{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UAQFXHMS2TYQ64WXGTWUL7BU7D","short_pith_number":"pith:UAQFXHMS","schema_version":"1.0","canonical_sha256":"a0205b9d92d4f10f72d734ed45fc34f8c358f93dcbec12083bb1636b8b028fca","source":{"kind":"arxiv","id":"2303.12218","version":2},"attestation_state":"computed","paper":{"title":"Compositional 3D Scene Generation using Locally Conditioned Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gordon Wetzstein, Ryan Po","submitted_at":"2023-03-21T22:37:16Z","abstract_excerpt":"Designing complex 3D scenes has been a tedious, manual process requiring domain expertise. Emerging text-to-3D generative models show great promise for making this task more intuitive, but existing approaches are limited to object-level generation. We introduce \\textbf{locally conditioned diffusion} as an approach to compositional scene diffusion, providing control over semantic parts using text prompts and bounding boxes while ensuring seamless transitions between these parts. We demonstrate a score distillation sampling--based text-to-3D synthesis pipeline that enables compositional 3D scene"},"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":"2303.12218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-21T22:37:16Z","cross_cats_sorted":[],"title_canon_sha256":"d04136b171b03cbc58717de78641f2dd563471b3150bdef21b840138eb1cb23d","abstract_canon_sha256":"7941d0084bf17206c57d60c6b90a9740713c0757aeb8895c3539baa671d704af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:53.733060Z","signature_b64":"SDSgXmd9oeM6xWhrHsZbp1DhY6LKt2YLyzNIfmLVM398g05niqARq/bd2eKwpircJOT8CWHsGspOffr8MC5XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0205b9d92d4f10f72d734ed45fc34f8c358f93dcbec12083bb1636b8b028fca","last_reissued_at":"2026-07-05T05:53:53.732637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:53.732637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional 3D Scene Generation using Locally Conditioned Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gordon Wetzstein, Ryan Po","submitted_at":"2023-03-21T22:37:16Z","abstract_excerpt":"Designing complex 3D scenes has been a tedious, manual process requiring domain expertise. Emerging text-to-3D generative models show great promise for making this task more intuitive, but existing approaches are limited to object-level generation. We introduce \\textbf{locally conditioned diffusion} as an approach to compositional scene diffusion, providing control over semantic parts using text prompts and bounding boxes while ensuring seamless transitions between these parts. We demonstrate a score distillation sampling--based text-to-3D synthesis pipeline that enables compositional 3D scene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12218","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/2303.12218/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":"2303.12218","created_at":"2026-07-05T05:53:53.732692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12218v2","created_at":"2026-07-05T05:53:53.732692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12218","created_at":"2026-07-05T05:53:53.732692+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAQFXHMS2TYQ","created_at":"2026-07-05T05:53:53.732692+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAQFXHMS2TYQ64WX","created_at":"2026-07-05T05:53:53.732692+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAQFXHMS","created_at":"2026-07-05T05:53:53.732692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05392","citing_title":"SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2406.02509","citing_title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":190,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D","json":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D.json","graph_json":"https://pith.science/api/pith-number/UAQFXHMS2TYQ64WXGTWUL7BU7D/graph.json","events_json":"https://pith.science/api/pith-number/UAQFXHMS2TYQ64WXGTWUL7BU7D/events.json","paper":"https://pith.science/paper/UAQFXHMS"},"agent_actions":{"view_html":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D","download_json":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D.json","view_paper":"https://pith.science/paper/UAQFXHMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12218&json=true","fetch_graph":"https://pith.science/api/pith-number/UAQFXHMS2TYQ64WXGTWUL7BU7D/graph.json","fetch_events":"https://pith.science/api/pith-number/UAQFXHMS2TYQ64WXGTWUL7BU7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D/action/storage_attestation","attest_author":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D/action/author_attestation","sign_citation":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D/action/citation_signature","submit_replication":"https://pith.science/pith/UAQFXHMS2TYQ64WXGTWUL7BU7D/action/replication_record"}},"created_at":"2026-07-05T05:53:53.732692+00:00","updated_at":"2026-07-05T05:53:53.732692+00:00"}