{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y36KFHQ6FZNP4NQTLIEXEHKSR6","short_pith_number":"pith:Y36KFHQ6","schema_version":"1.0","canonical_sha256":"c6fca29e1e2e5afe36135a09721d528f8096e6f195f3d68f9235d5e1c1d7b8c6","source":{"kind":"arxiv","id":"2407.07775","version":2},"attestation_state":"computed","paper":{"title":"Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Carolina Parada, Chelsea Finn, Connor Schenck, David Rendleman, Dhruv Shah, Fei Xia, Hao-Tien Lewis Chiang, Jasmine Hsu, Jie Tan, Jonathan Hoech, Mithun George Jacob, Peng Xu, Pete Florence, Sean Kirmani, Sergey Levine, Sumeet Singh, Tingnan Zhang, Tsang-Wei Edward Lee, Vikas Sindhwani, Wenhao Yu, Zhuo Xu, Zipeng Fu","submitted_at":"2024-07-10T15:49:07Z","abstract_excerpt":"An elusive goal in navigation research is to build an intelligent agent that can understand multimodal instructions including natural language and image, and perform useful navigation. To achieve this, we study a widely useful category of navigation tasks we call Multimodal Instruction Navigation with demonstration Tours (MINT), in which the environment prior is provided through a previously recorded demonstration video. Recent advances in Vision Language Models (VLMs) have shown a promising path in achieving this goal as it demonstrates capabilities in perceiving and reasoning about multimoda"},"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":"2407.07775","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-10T15:49:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0b081faa9797cb137e4e4c675e1a27b1c101d76d940bc5955d27e0008e2d6d0","abstract_canon_sha256":"8f1ab7bd90f87686a4a6d7c231192b742d33728525f4fe2be8efefd3c4558517"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:12.250853Z","signature_b64":"cAkTY7HliLPes14xUb/mcyNELRDaNJ3YOkCp7wfYdQhorjYInrCvczrlwkybnWs4WKn8nC+QC90hLZTwSuKSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6fca29e1e2e5afe36135a09721d528f8096e6f195f3d68f9235d5e1c1d7b8c6","last_reissued_at":"2026-07-05T08:43:12.250381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:12.250381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Carolina Parada, Chelsea Finn, Connor Schenck, David Rendleman, Dhruv Shah, Fei Xia, Hao-Tien Lewis Chiang, Jasmine Hsu, Jie Tan, Jonathan Hoech, Mithun George Jacob, Peng Xu, Pete Florence, Sean Kirmani, Sergey Levine, Sumeet Singh, Tingnan Zhang, Tsang-Wei Edward Lee, Vikas Sindhwani, Wenhao Yu, Zhuo Xu, Zipeng Fu","submitted_at":"2024-07-10T15:49:07Z","abstract_excerpt":"An elusive goal in navigation research is to build an intelligent agent that can understand multimodal instructions including natural language and image, and perform useful navigation. To achieve this, we study a widely useful category of navigation tasks we call Multimodal Instruction Navigation with demonstration Tours (MINT), in which the environment prior is provided through a previously recorded demonstration video. Recent advances in Vision Language Models (VLMs) have shown a promising path in achieving this goal as it demonstrates capabilities in perceiving and reasoning about multimoda"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07775","kind":"arxiv","version":2},"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/2407.07775/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":"2407.07775","created_at":"2026-07-05T08:43:12.250437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07775v2","created_at":"2026-07-05T08:43:12.250437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07775","created_at":"2026-07-05T08:43:12.250437+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y36KFHQ6FZNP","created_at":"2026-07-05T08:43:12.250437+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y36KFHQ6FZNP4NQT","created_at":"2026-07-05T08:43:12.250437+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y36KFHQ6","created_at":"2026-07-05T08:43:12.250437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20905","citing_title":"Vesta: A Generalist Embodied Reasoning Model","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13456","citing_title":"Block-wise Adaptive Caching for Accelerating Diffusion Policy","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10698","citing_title":"AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24086","citing_title":"AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19034","citing_title":"Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6","json":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6.json","graph_json":"https://pith.science/api/pith-number/Y36KFHQ6FZNP4NQTLIEXEHKSR6/graph.json","events_json":"https://pith.science/api/pith-number/Y36KFHQ6FZNP4NQTLIEXEHKSR6/events.json","paper":"https://pith.science/paper/Y36KFHQ6"},"agent_actions":{"view_html":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6","download_json":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6.json","view_paper":"https://pith.science/paper/Y36KFHQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07775&json=true","fetch_graph":"https://pith.science/api/pith-number/Y36KFHQ6FZNP4NQTLIEXEHKSR6/graph.json","fetch_events":"https://pith.science/api/pith-number/Y36KFHQ6FZNP4NQTLIEXEHKSR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6/action/storage_attestation","attest_author":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6/action/author_attestation","sign_citation":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6/action/citation_signature","submit_replication":"https://pith.science/pith/Y36KFHQ6FZNP4NQTLIEXEHKSR6/action/replication_record"}},"created_at":"2026-07-05T08:43:12.250437+00:00","updated_at":"2026-07-05T08:43:12.250437+00:00"}