{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2KWMSI2HO4WNIGE2JJMZJNGTZ5","short_pith_number":"pith:2KWMSI2H","schema_version":"1.0","canonical_sha256":"d2acc92347772cd4189a4a5994b4d3cf5c40516760eedd1d618380c950e663cd","source":{"kind":"arxiv","id":"2508.05899","version":3},"attestation_state":"computed","paper":{"title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chris Callison-Burch, Ruohan Ren, Yue Yang, Zixuan Bian","submitted_at":"2025-08-07T23:23:07Z","abstract_excerpt":"3D scene generation plays a crucial role in gaming, artistic creation, virtual reality, and many other domains. However, current 3D scene design still relies heavily on extensive manual effort from creators, and existing automated methods struggle to generate open-domain scenes or support flexible editing. To address those challenges, we introduce HOLODECK 2.0, an advanced vision-language-guided framework for 3D world generation with support for interactive scene editing based on human feedback. HOLODECK 2.0 can generate diverse and stylistically rich 3D scenes (e.g., realistic, cartoon, anime"},"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":"2508.05899","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T23:23:07Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"ece655208388c00683c71cd938898048f2e15059777ac9160d58eaed7be187d4","abstract_canon_sha256":"48a3c6e0cae2360149f40a9cd069562bf398768f71a4117deea3eb193c8bbeef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:32.592586Z","signature_b64":"9Of5WMU6UqiQOYDgidgG5XAmXp01Beg4FWCW7QZts4sqBIcWI8EUinlHJIeGKjloR8ghsC7nljON021gh77GDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2acc92347772cd4189a4a5994b4d3cf5c40516760eedd1d618380c950e663cd","last_reissued_at":"2026-07-29T00:24:32.591538Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:32.591538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chris Callison-Burch, Ruohan Ren, Yue Yang, Zixuan Bian","submitted_at":"2025-08-07T23:23:07Z","abstract_excerpt":"3D scene generation plays a crucial role in gaming, artistic creation, virtual reality, and many other domains. However, current 3D scene design still relies heavily on extensive manual effort from creators, and existing automated methods struggle to generate open-domain scenes or support flexible editing. To address those challenges, we introduce HOLODECK 2.0, an advanced vision-language-guided framework for 3D world generation with support for interactive scene editing based on human feedback. HOLODECK 2.0 can generate diverse and stylistically rich 3D scenes (e.g., realistic, cartoon, anime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05899","kind":"arxiv","version":3},"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/2508.05899/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":"2508.05899","created_at":"2026-07-29T00:24:32.592014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05899v3","created_at":"2026-07-29T00:24:32.592014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05899","created_at":"2026-07-29T00:24:32.592014+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KWMSI2HO4WN","created_at":"2026-07-29T00:24:32.592014+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KWMSI2HO4WNIGE2","created_at":"2026-07-29T00:24:32.592014+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KWMSI2H","created_at":"2026-07-29T00:24:32.592014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.13035","citing_title":"SceneCritic: A Symbolic Evaluator for 3D Indoor Scene Synthesis","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5","json":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5.json","graph_json":"https://pith.science/api/pith-number/2KWMSI2HO4WNIGE2JJMZJNGTZ5/graph.json","events_json":"https://pith.science/api/pith-number/2KWMSI2HO4WNIGE2JJMZJNGTZ5/events.json","paper":"https://pith.science/paper/2KWMSI2H"},"agent_actions":{"view_html":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5","download_json":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5.json","view_paper":"https://pith.science/paper/2KWMSI2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05899&json=true","fetch_graph":"https://pith.science/api/pith-number/2KWMSI2HO4WNIGE2JJMZJNGTZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/2KWMSI2HO4WNIGE2JJMZJNGTZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5/action/storage_attestation","attest_author":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5/action/author_attestation","sign_citation":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5/action/citation_signature","submit_replication":"https://pith.science/pith/2KWMSI2HO4WNIGE2JJMZJNGTZ5/action/replication_record"}},"created_at":"2026-07-29T00:24:32.592014+00:00","updated_at":"2026-07-29T00:24:32.592014+00:00"}