{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2GKZXU565SV6Q2CSJMM5TIHURL","short_pith_number":"pith:2GKZXU56","schema_version":"1.0","canonical_sha256":"d1959bd3beecabe868524b19d9a0f48aeae618f3a0a28bddd3136db0a5bf621c","source":{"kind":"arxiv","id":"2406.09417","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Score Distillation as a Bridge Between Image Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alexei A. Efros, Angjoo Kanazawa, David McAllister, David W. Jacobs, Jia-Bin Huang, Songwei Ge","submitted_at":"2024-06-13T17:59:58Z","abstract_excerpt":"Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its usefulness in general-purpose applications. In this paper, we make progress toward understanding the behavior of SDS and its variants by viewing them as solving an optimal-cost transport path from a source distribution to a target distribution. Under this new interpretation, these methods seek to transport corrupted images (source) to the natural image distribut"},"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":"2406.09417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:58Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"1e6c12faa7c93fb08ab14b0da20cb383b94d78ecab8fc7fb74cf5d53c932d940","abstract_canon_sha256":"55c35e0c3be6bc4e9143afb706620705cce5712ac0967219df3d059492925a4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:31.021817Z","signature_b64":"RHS+6yjz1sWD3fFe4Q0SKisc3EQrpJE2xPGjnAqh65fswFSd2Plf42LHGBe9m8pY3n8qmC0BKmXo7CsnhgL8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1959bd3beecabe868524b19d9a0f48aeae618f3a0a28bddd3136db0a5bf621c","last_reissued_at":"2026-07-05T09:47:31.021281Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:31.021281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Score Distillation as a Bridge Between Image Distributions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, Alexei A. Efros, Angjoo Kanazawa, David McAllister, David W. Jacobs, Jia-Bin Huang, Songwei Ge","submitted_at":"2024-06-13T17:59:58Z","abstract_excerpt":"Score distillation sampling (SDS) has proven to be an important tool, enabling the use of large-scale diffusion priors for tasks operating in data-poor domains. Unfortunately, SDS has a number of characteristic artifacts that limit its usefulness in general-purpose applications. In this paper, we make progress toward understanding the behavior of SDS and its variants by viewing them as solving an optimal-cost transport path from a source distribution to a target distribution. Under this new interpretation, these methods seek to transport corrupted images (source) to the natural image distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09417","kind":"arxiv","version":2},"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/2406.09417/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":"2406.09417","created_at":"2026-07-05T09:47:31.021342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09417v2","created_at":"2026-07-05T09:47:31.021342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09417","created_at":"2026-07-05T09:47:31.021342+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GKZXU565SV6","created_at":"2026-07-05T09:47:31.021342+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GKZXU565SV6Q2CS","created_at":"2026-07-05T09:47:31.021342+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GKZXU56","created_at":"2026-07-05T09:47:31.021342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL","json":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL.json","graph_json":"https://pith.science/api/pith-number/2GKZXU565SV6Q2CSJMM5TIHURL/graph.json","events_json":"https://pith.science/api/pith-number/2GKZXU565SV6Q2CSJMM5TIHURL/events.json","paper":"https://pith.science/paper/2GKZXU56"},"agent_actions":{"view_html":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL","download_json":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL.json","view_paper":"https://pith.science/paper/2GKZXU56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09417&json=true","fetch_graph":"https://pith.science/api/pith-number/2GKZXU565SV6Q2CSJMM5TIHURL/graph.json","fetch_events":"https://pith.science/api/pith-number/2GKZXU565SV6Q2CSJMM5TIHURL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL/action/storage_attestation","attest_author":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL/action/author_attestation","sign_citation":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL/action/citation_signature","submit_replication":"https://pith.science/pith/2GKZXU565SV6Q2CSJMM5TIHURL/action/replication_record"}},"created_at":"2026-07-05T09:47:31.021342+00:00","updated_at":"2026-07-05T09:47:31.021342+00:00"}