{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZPXC5M76NSQK46QFEWSLWZ4XVG","short_pith_number":"pith:ZPXC5M76","schema_version":"1.0","canonical_sha256":"cbee2eb3fe6ca0ae7a0525a4bb6797a98b2c8860b401f6a50d3f923ba26e3927","source":{"kind":"arxiv","id":"2407.12366","version":2},"attestation_state":"computed","paper":{"title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Gengze Zhou, Qi Wu, Xin Eric Wang, Yicong Hong, Zun Wang","submitted_at":"2024-07-17T07:44:26Z","abstract_excerpt":"Capitalizing on the remarkable advancements in Large Language Models (LLMs), there is a burgeoning initiative to harness LLMs for instruction following robotic navigation. Such a trend underscores the potential of LLMs to generalize navigational reasoning and diverse language understanding. However, a significant discrepancy in agent performance is observed when integrating LLMs in the Vision-and-Language navigation (VLN) tasks compared to previous downstream specialist models. Furthermore, the inherent capacity of language to interpret and facilitate communication in agent interactions is oft"},"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":"2407.12366","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T07:44:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"0e7f57c66e6350272487eaf30dc400a8b2861eb1d519f28d7e0c1b54ff2514b0","abstract_canon_sha256":"1eb70b497b4a72a34e7ed8b3224d564f088cfba866149074ce538d87bdbb67b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:24.539366Z","signature_b64":"IOATpPYmyY4uZ2RMw+N4zr/GEKrWvO/Pv8Zx55m8a09co16dmkWA7P/CfKcPMA8MZIn+AUsBdroFG+y3Mf/7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbee2eb3fe6ca0ae7a0525a4bb6797a98b2c8860b401f6a50d3f923ba26e3927","last_reissued_at":"2026-07-05T09:09:24.538832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:24.538832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Gengze Zhou, Qi Wu, Xin Eric Wang, Yicong Hong, Zun Wang","submitted_at":"2024-07-17T07:44:26Z","abstract_excerpt":"Capitalizing on the remarkable advancements in Large Language Models (LLMs), there is a burgeoning initiative to harness LLMs for instruction following robotic navigation. Such a trend underscores the potential of LLMs to generalize navigational reasoning and diverse language understanding. However, a significant discrepancy in agent performance is observed when integrating LLMs in the Vision-and-Language navigation (VLN) tasks compared to previous downstream specialist models. Furthermore, the inherent capacity of language to interpret and facilitate communication in agent interactions is oft"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12366","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/2407.12366/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":"2407.12366","created_at":"2026-07-05T09:09:24.538901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12366v2","created_at":"2026-07-05T09:09:24.538901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12366","created_at":"2026-07-05T09:09:24.538901+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPXC5M76NSQK","created_at":"2026-07-05T09:09:24.538901+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPXC5M76NSQK46QF","created_at":"2026-07-05T09:09:24.538901+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPXC5M76","created_at":"2026-07-05T09:09:24.538901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05765","citing_title":"Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2508.07642","citing_title":"Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG","json":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG.json","graph_json":"https://pith.science/api/pith-number/ZPXC5M76NSQK46QFEWSLWZ4XVG/graph.json","events_json":"https://pith.science/api/pith-number/ZPXC5M76NSQK46QFEWSLWZ4XVG/events.json","paper":"https://pith.science/paper/ZPXC5M76"},"agent_actions":{"view_html":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG","download_json":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG.json","view_paper":"https://pith.science/paper/ZPXC5M76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12366&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPXC5M76NSQK46QFEWSLWZ4XVG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPXC5M76NSQK46QFEWSLWZ4XVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG/action/storage_attestation","attest_author":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG/action/author_attestation","sign_citation":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG/action/citation_signature","submit_replication":"https://pith.science/pith/ZPXC5M76NSQK46QFEWSLWZ4XVG/action/replication_record"}},"created_at":"2026-07-05T09:09:24.538901+00:00","updated_at":"2026-07-05T09:09:24.538901+00:00"}