{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y36KFHQ6FZNP4NQTLIEXEHKSR6","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":"8f1ab7bd90f87686a4a6d7c231192b742d33728525f4fe2be8efefd3c4558517","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-10T15:49:07Z","title_canon_sha256":"a0b081faa9797cb137e4e4c675e1a27b1c101d76d940bc5955d27e0008e2d6d0"},"schema_version":"1.0","source":{"id":"2407.07775","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07775","created_at":"2026-07-05T08:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07775v2","created_at":"2026-07-05T08:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07775","created_at":"2026-07-05T08:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y36KFHQ6FZNP","created_at":"2026-07-05T08:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y36KFHQ6FZNP4NQT","created_at":"2026-07-05T08:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y36KFHQ6","created_at":"2026-07-05T08:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:e6f10bd2f9101433035c6ef4d025932bd8cffa035e69b6ef935e95557694e962","target":"graph","created_at":"2026-07-05T08:43:12Z","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/2407.07775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-10T15:49:07Z","title":"Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07775","kind":"arxiv","version":2},"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":"sha256:54ca7f367d4b2d5952bf611cc3ab92a41737928a609caade061d872225d8ae3b","target":"record","created_at":"2026-07-05T08:43:12Z","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":"8f1ab7bd90f87686a4a6d7c231192b742d33728525f4fe2be8efefd3c4558517","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-10T15:49:07Z","title_canon_sha256":"a0b081faa9797cb137e4e4c675e1a27b1c101d76d940bc5955d27e0008e2d6d0"},"schema_version":"1.0","source":{"id":"2407.07775","kind":"arxiv","version":2}},"canonical_sha256":"c6fca29e1e2e5afe36135a09721d528f8096e6f195f3d68f9235d5e1c1d7b8c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6fca29e1e2e5afe36135a09721d528f8096e6f195f3d68f9235d5e1c1d7b8c6","first_computed_at":"2026-07-05T08:43:12.250381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:12.250381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cAkTY7HliLPes14xUb/mcyNELRDaNJ3YOkCp7wfYdQhorjYInrCvczrlwkybnWs4WKn8nC+QC90hLZTwSuKSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:12.250853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07775","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54ca7f367d4b2d5952bf611cc3ab92a41737928a609caade061d872225d8ae3b","sha256:e6f10bd2f9101433035c6ef4d025932bd8cffa035e69b6ef935e95557694e962"],"state_sha256":"7adac3a56f746808149370c30014994b8b98b0c26bc33a2a986d8e60e87bb9c4"}