https://pith.science/api/pith-number/B4ASGIDASTGFXOWR6WZZPVLCPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV/action/storage_attestation","attest_author":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV/action/author_attestation","sign_citation":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV/action/citation_signature","submit_replication":"https://pith.science/pith/B4ASGIDASTGFXOWR6WZZPVLCPV/action/replication_record"}},"created_at":"2026-07-05T09:53:45.113468+00:00","updated_at":"2026-07-05T09:53:45.113468+00:00"}