{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QMPUNDPFWB4BI7WZKPTPETAEMM","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":"a105d615081d0263ee06071f9ba05a611a2c48fef22439747d8f9615f72a82c4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-11T20:51:58Z","title_canon_sha256":"d9d62e8ffb3333d625c25d472a78810c2f39de6027d6cbf976521d87f3130c42"},"schema_version":"1.0","source":{"id":"2506.10172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10172","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10172v1","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10172","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"QMPUNDPFWB4B","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"QMPUNDPFWB4BI7WZ","created_at":"2026-07-05T11:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"QMPUNDPF","created_at":"2026-07-05T11:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:7e134255a65fd9ab0842eb90c3fb45c7aec9342a435d4b364d5444ae976e301f","target":"graph","created_at":"2026-07-05T11:20:17Z","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/2506.10172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language Navigation (VLN) presents a complex challenge in embodied AI, requiring agents to interpret natural language instructions and navigate through visually rich, unfamiliar environments. Recent advances in large vision-language models (LVLMs), such as CLIP and Flamingo, have significantly improved multimodal understanding but introduced new challenges related to computational cost and real-time deployment. In this project, we propose a modular, plug-and-play navigation framework that decouples vision-language understanding from action planning. By integrating a frozen vision-la","authors_text":"Kaiyu Tang, Yicheng Duan","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-11T20:51:58Z","title":"A Navigation Framework Utilizing Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10172","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:e7254f035427b6b122f49f2abfc6853945d3db660812e70143f485237fc02bcf","target":"record","created_at":"2026-07-05T11:20:17Z","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":"a105d615081d0263ee06071f9ba05a611a2c48fef22439747d8f9615f72a82c4","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-11T20:51:58Z","title_canon_sha256":"d9d62e8ffb3333d625c25d472a78810c2f39de6027d6cbf976521d87f3130c42"},"schema_version":"1.0","source":{"id":"2506.10172","kind":"arxiv","version":1}},"canonical_sha256":"831f468de5b078147ed953e6f24c0463389b5f39c462501688ad8618871ca367","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"831f468de5b078147ed953e6f24c0463389b5f39c462501688ad8618871ca367","first_computed_at":"2026-07-05T11:20:17.696409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:17.696409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O1RBICVuF8VhVa4RYAsc9jaA5MNlCevd4/TezbAxx5Ldddl6y+8h0soKZb3CvxUzGEC1DwMBX+2ujBth/RcOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:17.696958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7254f035427b6b122f49f2abfc6853945d3db660812e70143f485237fc02bcf","sha256:7e134255a65fd9ab0842eb90c3fb45c7aec9342a435d4b364d5444ae976e301f"],"state_sha256":"743ad4e5d6f732abd4e89995ca504c73b789a3068d3acb42cc41c5f2ae5553a7"}