{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KSSBYJVORHP5OXBFRM47GECC2M","short_pith_number":"pith:KSSBYJVO","schema_version":"1.0","canonical_sha256":"54a41c26ae89dfd75c258b39f31042d32798663bdb87f553732ba5058a66adb1","source":{"kind":"arxiv","id":"2211.16649","version":1},"attestation_state":"computed","paper":{"title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Gaurav S. Sukhatme, Gunnar Sigurdsson, Jesse Thomason, Robinson Piramuthu, Vishnu Sashank Dorbala","submitted_at":"2022-11-30T00:38:54Z","abstract_excerpt":"Household environments are visually diverse. Embodied agents performing Vision-and-Language Navigation (VLN) in the wild must be able to handle this diversity, while also following arbitrary language instructions. Recently, Vision-Language models like CLIP have shown great performance on the task of zero-shot object recognition. In this work, we ask if these models are also capable of zero-shot language grounding. In particular, we utilize CLIP to tackle the novel problem of zero-shot VLN using natural language referring expressions that describe target objects, in contrast to past work that u"},"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":"2211.16649","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-30T00:38:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"8a3f090433ad5c35df8030cffa0293e3ed91cd9e1e01f5fe30ba28ab6bd96ed1","abstract_canon_sha256":"ba433ee037dfd7388c02eb95165111b8aa4bc2c94e85ebb4c6afa251b2a1ce17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:09.313975Z","signature_b64":"+8OqYI+prv39r4Zvu55I175cVdHj2EwOn36aBMGntFd5hYgaNkSjUmDg87DRU2zUU41x3zP15urB3513PuacBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a41c26ae89dfd75c258b39f31042d32798663bdb87f553732ba5058a66adb1","last_reissued_at":"2026-07-05T05:21:09.313482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:09.313482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Gaurav S. Sukhatme, Gunnar Sigurdsson, Jesse Thomason, Robinson Piramuthu, Vishnu Sashank Dorbala","submitted_at":"2022-11-30T00:38:54Z","abstract_excerpt":"Household environments are visually diverse. Embodied agents performing Vision-and-Language Navigation (VLN) in the wild must be able to handle this diversity, while also following arbitrary language instructions. Recently, Vision-Language models like CLIP have shown great performance on the task of zero-shot object recognition. In this work, we ask if these models are also capable of zero-shot language grounding. In particular, we utilize CLIP to tackle the novel problem of zero-shot VLN using natural language referring expressions that describe target objects, in contrast to past work that u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16649","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/2211.16649/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":"2211.16649","created_at":"2026-07-05T05:21:09.313543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16649v1","created_at":"2026-07-05T05:21:09.313543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16649","created_at":"2026-07-05T05:21:09.313543+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSSBYJVORHP5","created_at":"2026-07-05T05:21:09.313543+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSSBYJVORHP5OXBF","created_at":"2026-07-05T05:21:09.313543+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSSBYJVO","created_at":"2026-07-05T05:21:09.313543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25136","citing_title":"Memory Retrieval in Visuomotor Policies for Long-Horizon Robot Control","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28237","citing_title":"POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16979","citing_title":"NORM-Nav: Zero-Shot Mobile Robot Navigation with Natural Language Behavioral Constraints","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06224","citing_title":"Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2512.24985","citing_title":"DarkQA: Benchmarking Vision-Language Models on Visual-Primitive Question Answering in Low-Light Indoor Scenes","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07973","citing_title":"How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16298","citing_title":"FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M","json":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M.json","graph_json":"https://pith.science/api/pith-number/KSSBYJVORHP5OXBFRM47GECC2M/graph.json","events_json":"https://pith.science/api/pith-number/KSSBYJVORHP5OXBFRM47GECC2M/events.json","paper":"https://pith.science/paper/KSSBYJVO"},"agent_actions":{"view_html":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M","download_json":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M.json","view_paper":"https://pith.science/paper/KSSBYJVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16649&json=true","fetch_graph":"https://pith.science/api/pith-number/KSSBYJVORHP5OXBFRM47GECC2M/graph.json","fetch_events":"https://pith.science/api/pith-number/KSSBYJVORHP5OXBFRM47GECC2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M/action/storage_attestation","attest_author":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M/action/author_attestation","sign_citation":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M/action/citation_signature","submit_replication":"https://pith.science/pith/KSSBYJVORHP5OXBFRM47GECC2M/action/replication_record"}},"created_at":"2026-07-05T05:21:09.313543+00:00","updated_at":"2026-07-05T05:21:09.313543+00:00"}