{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FNV265ZGO4XQTU3VXHSFG6BIGP","short_pith_number":"pith:FNV265ZG","schema_version":"1.0","canonical_sha256":"2b6baf7726772f09d375b9e453782833db62f7a0912fe71664d9465dc4255aba","source":{"kind":"arxiv","id":"2304.01192","version":1},"attestation_state":"computed","paper":{"title":"Navigating to Objects Specified by Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Austin Wang, Chris Paxton, Devendra Singh Chaplot, Dhruv Batra, Jacob Krantz, Jitendra Malik, Karmesh Yadav, Roozbeh Mottaghi, Stefan Lee, Theophile Gervet","submitted_at":"2023-04-03T17:58:00Z","abstract_excerpt":"Images are a convenient way to specify which particular object instance an embodied agent should navigate to. Solving this task requires semantic visual reasoning and exploration of unknown environments. We present a system that can perform this task in both simulation and the real world. Our modular method solves sub-tasks of exploration, goal instance re-identification, goal localization, and local navigation. We re-identify the goal instance in egocentric vision using feature-matching and localize the goal instance by projecting matched features to a map. Each sub-task is solved using off-t"},"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":"2304.01192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T17:58:00Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"423f45ce3125fb74b801dd60e57723cbdb84a4651cd51c209ced43ce237839cf","abstract_canon_sha256":"604eb97103ff5cc6db6264c1c37d9fba6845896833d68daa1e21136ac1fe4a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:27.583304Z","signature_b64":"Pz7vW/zhmcrtjlpJa6kA7LBDiJdYd7e7CuWWITVBWUHMAMsUN76csoje4RFxYuLxcxT2wKGqHTfIj4p3IdjgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b6baf7726772f09d375b9e453782833db62f7a0912fe71664d9465dc4255aba","last_reissued_at":"2026-07-05T05:57:27.582777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:27.582777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating to Objects Specified by Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Austin Wang, Chris Paxton, Devendra Singh Chaplot, Dhruv Batra, Jacob Krantz, Jitendra Malik, Karmesh Yadav, Roozbeh Mottaghi, Stefan Lee, Theophile Gervet","submitted_at":"2023-04-03T17:58:00Z","abstract_excerpt":"Images are a convenient way to specify which particular object instance an embodied agent should navigate to. Solving this task requires semantic visual reasoning and exploration of unknown environments. We present a system that can perform this task in both simulation and the real world. Our modular method solves sub-tasks of exploration, goal instance re-identification, goal localization, and local navigation. We re-identify the goal instance in egocentric vision using feature-matching and localize the goal instance by projecting matched features to a map. Each sub-task is solved using off-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.01192","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/2304.01192/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":"2304.01192","created_at":"2026-07-05T05:57:27.582837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.01192v1","created_at":"2026-07-05T05:57:27.582837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.01192","created_at":"2026-07-05T05:57:27.582837+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNV265ZGO4XQ","created_at":"2026-07-05T05:57:27.582837+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNV265ZGO4XQTU3V","created_at":"2026-07-05T05:57:27.582837+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNV265ZG","created_at":"2026-07-05T05:57:27.582837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10454","citing_title":"GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP","json":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP.json","graph_json":"https://pith.science/api/pith-number/FNV265ZGO4XQTU3VXHSFG6BIGP/graph.json","events_json":"https://pith.science/api/pith-number/FNV265ZGO4XQTU3VXHSFG6BIGP/events.json","paper":"https://pith.science/paper/FNV265ZG"},"agent_actions":{"view_html":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP","download_json":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP.json","view_paper":"https://pith.science/paper/FNV265ZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.01192&json=true","fetch_graph":"https://pith.science/api/pith-number/FNV265ZGO4XQTU3VXHSFG6BIGP/graph.json","fetch_events":"https://pith.science/api/pith-number/FNV265ZGO4XQTU3VXHSFG6BIGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP/action/storage_attestation","attest_author":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP/action/author_attestation","sign_citation":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP/action/citation_signature","submit_replication":"https://pith.science/pith/FNV265ZGO4XQTU3VXHSFG6BIGP/action/replication_record"}},"created_at":"2026-07-05T05:57:27.582837+00:00","updated_at":"2026-07-05T05:57:27.582837+00:00"}