{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZSTI2NVMPTSVAKLLYOUKRIULGD","short_pith_number":"pith:ZSTI2NVM","schema_version":"1.0","canonical_sha256":"cca68d36ac7ce550296bc3a8a8a28b30c26ed38900181f092070667d25ba04fc","source":{"kind":"arxiv","id":"2312.09305","version":2},"attestation_state":"computed","paper":{"title":"Stable Score Distillation for High-Quality 3D Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boshi Tang, Jianan Wang, Lei Zhang, Zhiyong Wu","submitted_at":"2023-12-14T19:18:38Z","abstract_excerpt":"Although Score Distillation Sampling (SDS) has exhibited remarkable performance in conditional 3D content generation, a comprehensive understanding of its formulation is still lacking, hindering the development of 3D generation. In this work, we decompose SDS as a combination of three functional components, namely mode-seeking, mode-disengaging and variance-reducing terms, analyzing the properties of each. We show that problems such as over-smoothness and implausibility result from the intrinsic deficiency of the first two terms and propose a more advanced variance-reducing term than that intr"},"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":"2312.09305","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T19:18:38Z","cross_cats_sorted":[],"title_canon_sha256":"f06c0fcb3926c2aca75bb205df8bb50c3789ee9855970a3e76edb32fbe8fb6a4","abstract_canon_sha256":"37563bf76f759cf66f41f11c97e23d53f4e6a6cd4f403a26dad0c7b3ea42743e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:22.570419Z","signature_b64":"+GN8vPwqNXwh8h87YAg8WIyaLABQFndS+8WoU9nG4zkA2JNzVCN5ECHuJCRKmfDo8W6lqDodIrE7IjAjYzyUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cca68d36ac7ce550296bc3a8a8a28b30c26ed38900181f092070667d25ba04fc","last_reissued_at":"2026-07-05T07:42:22.569921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:22.569921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Score Distillation for High-Quality 3D Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boshi Tang, Jianan Wang, Lei Zhang, Zhiyong Wu","submitted_at":"2023-12-14T19:18:38Z","abstract_excerpt":"Although Score Distillation Sampling (SDS) has exhibited remarkable performance in conditional 3D content generation, a comprehensive understanding of its formulation is still lacking, hindering the development of 3D generation. In this work, we decompose SDS as a combination of three functional components, namely mode-seeking, mode-disengaging and variance-reducing terms, analyzing the properties of each. We show that problems such as over-smoothness and implausibility result from the intrinsic deficiency of the first two terms and propose a more advanced variance-reducing term than that intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09305","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/2312.09305/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":"2312.09305","created_at":"2026-07-05T07:42:22.569987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09305v2","created_at":"2026-07-05T07:42:22.569987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09305","created_at":"2026-07-05T07:42:22.569987+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSTI2NVMPTSV","created_at":"2026-07-05T07:42:22.569987+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSTI2NVMPTSVAKLL","created_at":"2026-07-05T07:42:22.569987+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSTI2NVM","created_at":"2026-07-05T07:42:22.569987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05163","citing_title":"PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD","json":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD.json","graph_json":"https://pith.science/api/pith-number/ZSTI2NVMPTSVAKLLYOUKRIULGD/graph.json","events_json":"https://pith.science/api/pith-number/ZSTI2NVMPTSVAKLLYOUKRIULGD/events.json","paper":"https://pith.science/paper/ZSTI2NVM"},"agent_actions":{"view_html":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD","download_json":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD.json","view_paper":"https://pith.science/paper/ZSTI2NVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09305&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSTI2NVMPTSVAKLLYOUKRIULGD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSTI2NVMPTSVAKLLYOUKRIULGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD/action/storage_attestation","attest_author":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD/action/author_attestation","sign_citation":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD/action/citation_signature","submit_replication":"https://pith.science/pith/ZSTI2NVMPTSVAKLLYOUKRIULGD/action/replication_record"}},"created_at":"2026-07-05T07:42:22.569987+00:00","updated_at":"2026-07-05T07:42:22.569987+00:00"}