{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QMPUNDPFWB4BI7WZKPTPETAEMM","short_pith_number":"pith:QMPUNDPF","schema_version":"1.0","canonical_sha256":"831f468de5b078147ed953e6f24c0463389b5f39c462501688ad8618871ca367","source":{"kind":"arxiv","id":"2506.10172","version":1},"attestation_state":"computed","paper":{"title":"A Navigation Framework Utilizing Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Kaiyu Tang, Yicheng Duan","submitted_at":"2025-06-11T20:51:58Z","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"},"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":"2506.10172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-11T20:51:58Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"d9d62e8ffb3333d625c25d472a78810c2f39de6027d6cbf976521d87f3130c42","abstract_canon_sha256":"a105d615081d0263ee06071f9ba05a611a2c48fef22439747d8f9615f72a82c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:17.696958Z","signature_b64":"O1RBICVuF8VhVa4RYAsc9jaA5MNlCevd4/TezbAxx5Ldddl6y+8h0soKZb3CvxUzGEC1DwMBX+2ujBth/RcOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"831f468de5b078147ed953e6f24c0463389b5f39c462501688ad8618871ca367","last_reissued_at":"2026-07-05T11:20:17.696409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:17.696409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Navigation Framework Utilizing Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Kaiyu Tang, Yicheng Duan","submitted_at":"2025-06-11T20:51:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10172","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/2506.10172/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":"2506.10172","created_at":"2026-07-05T11:20:17.696473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10172v1","created_at":"2026-07-05T11:20:17.696473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10172","created_at":"2026-07-05T11:20:17.696473+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMPUNDPFWB4B","created_at":"2026-07-05T11:20:17.696473+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMPUNDPFWB4BI7WZ","created_at":"2026-07-05T11:20:17.696473+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMPUNDPF","created_at":"2026-07-05T11:20:17.696473+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/QMPUNDPFWB4BI7WZKPTPETAEMM","json":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM.json","graph_json":"https://pith.science/api/pith-number/QMPUNDPFWB4BI7WZKPTPETAEMM/graph.json","events_json":"https://pith.science/api/pith-number/QMPUNDPFWB4BI7WZKPTPETAEMM/events.json","paper":"https://pith.science/paper/QMPUNDPF"},"agent_actions":{"view_html":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM","download_json":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM.json","view_paper":"https://pith.science/paper/QMPUNDPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10172&json=true","fetch_graph":"https://pith.science/api/pith-number/QMPUNDPFWB4BI7WZKPTPETAEMM/graph.json","fetch_events":"https://pith.science/api/pith-number/QMPUNDPFWB4BI7WZKPTPETAEMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM/action/storage_attestation","attest_author":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM/action/author_attestation","sign_citation":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM/action/citation_signature","submit_replication":"https://pith.science/pith/QMPUNDPFWB4BI7WZKPTPETAEMM/action/replication_record"}},"created_at":"2026-07-05T11:20:17.696473+00:00","updated_at":"2026-07-05T11:20:17.696473+00:00"}