{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SMAYSQGLQICZ26BUJO3HMQAINT","short_pith_number":"pith:SMAYSQGL","schema_version":"1.0","canonical_sha256":"93018940cb82059d78344bb67640086ceae9a4584d4cf209bf3e1baf52ee6301","source":{"kind":"arxiv","id":"2406.08953","version":1},"attestation_state":"computed","paper":{"title":"Preserving Identity with Variational Score for General-purpose 3D Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Duong H. Le, Jiasen Lu, Stephan Mandt, Tuan Pham, Wei-Chiu Ma","submitted_at":"2024-06-13T09:32:40Z","abstract_excerpt":"We present Piva (Preserving Identity with Variational Score Distillation), a novel optimization-based method for editing images and 3D models based on diffusion models. Specifically, our approach is inspired by the recently proposed method for 2D image editing - Delta Denoising Score (DDS). We pinpoint the limitations in DDS for 2D and 3D editing, which causes detail loss and over-saturation. To address this, we propose an additional score distillation term that enforces identity preservation. This results in a more stable editing process, gradually optimizing NeRF models to match target promp"},"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":"2406.08953","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T09:32:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d81be5083680a0cfd847a333282cff172821787150d0b42885c5808578bfd626","abstract_canon_sha256":"47aff51d5a32b5f886064c86ca89dbabe197fe640c4e698bd7337528e524feb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:26.535252Z","signature_b64":"LXPZcwRjEI1PDshzBCag+QqyWwRrEbTs/NcMCSFqbZ0X4feuV/iQaQV11D2XcTZii7M74e4g5KD2/8Kyj+8JAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93018940cb82059d78344bb67640086ceae9a4584d4cf209bf3e1baf52ee6301","last_reissued_at":"2026-07-05T08:31:26.534826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:26.534826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preserving Identity with Variational Score for General-purpose 3D Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Duong H. Le, Jiasen Lu, Stephan Mandt, Tuan Pham, Wei-Chiu Ma","submitted_at":"2024-06-13T09:32:40Z","abstract_excerpt":"We present Piva (Preserving Identity with Variational Score Distillation), a novel optimization-based method for editing images and 3D models based on diffusion models. Specifically, our approach is inspired by the recently proposed method for 2D image editing - Delta Denoising Score (DDS). We pinpoint the limitations in DDS for 2D and 3D editing, which causes detail loss and over-saturation. To address this, we propose an additional score distillation term that enforces identity preservation. This results in a more stable editing process, gradually optimizing NeRF models to match target promp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08953","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/2406.08953/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":"2406.08953","created_at":"2026-07-05T08:31:26.534893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08953v1","created_at":"2026-07-05T08:31:26.534893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08953","created_at":"2026-07-05T08:31:26.534893+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMAYSQGLQICZ","created_at":"2026-07-05T08:31:26.534893+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMAYSQGLQICZ26BU","created_at":"2026-07-05T08:31:26.534893+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMAYSQGL","created_at":"2026-07-05T08:31:26.534893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07187","citing_title":"EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT","json":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT.json","graph_json":"https://pith.science/api/pith-number/SMAYSQGLQICZ26BUJO3HMQAINT/graph.json","events_json":"https://pith.science/api/pith-number/SMAYSQGLQICZ26BUJO3HMQAINT/events.json","paper":"https://pith.science/paper/SMAYSQGL"},"agent_actions":{"view_html":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT","download_json":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT.json","view_paper":"https://pith.science/paper/SMAYSQGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08953&json=true","fetch_graph":"https://pith.science/api/pith-number/SMAYSQGLQICZ26BUJO3HMQAINT/graph.json","fetch_events":"https://pith.science/api/pith-number/SMAYSQGLQICZ26BUJO3HMQAINT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT/action/storage_attestation","attest_author":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT/action/author_attestation","sign_citation":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT/action/citation_signature","submit_replication":"https://pith.science/pith/SMAYSQGLQICZ26BUJO3HMQAINT/action/replication_record"}},"created_at":"2026-07-05T08:31:26.534893+00:00","updated_at":"2026-07-05T08:31:26.534893+00:00"}