{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U7H6LD4PDCOLV2WMHA3XCLKVSU","short_pith_number":"pith:U7H6LD4P","schema_version":"1.0","canonical_sha256":"a7cfe58f8f189cbaeacc3837712d559504db1cd5fd63bfd83f094d400cc357c2","source":{"kind":"arxiv","id":"2607.03920","version":1},"attestation_state":"computed","paper":{"title":"LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hechang Chen, Hui Xiong, Rufeng Chen, Sihong Xie, Yue Chang, Zhaofan Zhang, Zili Shao","submitted_at":"2026-07-04T15:25:25Z","abstract_excerpt":"Embodied navigation is moving toward long-horizon missions, yet existing long-horizon benchmarks are largely acoustically silent, and audio-visual navigation tasks typically focus on a single goal. We introduce LH-AVLN, a benchmark for Long-Horizon Audio-Visual-Language Navigation that combines multi-goal mission execution, heterogeneous goal specifications, and persistent spatialized acoustic cues. In LH-AVLN, an agent receives a global mission of two to four goals specified by category, language description, or reference image, and navigates with RGB-D observations, pose, and binaural audio "},"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":"2607.03920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-04T15:25:25Z","cross_cats_sorted":[],"title_canon_sha256":"4b0a99cd053325d7415493ea5195c8e975ff4b3493c8fc3c84ae20170303f005","abstract_canon_sha256":"cc153d2031d3073652887a8a890ff8d5852a15ee067033ee2f6846bd0f4210dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:14.691585Z","signature_b64":"WRxrdyW6MF5LFjD960P+slc+bGp16EAxZyweyar4LUHjesrFGACRI8P3+fddHxlTUmYb511C8ZZuI7b1HG6SDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7cfe58f8f189cbaeacc3837712d559504db1cd5fd63bfd83f094d400cc357c2","last_reissued_at":"2026-07-07T02:18:14.690588Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:14.690588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hechang Chen, Hui Xiong, Rufeng Chen, Sihong Xie, Yue Chang, Zhaofan Zhang, Zili Shao","submitted_at":"2026-07-04T15:25:25Z","abstract_excerpt":"Embodied navigation is moving toward long-horizon missions, yet existing long-horizon benchmarks are largely acoustically silent, and audio-visual navigation tasks typically focus on a single goal. We introduce LH-AVLN, a benchmark for Long-Horizon Audio-Visual-Language Navigation that combines multi-goal mission execution, heterogeneous goal specifications, and persistent spatialized acoustic cues. In LH-AVLN, an agent receives a global mission of two to four goals specified by category, language description, or reference image, and navigates with RGB-D observations, pose, and binaural audio "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03920","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/2607.03920/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":"2607.03920","created_at":"2026-07-07T02:18:14.690695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03920v1","created_at":"2026-07-07T02:18:14.690695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03920","created_at":"2026-07-07T02:18:14.690695+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7H6LD4PDCOL","created_at":"2026-07-07T02:18:14.690695+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7H6LD4PDCOLV2WM","created_at":"2026-07-07T02:18:14.690695+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7H6LD4P","created_at":"2026-07-07T02:18:14.690695+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/U7H6LD4PDCOLV2WMHA3XCLKVSU","json":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU.json","graph_json":"https://pith.science/api/pith-number/U7H6LD4PDCOLV2WMHA3XCLKVSU/graph.json","events_json":"https://pith.science/api/pith-number/U7H6LD4PDCOLV2WMHA3XCLKVSU/events.json","paper":"https://pith.science/paper/U7H6LD4P"},"agent_actions":{"view_html":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU","download_json":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU.json","view_paper":"https://pith.science/paper/U7H6LD4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03920&json=true","fetch_graph":"https://pith.science/api/pith-number/U7H6LD4PDCOLV2WMHA3XCLKVSU/graph.json","fetch_events":"https://pith.science/api/pith-number/U7H6LD4PDCOLV2WMHA3XCLKVSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU/action/storage_attestation","attest_author":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU/action/author_attestation","sign_citation":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU/action/citation_signature","submit_replication":"https://pith.science/pith/U7H6LD4PDCOLV2WMHA3XCLKVSU/action/replication_record"}},"created_at":"2026-07-07T02:18:14.690695+00:00","updated_at":"2026-07-07T02:18:14.690695+00:00"}