{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6B6AE3MHWPP6BHXFPAZJZECBPN","short_pith_number":"pith:6B6AE3MH","schema_version":"1.0","canonical_sha256":"f07c026d87b3dfe09ee578329c90417b40097e27e5475ef3f202f28477771ff9","source":{"kind":"arxiv","id":"2108.04097","version":4},"attestation_state":"computed","paper":{"title":"Deep Learning for Embodied Vision Navigation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Fengda Zhu, Vincent CS Lee, Xiaodan Liang, Xiaojun Chang, Yi Zhu","submitted_at":"2021-07-07T12:09:04Z","abstract_excerpt":"\"Embodied visual navigation\" problem requires an agent to navigate in a 3D environment mainly rely on its first-person observation. This problem has attracted rising attention in recent years due to its wide application in autonomous driving, vacuum cleaner, and rescue robot. A navigation agent is supposed to have various intelligent skills, such as visual perceiving, mapping, planning, exploring and reasoning, etc. Building such an agent that observes, thinks, and acts is a key to real intelligence. The remarkable learning ability of deep learning methods empowered the agents to accomplish em"},"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":"2108.04097","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T12:09:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"170ff4bd4d7f5378d3a86b880176633620c2e27ab530a4b13df93f564909f779","abstract_canon_sha256":"141685a4869841266c1d14ac5e0fd749162b3a86cae5eb9024b2a63c1aa144dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:12.860719Z","signature_b64":"cV5wA1z0+7u65aHX7sMylFpwF1D6TR26v4pH0jP0HR1ZgD+Ty+Zu+6ys1CUdRze2XQTTLeUxHDIGV/Idc9D0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f07c026d87b3dfe09ee578329c90417b40097e27e5475ef3f202f28477771ff9","last_reissued_at":"2026-07-05T03:21:12.860246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:12.860246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning for Embodied Vision Navigation: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Fengda Zhu, Vincent CS Lee, Xiaodan Liang, Xiaojun Chang, Yi Zhu","submitted_at":"2021-07-07T12:09:04Z","abstract_excerpt":"\"Embodied visual navigation\" problem requires an agent to navigate in a 3D environment mainly rely on its first-person observation. This problem has attracted rising attention in recent years due to its wide application in autonomous driving, vacuum cleaner, and rescue robot. A navigation agent is supposed to have various intelligent skills, such as visual perceiving, mapping, planning, exploring and reasoning, etc. Building such an agent that observes, thinks, and acts is a key to real intelligence. The remarkable learning ability of deep learning methods empowered the agents to accomplish em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04097","kind":"arxiv","version":4},"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/2108.04097/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":"2108.04097","created_at":"2026-07-05T03:21:12.860304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04097v4","created_at":"2026-07-05T03:21:12.860304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04097","created_at":"2026-07-05T03:21:12.860304+00:00"},{"alias_kind":"pith_short_12","alias_value":"6B6AE3MHWPP6","created_at":"2026-07-05T03:21:12.860304+00:00"},{"alias_kind":"pith_short_16","alias_value":"6B6AE3MHWPP6BHXF","created_at":"2026-07-05T03:21:12.860304+00:00"},{"alias_kind":"pith_short_8","alias_value":"6B6AE3MH","created_at":"2026-07-05T03:21:12.860304+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":124,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN","json":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN.json","graph_json":"https://pith.science/api/pith-number/6B6AE3MHWPP6BHXFPAZJZECBPN/graph.json","events_json":"https://pith.science/api/pith-number/6B6AE3MHWPP6BHXFPAZJZECBPN/events.json","paper":"https://pith.science/paper/6B6AE3MH"},"agent_actions":{"view_html":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN","download_json":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN.json","view_paper":"https://pith.science/paper/6B6AE3MH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04097&json=true","fetch_graph":"https://pith.science/api/pith-number/6B6AE3MHWPP6BHXFPAZJZECBPN/graph.json","fetch_events":"https://pith.science/api/pith-number/6B6AE3MHWPP6BHXFPAZJZECBPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN/action/storage_attestation","attest_author":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN/action/author_attestation","sign_citation":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN/action/citation_signature","submit_replication":"https://pith.science/pith/6B6AE3MHWPP6BHXFPAZJZECBPN/action/replication_record"}},"created_at":"2026-07-05T03:21:12.860304+00:00","updated_at":"2026-07-05T03:21:12.860304+00:00"}