{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VH4QGEXCDXUBDG7VNJRL3COZ4Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"50d81a6eaa10fbb1e7a119b3a3ed7b44dcd81d09b68713a6e7c665771457886a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T13:21:22Z","title_canon_sha256":"a9f84409363b6203c2fbc1e07ccd0d12a7ac15d83ed230f6903a7c69df8a430b"},"schema_version":"1.0","source":{"id":"2605.16990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16990","created_at":"2026-05-20T00:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16990v1","created_at":"2026-05-20T00:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16990","created_at":"2026-05-20T00:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"VH4QGEXCDXUB","created_at":"2026-05-20T00:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"VH4QGEXCDXUBDG7V","created_at":"2026-05-20T00:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"VH4QGEXC","created_at":"2026-05-20T00:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:53caa79238b7b32857b060b00b70910b5958d994410069305a02d9d1ef716ead","target":"graph","created_at":"2026-05-20T00:03:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Extensive evaluations across diverse editing scenarios demonstrate that our method successfully transfers the flexibility of 2D personalization to 3D, achieving state-of-the-art edit faithfulness and identity preservation compared to existing baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The approach assumes that rendering orthogonal views and extracting object-level segmentation masks will allow learning of distinct, composable token embeddings that preserve multi-view consistency when combined with editing prompts (stated in the abstract description of the input processing and two-phase optimization)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DreamEdit3D learns separate token embeddings for segmented object components via two-phase multi-view optimization to enable text-guided 3D editing with consistent image generation and mesh reconstruction."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Personalizing multi-view diffusion models enables text-guided 3D editing with object-level control and preserved consistency."}],"snapshot_sha256":"783ed69174db829ca1bea16a8d4122d83c8a1b6f47cf9296e5eac67cf85bee83"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"19c9629b3e309564290db3bb6e7b9889a9f1c661d62965a2ddae0d50a0a8e56a"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T20:31:33.526693Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T20:31:19.032114Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T19:50:03.341353Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T19:23:44.291164Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.207514Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.296066Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16990/integrity.json","findings":[],"snapshot_sha256":"5500fbc624935198dcf6643432d3e8659cc99d55986c70f526b865ddd6ead77c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the complexities of multi-view consistency and spatial control. Inspired by these 2D advancements, we present a novel personalization method for text-guided 3D editing that enables compositional, object-level control through natural language. Given a 3D input, we render orthogonal views and extract object-level segmentation masks to isolate semantic components. We then learn distinct token embeddings for each component ","authors_text":"Jinxin Ai, Matthias Nie{\\ss}ner, Ziya Erko\\c{c}","cross_cats":[],"headline":"Personalizing multi-view diffusion models enables text-guided 3D editing with object-level control and preserved consistency.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T13:21:22Z","title":"DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing"},"references":{"count":52,"internal_anchors":14,"resolved_work":52,"sample":[{"cited_arxiv_id":"","doi":"10.1145/3610548.3618154","is_internal_anchor":false,"ref_index":1,"title":"In: SIGGRAPH Asia 2023 Conference Papers","work_id":"e9011604-8e04-4abb-8699-4ea5e5063195","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2408.07009 (2024)","work_id":"a1dd317f-8300-4a79-a1d0-92ddd93fa983","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"In- stant3dit: Multiview inpainting for fast editing of 3d objects","work_id":"334cb1af-d967-4b42-8a43-91d705b2480a","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Betker, J., Goh, G., Jing, L., TimBrooks, Wang, J., Li, L., LongOuyang, Jun- tangZhuang, JoyceLee, YufeiGuo, WesamManassra, PrafullaDhariwal, CaseyChu, YunxinJiao, Ramesh, A.: Improving image generati","work_id":"dc86f290-6860-40cf-a624-8dc47ef83d80","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","work_id":"3abb7fd7-a4d5-4eec-a516-50482221a431","year":2022}],"snapshot_sha256":"2cdab04c5b2f980fcaa4eabb9b17030964c0d2a067b70a5579e437a16b0a5bf7"},"source":{"id":"2605.16990","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T20:24:04.921343Z","id":"17c95cdb-2d62-405d-8cf6-72f8fcc2194e","model_set":{"reader":"grok-4.3"},"one_line_summary":"DreamEdit3D learns separate token embeddings for segmented object components via two-phase multi-view optimization to enable text-guided 3D editing with consistent image generation and mesh reconstruction.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Personalizing multi-view diffusion models enables text-guided 3D editing with object-level control and preserved consistency.","strongest_claim":"Extensive evaluations across diverse editing scenarios demonstrate that our method successfully transfers the flexibility of 2D personalization to 3D, achieving state-of-the-art edit faithfulness and identity preservation compared to existing baselines.","weakest_assumption":"The approach assumes that rendering orthogonal views and extracting object-level segmentation masks will allow learning of distinct, composable token embeddings that preserve multi-view consistency when combined with editing prompts (stated in the abstract description of the input processing and two-phase optimization)."}},"verdict_id":"17c95cdb-2d62-405d-8cf6-72f8fcc2194e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4f4174d4bb8622f44a38cad6187252571419989c670ac5843173af96b9cc0210","target":"record","created_at":"2026-05-20T00:03:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"50d81a6eaa10fbb1e7a119b3a3ed7b44dcd81d09b68713a6e7c665771457886a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T13:21:22Z","title_canon_sha256":"a9f84409363b6203c2fbc1e07ccd0d12a7ac15d83ed230f6903a7c69df8a430b"},"schema_version":"1.0","source":{"id":"2605.16990","kind":"arxiv","version":1}},"canonical_sha256":"a9f90312e21de8119bf56a62bd89d9e405da5394cda2912c0f7a9c43d56a8574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9f90312e21de8119bf56a62bd89d9e405da5394cda2912c0f7a9c43d56a8574","first_computed_at":"2026-05-20T00:03:34.824778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:34.824778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8+1Taof/enopCnwzqn8Y9Fvytnc73aLdmTv44v1yk0n6HUaY7WPvsdOyn4qZR9E94a477avdyJoLJj+M4aiAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:34.825658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f4174d4bb8622f44a38cad6187252571419989c670ac5843173af96b9cc0210","sha256:53caa79238b7b32857b060b00b70910b5958d994410069305a02d9d1ef716ead"],"state_sha256":"ad2615f99e641df2bde29383fff9da1b8fa50299a9e84f04c07b4dc9664cc793"}