{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PSDZ6KV6XPCSBCT4EFMUFD4F2P","short_pith_number":"pith:PSDZ6KV6","schema_version":"1.0","canonical_sha256":"7c879f2abebbc5208a7c2159428f85d3ca563654ac86f3f68408f94a1408e8d1","source":{"kind":"arxiv","id":"2507.13985","version":2},"attestation_state":"computed","paper":{"title":"DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Li, Kun Lan, Lin Wang, Pan Hui, Peng Yuan Zhou, Yong Liao, Yuli Tian","submitted_at":"2025-07-18T14:45:54Z","abstract_excerpt":"Generating 3D scenes from natural language holds great promise for applications in gaming, film, and design. However, existing methods struggle with automation, 3D consistency, and fine-grained control. We present DreamScene, an end-to-end framework for high-quality and editable 3D scene generation from text or dialogue. DreamScene begins with a scene planning module, where a GPT-4 agent infers object semantics and spatial constraints to construct a hybrid graph. A graph-based placement algorithm then produces a structured, collision-free layout. Based on this layout, Formation Pattern Samplin"},"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":"2507.13985","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-18T14:45:54Z","cross_cats_sorted":[],"title_canon_sha256":"3fc5039621af2aa7c2cb9f27728b2522a781da4ad5d4c9afc8b19d7e14dd5e6b","abstract_canon_sha256":"3d8ccdf0ce0b2523b0a3007dedfff9bc44f1316cdba8b6f1b3bc38c372d9ccff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:51.821803Z","signature_b64":"M2PJCfux42rw+hNfXfB+Pwfua+bM8ccav7oqJZygQwCFcFldWbypQog+moLqILNmux9AtcNDezDE3DlXakNvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c879f2abebbc5208a7c2159428f85d3ca563654ac86f3f68408f94a1408e8d1","last_reissued_at":"2026-07-05T11:44:51.821386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:51.821386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamScene: 3D Gaussian-based End-to-end Text-to-3D Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Li, Kun Lan, Lin Wang, Pan Hui, Peng Yuan Zhou, Yong Liao, Yuli Tian","submitted_at":"2025-07-18T14:45:54Z","abstract_excerpt":"Generating 3D scenes from natural language holds great promise for applications in gaming, film, and design. However, existing methods struggle with automation, 3D consistency, and fine-grained control. We present DreamScene, an end-to-end framework for high-quality and editable 3D scene generation from text or dialogue. DreamScene begins with a scene planning module, where a GPT-4 agent infers object semantics and spatial constraints to construct a hybrid graph. A graph-based placement algorithm then produces a structured, collision-free layout. Based on this layout, Formation Pattern Samplin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13985","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/2507.13985/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":"2507.13985","created_at":"2026-07-05T11:44:51.821439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13985v2","created_at":"2026-07-05T11:44:51.821439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13985","created_at":"2026-07-05T11:44:51.821439+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSDZ6KV6XPCS","created_at":"2026-07-05T11:44:51.821439+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSDZ6KV6XPCSBCT4","created_at":"2026-07-05T11:44:51.821439+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSDZ6KV6","created_at":"2026-07-05T11:44:51.821439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.26661","citing_title":"GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P","json":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P.json","graph_json":"https://pith.science/api/pith-number/PSDZ6KV6XPCSBCT4EFMUFD4F2P/graph.json","events_json":"https://pith.science/api/pith-number/PSDZ6KV6XPCSBCT4EFMUFD4F2P/events.json","paper":"https://pith.science/paper/PSDZ6KV6"},"agent_actions":{"view_html":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P","download_json":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P.json","view_paper":"https://pith.science/paper/PSDZ6KV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13985&json=true","fetch_graph":"https://pith.science/api/pith-number/PSDZ6KV6XPCSBCT4EFMUFD4F2P/graph.json","fetch_events":"https://pith.science/api/pith-number/PSDZ6KV6XPCSBCT4EFMUFD4F2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P/action/storage_attestation","attest_author":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P/action/author_attestation","sign_citation":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P/action/citation_signature","submit_replication":"https://pith.science/pith/PSDZ6KV6XPCSBCT4EFMUFD4F2P/action/replication_record"}},"created_at":"2026-07-05T11:44:51.821439+00:00","updated_at":"2026-07-05T11:44:51.821439+00:00"}