{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NHXQXYTNYBVBFO2EKO2IDDWNMV","short_pith_number":"pith:NHXQXYTN","schema_version":"1.0","canonical_sha256":"69ef0be26dc06a12bb4453b4818ecd6563d5743cbde240ac9290c77e9602adec","source":{"kind":"arxiv","id":"2407.05890","version":2},"attestation_state":"computed","paper":{"title":"Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Bingqian Lin, Jiaqi Chen, Kwan-Yee K. Wong, Lin Ma, Xiaodan Liang, Xinmin Liu","submitted_at":"2024-07-08T12:52:46Z","abstract_excerpt":"LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) task. However, existing LLM-based methods often focus only on solving high-level task planning by selecting nodes in predefined navigation graphs for movements, overlooking low-level control in navigation scenarios. To bridge this gap, we propose AO-Planner, a novel Affordances-Oriented Planner for continuous VLN task. Our AO-Planner integrates various foundation models to achieve affordances-oriented low-level motion planning and high-level decision-making, both performed in a zero-shot set"},"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":"2407.05890","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-08T12:52:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9fe718542ff918fd2523e9dc3e6cf2d0593d1cfc3f29d70e458d00b012a76fcf","abstract_canon_sha256":"abb0e8b3ac092a2208ef9f73cdf60f3dff2ab301af21c4a030d9d0b4aaa95382"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:05.522947Z","signature_b64":"a3QtxCYIya/7iMwEjD6Jn0SZKpklYnZ8vZ1MvwLHVUgvEw8bc5jgXwDKGZ1SxPm+mRj0B6lqZbdHnftthZCbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69ef0be26dc06a12bb4453b4818ecd6563d5743cbde240ac9290c77e9602adec","last_reissued_at":"2026-07-05T08:57:05.522456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:05.522456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Bingqian Lin, Jiaqi Chen, Kwan-Yee K. Wong, Lin Ma, Xiaodan Liang, Xinmin Liu","submitted_at":"2024-07-08T12:52:46Z","abstract_excerpt":"LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) task. However, existing LLM-based methods often focus only on solving high-level task planning by selecting nodes in predefined navigation graphs for movements, overlooking low-level control in navigation scenarios. To bridge this gap, we propose AO-Planner, a novel Affordances-Oriented Planner for continuous VLN task. Our AO-Planner integrates various foundation models to achieve affordances-oriented low-level motion planning and high-level decision-making, both performed in a zero-shot set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05890","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/2407.05890/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":"2407.05890","created_at":"2026-07-05T08:57:05.522515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05890v2","created_at":"2026-07-05T08:57:05.522515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05890","created_at":"2026-07-05T08:57:05.522515+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHXQXYTNYBVB","created_at":"2026-07-05T08:57:05.522515+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHXQXYTNYBVBFO2E","created_at":"2026-07-05T08:57:05.522515+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHXQXYTN","created_at":"2026-07-05T08:57:05.522515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.13451","citing_title":"MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13328","citing_title":"What Limits Vision-and-Language Navigation ?","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV","json":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV.json","graph_json":"https://pith.science/api/pith-number/NHXQXYTNYBVBFO2EKO2IDDWNMV/graph.json","events_json":"https://pith.science/api/pith-number/NHXQXYTNYBVBFO2EKO2IDDWNMV/events.json","paper":"https://pith.science/paper/NHXQXYTN"},"agent_actions":{"view_html":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV","download_json":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV.json","view_paper":"https://pith.science/paper/NHXQXYTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05890&json=true","fetch_graph":"https://pith.science/api/pith-number/NHXQXYTNYBVBFO2EKO2IDDWNMV/graph.json","fetch_events":"https://pith.science/api/pith-number/NHXQXYTNYBVBFO2EKO2IDDWNMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV/action/storage_attestation","attest_author":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV/action/author_attestation","sign_citation":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV/action/citation_signature","submit_replication":"https://pith.science/pith/NHXQXYTNYBVBFO2EKO2IDDWNMV/action/replication_record"}},"created_at":"2026-07-05T08:57:05.522515+00:00","updated_at":"2026-07-05T08:57:05.522515+00:00"}