{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L2Y3NHTQKLAZYTS5NX7SITYPWG","short_pith_number":"pith:L2Y3NHTQ","schema_version":"1.0","canonical_sha256":"5eb1b69e7052c19c4e5d6dff244f0fb1b6ad077fed59209a3079ad12b3db70d5","source":{"kind":"arxiv","id":"2506.15096","version":1},"attestation_state":"computed","paper":{"title":"DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huangxuan Lin, Yue Gao, Zihe Ji","submitted_at":"2025-06-18T03:06:01Z","abstract_excerpt":"We present DyNaVLM, an end-to-end vision-language navigation framework using Vision-Language Models (VLM). In contrast to prior methods constrained by fixed angular or distance intervals, our system empowers agents to freely select navigation targets via visual-language reasoning. At its core lies a self-refining graph memory that 1) stores object locations as executable topological relations, 2) enables cross-robot memory sharing through distributed graph updates, and 3) enhances VLM's decision-making via retrieval augmentation. Operating without task-specific training or fine-tuning, DyNaVLM"},"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":"2506.15096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-18T03:06:01Z","cross_cats_sorted":[],"title_canon_sha256":"da85e0d238d22b22b1e493af8535e3c297e88e2b3380561e9ffaad297c807f9c","abstract_canon_sha256":"8b612b70be49ee9357e29dbb8c645ffa8c0a88b0d5c635924135bc219e25e10c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:37.024152Z","signature_b64":"Bt7ee1L3Jd2JCEDxdxqlrW5BOsst8kH/6i52vsYrl7l9G1mCd6BTNbn+pDa4MmiBVJOcpTMUVZ5HWbOf7qkQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eb1b69e7052c19c4e5d6dff244f0fb1b6ad077fed59209a3079ad12b3db70d5","last_reissued_at":"2026-07-05T11:23:37.023653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:37.023653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huangxuan Lin, Yue Gao, Zihe Ji","submitted_at":"2025-06-18T03:06:01Z","abstract_excerpt":"We present DyNaVLM, an end-to-end vision-language navigation framework using Vision-Language Models (VLM). In contrast to prior methods constrained by fixed angular or distance intervals, our system empowers agents to freely select navigation targets via visual-language reasoning. At its core lies a self-refining graph memory that 1) stores object locations as executable topological relations, 2) enables cross-robot memory sharing through distributed graph updates, and 3) enhances VLM's decision-making via retrieval augmentation. Operating without task-specific training or fine-tuning, DyNaVLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15096","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/2506.15096/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":"2506.15096","created_at":"2026-07-05T11:23:37.023710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15096v1","created_at":"2026-07-05T11:23:37.023710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15096","created_at":"2026-07-05T11:23:37.023710+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2Y3NHTQKLAZ","created_at":"2026-07-05T11:23:37.023710+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2Y3NHTQKLAZYTS5","created_at":"2026-07-05T11:23:37.023710+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2Y3NHTQ","created_at":"2026-07-05T11:23:37.023710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18634","citing_title":"EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03509","citing_title":"EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG","json":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG.json","graph_json":"https://pith.science/api/pith-number/L2Y3NHTQKLAZYTS5NX7SITYPWG/graph.json","events_json":"https://pith.science/api/pith-number/L2Y3NHTQKLAZYTS5NX7SITYPWG/events.json","paper":"https://pith.science/paper/L2Y3NHTQ"},"agent_actions":{"view_html":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG","download_json":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG.json","view_paper":"https://pith.science/paper/L2Y3NHTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15096&json=true","fetch_graph":"https://pith.science/api/pith-number/L2Y3NHTQKLAZYTS5NX7SITYPWG/graph.json","fetch_events":"https://pith.science/api/pith-number/L2Y3NHTQKLAZYTS5NX7SITYPWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG/action/storage_attestation","attest_author":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG/action/author_attestation","sign_citation":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG/action/citation_signature","submit_replication":"https://pith.science/pith/L2Y3NHTQKLAZYTS5NX7SITYPWG/action/replication_record"}},"created_at":"2026-07-05T11:23:37.023710+00:00","updated_at":"2026-07-05T11:23:37.023710+00:00"}