{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QFALXB3OXZT4YVMJRIHXTH4UCF","short_pith_number":"pith:QFALXB3O","schema_version":"1.0","canonical_sha256":"8140bb876ebe67cc55898a0f799f94116fc30f43e19feba80a72ccdf106fa033","source":{"kind":"arxiv","id":"2607.11673","version":1},"attestation_state":"computed","paper":{"title":"ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoquan Chen, Chengzhen Yu, Chunnuo Gong, Chunxue Jia, Fei Yu, Guodong Sun, Hang Zhang, Haozhe Shi, Hongyu Pan, Huan Li, Jiacheng Zhang, Jiawei Zhang, Junnan Lai, Luyang Tang, Mengmeng Du, Mingchao Sun, Mu Xu, Nianfei Fan, Ning Guo, Shixing Yang, Shiying Zeng, Tianjian Ouyang, Wenzheng Chen, Xu Yan, Yang Liu, Yingliang Peng, Yongchang Zhang, Yongze Li, Yuan Liu, Yu Liu, Yumin Liu, Yunwei Zhang, Zengye Ge, Zhan Li, Zheng Zhou, Zhicheng Liu, Zhongxu Sun","submitted_at":"2026-07-13T15:14:48Z","abstract_excerpt":"We present ABot-3DWorld 0, a universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds. At the heart of our framework is a unified Spatial Generative Primitive (SGP), a compact tuple of a high-quality panorama and a spatial point cloud that delivers an efficient description of any 3D space. Multimodal inputs are first lifted into this primitive; a 3D-consistent panoramic video generator then explores the primitive along a planned trajectory; finally, our panoramic video reconstruction engine converts the generated video into a clean, "},"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":"2607.11673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T15:14:48Z","cross_cats_sorted":[],"title_canon_sha256":"13cf9f722e8a881037ccfbf8cf46df3d9cc6cf88273d5e295f9244de5b62ea31","abstract_canon_sha256":"774ef844a92b39aa5526d0dd23adeb41fa1891e2f8ed2e1e57b1a3aaf81acec3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:18.362026Z","signature_b64":"Uy9NPDsrjFtup6LLmi7QPIjBL2DButdJ+asMS+Dmgug15jfDKNgAvsNUf/WYHvrrshyRccTeBQcsbYxOOhW0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8140bb876ebe67cc55898a0f799f94116fc30f43e19feba80a72ccdf106fa033","last_reissued_at":"2026-07-14T02:22:18.361189Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:18.361189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoquan Chen, Chengzhen Yu, Chunnuo Gong, Chunxue Jia, Fei Yu, Guodong Sun, Hang Zhang, Haozhe Shi, Hongyu Pan, Huan Li, Jiacheng Zhang, Jiawei Zhang, Junnan Lai, Luyang Tang, Mengmeng Du, Mingchao Sun, Mu Xu, Nianfei Fan, Ning Guo, Shixing Yang, Shiying Zeng, Tianjian Ouyang, Wenzheng Chen, Xu Yan, Yang Liu, Yingliang Peng, Yongchang Zhang, Yongze Li, Yuan Liu, Yu Liu, Yumin Liu, Yunwei Zhang, Zengye Ge, Zhan Li, Zheng Zhou, Zhicheng Liu, Zhongxu Sun","submitted_at":"2026-07-13T15:14:48Z","abstract_excerpt":"We present ABot-3DWorld 0, a universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds. At the heart of our framework is a unified Spatial Generative Primitive (SGP), a compact tuple of a high-quality panorama and a spatial point cloud that delivers an efficient description of any 3D space. Multimodal inputs are first lifted into this primitive; a 3D-consistent panoramic video generator then explores the primitive along a planned trajectory; finally, our panoramic video reconstruction engine converts the generated video into a clean, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11673","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/2607.11673/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":"2607.11673","created_at":"2026-07-14T02:22:18.361622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11673v1","created_at":"2026-07-14T02:22:18.361622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11673","created_at":"2026-07-14T02:22:18.361622+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFALXB3OXZT4","created_at":"2026-07-14T02:22:18.361622+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFALXB3OXZT4YVMJ","created_at":"2026-07-14T02:22:18.361622+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFALXB3O","created_at":"2026-07-14T02:22:18.361622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF","json":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF.json","graph_json":"https://pith.science/api/pith-number/QFALXB3OXZT4YVMJRIHXTH4UCF/graph.json","events_json":"https://pith.science/api/pith-number/QFALXB3OXZT4YVMJRIHXTH4UCF/events.json","paper":"https://pith.science/paper/QFALXB3O"},"agent_actions":{"view_html":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF","download_json":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF.json","view_paper":"https://pith.science/paper/QFALXB3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11673&json=true","fetch_graph":"https://pith.science/api/pith-number/QFALXB3OXZT4YVMJRIHXTH4UCF/graph.json","fetch_events":"https://pith.science/api/pith-number/QFALXB3OXZT4YVMJRIHXTH4UCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF/action/storage_attestation","attest_author":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF/action/author_attestation","sign_citation":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF/action/citation_signature","submit_replication":"https://pith.science/pith/QFALXB3OXZT4YVMJRIHXTH4UCF/action/replication_record"}},"created_at":"2026-07-14T02:22:18.361622+00:00","updated_at":"2026-07-14T02:22:18.361622+00:00"}