{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MQ7FIRTWDUNFIGADLF5XUYNCA7","short_pith_number":"pith:MQ7FIRTW","schema_version":"1.0","canonical_sha256":"643e5446761d1a541803597b7a61a207edc98053a0132e5537d35c255bcc2f67","source":{"kind":"arxiv","id":"2410.20723","version":1},"attestation_state":"computed","paper":{"title":"CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfeng Xu, Chensheng Peng, Chongjian Ge, Masayoshi Tomizuka, Mingyu Ding, Ping Luo, Varun Jampani, Wei Zhan, Yuanfeng Ji","submitted_at":"2024-10-28T04:35:14Z","abstract_excerpt":"Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable interactions within a 3D space, a.k.a. compositional 3D generation, presents substantial challenges. This paper introduces CompGS, a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfe"},"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":"2410.20723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T04:35:14Z","cross_cats_sorted":[],"title_canon_sha256":"dda5080015fb39c59361c9437994fd0208e9011757b7b3d148384499c38bbf75","abstract_canon_sha256":"ee4bb402db4a937c023dda6c943a1971cc6a33991f5af5e976d8d8e7ceda644e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:10.012480Z","signature_b64":"6leHcK5a9v9RZiSxtkG+bLpJf4GcucQinq1iB9pQxwkw38U9lWPTetomNP/xptHVC6ePLrildwwNYvv3hvRiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"643e5446761d1a541803597b7a61a207edc98053a0132e5537d35c255bcc2f67","last_reissued_at":"2026-07-05T09:27:10.012049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:10.012049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfeng Xu, Chensheng Peng, Chongjian Ge, Masayoshi Tomizuka, Mingyu Ding, Ping Luo, Varun Jampani, Wei Zhan, Yuanfeng Ji","submitted_at":"2024-10-28T04:35:14Z","abstract_excerpt":"Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable interactions within a 3D space, a.k.a. compositional 3D generation, presents substantial challenges. This paper introduces CompGS, a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20723","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/2410.20723/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":"2410.20723","created_at":"2026-07-05T09:27:10.012108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20723v1","created_at":"2026-07-05T09:27:10.012108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20723","created_at":"2026-07-05T09:27:10.012108+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQ7FIRTWDUNF","created_at":"2026-07-05T09:27:10.012108+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQ7FIRTWDUNFIGAD","created_at":"2026-07-05T09:27:10.012108+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQ7FIRTW","created_at":"2026-07-05T09:27:10.012108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":181,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7","json":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7.json","graph_json":"https://pith.science/api/pith-number/MQ7FIRTWDUNFIGADLF5XUYNCA7/graph.json","events_json":"https://pith.science/api/pith-number/MQ7FIRTWDUNFIGADLF5XUYNCA7/events.json","paper":"https://pith.science/paper/MQ7FIRTW"},"agent_actions":{"view_html":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7","download_json":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7.json","view_paper":"https://pith.science/paper/MQ7FIRTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20723&json=true","fetch_graph":"https://pith.science/api/pith-number/MQ7FIRTWDUNFIGADLF5XUYNCA7/graph.json","fetch_events":"https://pith.science/api/pith-number/MQ7FIRTWDUNFIGADLF5XUYNCA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7/action/storage_attestation","attest_author":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7/action/author_attestation","sign_citation":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7/action/citation_signature","submit_replication":"https://pith.science/pith/MQ7FIRTWDUNFIGADLF5XUYNCA7/action/replication_record"}},"created_at":"2026-07-05T09:27:10.012108+00:00","updated_at":"2026-07-05T09:27:10.012108+00:00"}