{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KSSBYJVORHP5OXBFRM47GECC2M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ba433ee037dfd7388c02eb95165111b8aa4bc2c94e85ebb4c6afa251b2a1ce17","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-30T00:38:54Z","title_canon_sha256":"8a3f090433ad5c35df8030cffa0293e3ed91cd9e1e01f5fe30ba28ab6bd96ed1"},"schema_version":"1.0","source":{"id":"2211.16649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.16649","created_at":"2026-07-05T05:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2211.16649v1","created_at":"2026-07-05T05:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16649","created_at":"2026-07-05T05:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"KSSBYJVORHP5","created_at":"2026-07-05T05:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"KSSBYJVORHP5OXBF","created_at":"2026-07-05T05:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"KSSBYJVO","created_at":"2026-07-05T05:21:09Z"}],"graph_snapshots":[{"event_id":"sha256:710d0d3d9788124f220057dc47285f3d8803a26aa6c2f695450a31f454705d8e","target":"graph","created_at":"2026-07-05T05:21:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.16649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gaurav S. Sukhatme, Gunnar Sigurdsson, Jesse Thomason, Robinson Piramuthu, Vishnu Sashank Dorbala","cross_cats":["cs.AI","cs.CL","cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-30T00:38:54Z","title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16649","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6604f4b439b737c7f0434a9bf302c53cb674acf803ff4ad2ffe1bb4ef121dc94","target":"record","created_at":"2026-07-05T05:21:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ba433ee037dfd7388c02eb95165111b8aa4bc2c94e85ebb4c6afa251b2a1ce17","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-30T00:38:54Z","title_canon_sha256":"8a3f090433ad5c35df8030cffa0293e3ed91cd9e1e01f5fe30ba28ab6bd96ed1"},"schema_version":"1.0","source":{"id":"2211.16649","kind":"arxiv","version":1}},"canonical_sha256":"54a41c26ae89dfd75c258b39f31042d32798663bdb87f553732ba5058a66adb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54a41c26ae89dfd75c258b39f31042d32798663bdb87f553732ba5058a66adb1","first_computed_at":"2026-07-05T05:21:09.313482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:09.313482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+8OqYI+prv39r4Zvu55I175cVdHj2EwOn36aBMGntFd5hYgaNkSjUmDg87DRU2zUU41x3zP15urB3513PuacBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:09.313975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.16649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6604f4b439b737c7f0434a9bf302c53cb674acf803ff4ad2ffe1bb4ef121dc94","sha256:710d0d3d9788124f220057dc47285f3d8803a26aa6c2f695450a31f454705d8e"],"state_sha256":"59ff2cfd9c2648e7c9197ebf440b01acfce8b5b9f556eb2341d6b228c22c5d20"}