{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OOPYC2MMRSGB35XDRRDEU4KRMH","short_pith_number":"pith:OOPYC2MM","schema_version":"1.0","canonical_sha256":"739f81698c8c8c1df6e38c464a715161e7d32609af0bc4314b9c3076f96cde03","source":{"kind":"arxiv","id":"2507.09144","version":2},"attestation_state":"computed","paper":{"title":"$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxuan Wang, Ping Wei, Ruijie Zhang, Shuaijia Chen, Zhimin Liao, Ziyang Ren","submitted_at":"2025-07-12T05:14:39Z","abstract_excerpt":"Forecasting the evolution of 3D scenes and generating unseen scenarios via occupancy-based world models offers substantial potential for addressing corner cases in autonomous driving systems. While tokenization has revolutionized image and video generation, efficiently tokenizing complex 3D scenes remains a critical challenge for 3D world models. To address this, we propose $I^{2}$-World, an efficient framework for 4D occupancy forecasting. Our method decouples scene tokenization into intra-scene and inter-scene tokenizers. The intra-scene tokenizer employs a multi-scale residual quantization "},"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":"2507.09144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-12T05:14:39Z","cross_cats_sorted":[],"title_canon_sha256":"1ce24c2d3dc63dca31f13ba2e65625da8a5425ed6b2bf1c8785b4b84e356fed9","abstract_canon_sha256":"b044bd2efe8ce9558056d47edb61da5aea8909b7c3ee0af3ae092e10810b2bc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:25.847531Z","signature_b64":"iU794mSgiAVxBjrMPOTq2wAs35XjjZB89lNOXzFyjMmZNEf8Mz4bBWmcOtjZ0NkDfdfkbZ4aOteDB1ps4NeAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"739f81698c8c8c1df6e38c464a715161e7d32609af0bc4314b9c3076f96cde03","last_reissued_at":"2026-07-05T11:47:25.847017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:25.847017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoxuan Wang, Ping Wei, Ruijie Zhang, Shuaijia Chen, Zhimin Liao, Ziyang Ren","submitted_at":"2025-07-12T05:14:39Z","abstract_excerpt":"Forecasting the evolution of 3D scenes and generating unseen scenarios via occupancy-based world models offers substantial potential for addressing corner cases in autonomous driving systems. While tokenization has revolutionized image and video generation, efficiently tokenizing complex 3D scenes remains a critical challenge for 3D world models. To address this, we propose $I^{2}$-World, an efficient framework for 4D occupancy forecasting. Our method decouples scene tokenization into intra-scene and inter-scene tokenizers. The intra-scene tokenizer employs a multi-scale residual quantization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09144","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/2507.09144/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":"2507.09144","created_at":"2026-07-05T11:47:25.847079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09144v2","created_at":"2026-07-05T11:47:25.847079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09144","created_at":"2026-07-05T11:47:25.847079+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOPYC2MMRSGB","created_at":"2026-07-05T11:47:25.847079+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOPYC2MMRSGB35XD","created_at":"2026-07-05T11:47:25.847079+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOPYC2MM","created_at":"2026-07-05T11:47:25.847079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30421","citing_title":"OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22039","citing_title":"SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH","json":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH.json","graph_json":"https://pith.science/api/pith-number/OOPYC2MMRSGB35XDRRDEU4KRMH/graph.json","events_json":"https://pith.science/api/pith-number/OOPYC2MMRSGB35XDRRDEU4KRMH/events.json","paper":"https://pith.science/paper/OOPYC2MM"},"agent_actions":{"view_html":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH","download_json":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH.json","view_paper":"https://pith.science/paper/OOPYC2MM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09144&json=true","fetch_graph":"https://pith.science/api/pith-number/OOPYC2MMRSGB35XDRRDEU4KRMH/graph.json","fetch_events":"https://pith.science/api/pith-number/OOPYC2MMRSGB35XDRRDEU4KRMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH/action/storage_attestation","attest_author":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH/action/author_attestation","sign_citation":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH/action/citation_signature","submit_replication":"https://pith.science/pith/OOPYC2MMRSGB35XDRRDEU4KRMH/action/replication_record"}},"created_at":"2026-07-05T11:47:25.847079+00:00","updated_at":"2026-07-05T11:47:25.847079+00:00"}