{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TGVPL6KEXUZUY7JNG5LIEMFVKV","short_pith_number":"pith:TGVPL6KE","schema_version":"1.0","canonical_sha256":"99aaf5f944bd334c7d2d37568230b5557bb97c7be16543c54f8c9eeb499c1fa9","source":{"kind":"arxiv","id":"2412.04380","version":3},"attestation_state":"computed","paper":{"title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang, Yuqi Wu","submitted_at":"2024-12-05T17:57:09Z","abstract_excerpt":"3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception. Most existing methods focus on offline perception from one or a few views and cannot be applied to embodied agents that demand to gradually perceive the scene through progressive embodied exploration. In this paper, we formulate an embodied 3D occupancy prediction task to target this practical scenario and propose a Gaussian-based EmbodiedOcc framework to accomplish it. We initialize the global scene with uniform 3D semantic Gaussians and progressively upda"},"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":"2412.04380","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:57:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6e5a43b921cd007e8ef078c64b6e2c32e1254df09fc310b367151cdc369b7fe1","abstract_canon_sha256":"3095ce4a4b48a6ca685455ff73caace59d814afa371300a5f2ce223ca2fc9fc0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:22.515245Z","signature_b64":"PnkP87vwLhZ+4/DjEACysx8WMoOTw8GCjeUuvbVyGi42rAywfMObUxPOGppbdUOZh7fcGgp0XRYN2nBPHi5bDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99aaf5f944bd334c7d2d37568230b5557bb97c7be16543c54f8c9eeb499c1fa9","last_reissued_at":"2026-07-05T11:58:22.514754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:22.514754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang, Yuqi Wu","submitted_at":"2024-12-05T17:57:09Z","abstract_excerpt":"3D occupancy prediction provides a comprehensive description of the surrounding scenes and has become an essential task for 3D perception. Most existing methods focus on offline perception from one or a few views and cannot be applied to embodied agents that demand to gradually perceive the scene through progressive embodied exploration. In this paper, we formulate an embodied 3D occupancy prediction task to target this practical scenario and propose a Gaussian-based EmbodiedOcc framework to accomplish it. We initialize the global scene with uniform 3D semantic Gaussians and progressively upda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04380","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/2412.04380/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":"2412.04380","created_at":"2026-07-05T11:58:22.514813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04380v3","created_at":"2026-07-05T11:58:22.514813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04380","created_at":"2026-07-05T11:58:22.514813+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGVPL6KEXUZU","created_at":"2026-07-05T11:58:22.514813+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGVPL6KEXUZUY7JN","created_at":"2026-07-05T11:58:22.514813+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGVPL6KE","created_at":"2026-07-05T11:58:22.514813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.22667","citing_title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11539","citing_title":"Streaming 4D Visual Geometry Transformer","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27578","citing_title":"World2Minecraft: Occupancy-Driven Simulated Scenes Construction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13476","citing_title":"RobotPan: A 360$^\\circ$ Surround-View Robotic Vision System for Embodied Perception","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV","json":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV.json","graph_json":"https://pith.science/api/pith-number/TGVPL6KEXUZUY7JNG5LIEMFVKV/graph.json","events_json":"https://pith.science/api/pith-number/TGVPL6KEXUZUY7JNG5LIEMFVKV/events.json","paper":"https://pith.science/paper/TGVPL6KE"},"agent_actions":{"view_html":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV","download_json":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV.json","view_paper":"https://pith.science/paper/TGVPL6KE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04380&json=true","fetch_graph":"https://pith.science/api/pith-number/TGVPL6KEXUZUY7JNG5LIEMFVKV/graph.json","fetch_events":"https://pith.science/api/pith-number/TGVPL6KEXUZUY7JNG5LIEMFVKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV/action/storage_attestation","attest_author":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV/action/author_attestation","sign_citation":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV/action/citation_signature","submit_replication":"https://pith.science/pith/TGVPL6KEXUZUY7JNG5LIEMFVKV/action/replication_record"}},"created_at":"2026-07-05T11:58:22.514813+00:00","updated_at":"2026-07-05T11:58:22.514813+00:00"}