{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SCVYOYFZYBLDSKY6GVSAKLXJSU","short_pith_number":"pith:SCVYOYFZ","schema_version":"1.0","canonical_sha256":"90ab8760b9c056392b1e3564052ee9952c7216d18e09babbcaaf0f00acb1a667","source":{"kind":"arxiv","id":"2607.06882","version":1},"attestation_state":"computed","paper":{"title":"GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abdelwahed Khamis, Chris McCool, Peter Bohm, Peyman Moghadam, Sagun Man Singh Shrestha, Saimunur Rahman","submitted_at":"2026-07-08T00:46:57Z","abstract_excerpt":"Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe is necessary. In this paper, we introduce GemNav, a visual robot navigation policy that adapts a frozen Multimodal Large Language Model (MLLM) for short-to-medium horizon waypoint navigation using Low-Rank Adaptation (LoRA) on the language tower alone, with no auxiliary visual encoder and no continuous regression head. Waypoints and categorical navigation s"},"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":"2607.06882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-08T00:46:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eebfff45a8dc4e136f7fbcf6ecc62cdb3d79d259da46b3985ca53b70c519333e","abstract_canon_sha256":"91529ee000e7ef7afa48105c4d35e169b397bde9e54d1fde0b637209bc4e316c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:38.540157Z","signature_b64":"gwQDeQmu2oJcCyYSD8VGlMk/vMTTzkuTIU+kTFBocdPYSkYWZkZsfkDTx+Nutl3Vgo4pCYwHDGl2SET27GcQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ab8760b9c056392b1e3564052ee9952c7216d18e09babbcaaf0f00acb1a667","last_reissued_at":"2026-07-09T00:19:38.539687Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:38.539687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abdelwahed Khamis, Chris McCool, Peter Bohm, Peyman Moghadam, Sagun Man Singh Shrestha, Saimunur Rahman","submitted_at":"2026-07-08T00:46:57Z","abstract_excerpt":"Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets. We ask whether this recipe is necessary. In this paper, we introduce GemNav, a visual robot navigation policy that adapts a frozen Multimodal Large Language Model (MLLM) for short-to-medium horizon waypoint navigation using Low-Rank Adaptation (LoRA) on the language tower alone, with no auxiliary visual encoder and no continuous regression head. Waypoints and categorical navigation s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06882","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/2607.06882/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":"2607.06882","created_at":"2026-07-09T00:19:38.539746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06882v1","created_at":"2026-07-09T00:19:38.539746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06882","created_at":"2026-07-09T00:19:38.539746+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCVYOYFZYBLD","created_at":"2026-07-09T00:19:38.539746+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCVYOYFZYBLDSKY6","created_at":"2026-07-09T00:19:38.539746+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCVYOYFZ","created_at":"2026-07-09T00:19:38.539746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU","json":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU.json","graph_json":"https://pith.science/api/pith-number/SCVYOYFZYBLDSKY6GVSAKLXJSU/graph.json","events_json":"https://pith.science/api/pith-number/SCVYOYFZYBLDSKY6GVSAKLXJSU/events.json","paper":"https://pith.science/paper/SCVYOYFZ"},"agent_actions":{"view_html":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU","download_json":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU.json","view_paper":"https://pith.science/paper/SCVYOYFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06882&json=true","fetch_graph":"https://pith.science/api/pith-number/SCVYOYFZYBLDSKY6GVSAKLXJSU/graph.json","fetch_events":"https://pith.science/api/pith-number/SCVYOYFZYBLDSKY6GVSAKLXJSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU/action/storage_attestation","attest_author":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU/action/author_attestation","sign_citation":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU/action/citation_signature","submit_replication":"https://pith.science/pith/SCVYOYFZYBLDSKY6GVSAKLXJSU/action/replication_record"}},"created_at":"2026-07-09T00:19:38.539746+00:00","updated_at":"2026-07-09T00:19:38.539746+00:00"}