{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B45RSMK3QZQY36HRX2PY7QJISE","short_pith_number":"pith:B45RSMK3","schema_version":"1.0","canonical_sha256":"0f3b19315b86618df8f1be9f8fc128911573d461b97ff18bb884dff762ec8f0b","source":{"kind":"arxiv","id":"2105.09447","version":1},"attestation_state":"computed","paper":{"title":"VTNet: Visual Transformer Network for Object Goal Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heming Du, Liang Zheng, Xin Yu","submitted_at":"2021-05-20T01:23:15Z","abstract_excerpt":"Object goal navigation aims to steer an agent towards a target object based on observations of the agent. It is of pivotal importance to design effective visual representations of the observed scene in determining navigation actions. In this paper, we introduce a Visual Transformer Network (VTNet) for learning informative visual representation in navigation. VTNet is a highly effective structure that embodies two key properties for visual representations: First, the relationships among all the object instances in a scene are exploited; Second, the spatial locations of objects and image regions"},"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":"2105.09447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-20T01:23:15Z","cross_cats_sorted":[],"title_canon_sha256":"23407c660bacd0b1770038f65bf1f4be4d37f2bc03e3ad274817bdbca0f28b07","abstract_canon_sha256":"8467bbd35e74c260c67c9431e8c8395263866f8e5d422ef8aac2629fde222488"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:52.702226Z","signature_b64":"Wk6LheFf9cSJjwobmV4zFKoxBBi4ymcibrKTMLrLqFQrwKGbdHnTJQnv6NErMmDlziRv/aquKiuj+akXHPTFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f3b19315b86618df8f1be9f8fc128911573d461b97ff18bb884dff762ec8f0b","last_reissued_at":"2026-07-05T02:41:52.701824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:52.701824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VTNet: Visual Transformer Network for Object Goal Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heming Du, Liang Zheng, Xin Yu","submitted_at":"2021-05-20T01:23:15Z","abstract_excerpt":"Object goal navigation aims to steer an agent towards a target object based on observations of the agent. It is of pivotal importance to design effective visual representations of the observed scene in determining navigation actions. In this paper, we introduce a Visual Transformer Network (VTNet) for learning informative visual representation in navigation. VTNet is a highly effective structure that embodies two key properties for visual representations: First, the relationships among all the object instances in a scene are exploited; Second, the spatial locations of objects and image regions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09447","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/2105.09447/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":"2105.09447","created_at":"2026-07-05T02:41:52.701881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.09447v1","created_at":"2026-07-05T02:41:52.701881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09447","created_at":"2026-07-05T02:41:52.701881+00:00"},{"alias_kind":"pith_short_12","alias_value":"B45RSMK3QZQY","created_at":"2026-07-05T02:41:52.701881+00:00"},{"alias_kind":"pith_short_16","alias_value":"B45RSMK3QZQY36HR","created_at":"2026-07-05T02:41:52.701881+00:00"},{"alias_kind":"pith_short_8","alias_value":"B45RSMK3","created_at":"2026-07-05T02:41:52.701881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25497","citing_title":"SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30017","citing_title":"Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05960","citing_title":"Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE","json":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE.json","graph_json":"https://pith.science/api/pith-number/B45RSMK3QZQY36HRX2PY7QJISE/graph.json","events_json":"https://pith.science/api/pith-number/B45RSMK3QZQY36HRX2PY7QJISE/events.json","paper":"https://pith.science/paper/B45RSMK3"},"agent_actions":{"view_html":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE","download_json":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE.json","view_paper":"https://pith.science/paper/B45RSMK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.09447&json=true","fetch_graph":"https://pith.science/api/pith-number/B45RSMK3QZQY36HRX2PY7QJISE/graph.json","fetch_events":"https://pith.science/api/pith-number/B45RSMK3QZQY36HRX2PY7QJISE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE/action/storage_attestation","attest_author":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE/action/author_attestation","sign_citation":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE/action/citation_signature","submit_replication":"https://pith.science/pith/B45RSMK3QZQY36HRX2PY7QJISE/action/replication_record"}},"created_at":"2026-07-05T02:41:52.701881+00:00","updated_at":"2026-07-05T02:41:52.701881+00:00"}