{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OACQPW4KB3VRWUUAMAL64YJJRH","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":"85164c53cc0456275e252a87c9cef31dd14814fa52c918fba97ffe952045f385","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-24T09:24:07Z","title_canon_sha256":"0fa705d8e1a7c7bda91a6ba4d95277e6d4ef94685006eb91aa2f58a24a965666"},"schema_version":"1.0","source":{"id":"2410.18570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18570","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18570v1","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18570","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"OACQPW4KB3VR","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"OACQPW4KB3VRWUUA","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"OACQPW4K","created_at":"2026-07-05T09:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:bf515c5cb2daca0ae9909d1ffa76b828338ad9a8e9e86600ec8c9e2529bc1134","target":"graph","created_at":"2026-07-05T09:25:10Z","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/2410.18570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object navigation is crucial for robots, but traditional methods require substantial training data and cannot be generalized to unknown environments. Zero-shot object navigation (ZSON) aims to address this challenge, allowing robots to interact with unknown objects without specific training data. Language-driven zero-shot object navigation (L-ZSON) is an extension of ZSON that incorporates natural language instructions to guide robot navigation and interaction with objects. In this paper, we propose a novel Vision Language model with a Tree-of-thought Network (VLTNet) for L-ZSON. VLTNet compri","authors_text":"Congcong Wen, Hao Huang, Hui Lin, Shuaihang Yuan, Yanjia Huang, Yi Fang, Yisiyuan Huang, Yu Hao, Yu-Shen Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-24T09:24:07Z","title":"Zero-shot Object Navigation with Vision-Language Models Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18570","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":"sha256:6dc84e08fa98966001d4c83454ee93992c4c89c267943952298793632888831d","target":"record","created_at":"2026-07-05T09:25:10Z","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":"85164c53cc0456275e252a87c9cef31dd14814fa52c918fba97ffe952045f385","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-24T09:24:07Z","title_canon_sha256":"0fa705d8e1a7c7bda91a6ba4d95277e6d4ef94685006eb91aa2f58a24a965666"},"schema_version":"1.0","source":{"id":"2410.18570","kind":"arxiv","version":1}},"canonical_sha256":"700507db8a0eeb1b52806017ee612989e4587b0a8dbee33728c591a45cd84a80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"700507db8a0eeb1b52806017ee612989e4587b0a8dbee33728c591a45cd84a80","first_computed_at":"2026-07-05T09:25:10.447936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:10.447936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ikti8qp9fkOPv312d1mxyBAEEgmehgg2KX4Y/Kitp5iX3YNdVMEr2shjyKh2f/QQVrClderi4bCcZ7fDCMHzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:10.448332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dc84e08fa98966001d4c83454ee93992c4c89c267943952298793632888831d","sha256:bf515c5cb2daca0ae9909d1ffa76b828338ad9a8e9e86600ec8c9e2529bc1134"],"state_sha256":"5c428319c7b4d3f2542d30690493b65b3bc1240dc288e2abe7debb425d8258b4"}