{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G5E4D5APQDKDFNUAWRMFEO4EU4","short_pith_number":"pith:G5E4D5AP","schema_version":"1.0","canonical_sha256":"3749c1f40f80d432b680b458523b84a702950413f1f47889d68361beba138eae","source":{"kind":"arxiv","id":"2607.17767","version":1},"attestation_state":"computed","paper":{"title":"VLN-AVP: Zero-Shot Vision-Language Navigation with Hybrid Long-Short-Term Memory for Autonomous Valet Parking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Changze Li, Hantian Shi, Jia Cai, Jiyuan Cai, Ming Yang, Tong Qin, Xiangru Mu, Xiaoxue Liu, Yajing Sun, Yijian Li","submitted_at":"2026-07-20T10:01:20Z","abstract_excerpt":"Existing methods in Autonomous Valet Parking (AVP) typically rely on pre-built maps, which severely restricts their scalability to unseen environments and open-vocabulary targets. Inspired by the application of Vision-Language Models (VLMs) in Vision-Language Navigation (VLN) tasks, we propose VLN-AVP, a zero-shot navigation framework for AVP tasks. By combining the precise spatial perception of a Bird's-Eye-View (BEV) model with the general intelligence of VLMs, our framework 1) eliminates the dependency on pre-built maps, 2) interprets semantic environmental contexts in parking scenarios, an"},"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":"2607.17767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-20T10:01:20Z","cross_cats_sorted":[],"title_canon_sha256":"4b1a830a85d9902a68c6369c33b46312577a270181cd10a68090bd7b8b12ba8d","abstract_canon_sha256":"4fb791f2f79c4458bf222038cef1795d0633c24c0c63a33fd4c1fc0ffb0e28ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:21:59.130214Z","signature_b64":"czP7OnEBwOFsmOZH3yaUxLdiP2BZgemRgGYMd3TYwMQc15FMe8wy1RCPSod/k1crH+3LX6CHRLsC0h19b4Z/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3749c1f40f80d432b680b458523b84a702950413f1f47889d68361beba138eae","last_reissued_at":"2026-07-21T02:21:59.129444Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:21:59.129444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLN-AVP: Zero-Shot Vision-Language Navigation with Hybrid Long-Short-Term Memory for Autonomous Valet Parking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Changze Li, Hantian Shi, Jia Cai, Jiyuan Cai, Ming Yang, Tong Qin, Xiangru Mu, Xiaoxue Liu, Yajing Sun, Yijian Li","submitted_at":"2026-07-20T10:01:20Z","abstract_excerpt":"Existing methods in Autonomous Valet Parking (AVP) typically rely on pre-built maps, which severely restricts their scalability to unseen environments and open-vocabulary targets. Inspired by the application of Vision-Language Models (VLMs) in Vision-Language Navigation (VLN) tasks, we propose VLN-AVP, a zero-shot navigation framework for AVP tasks. By combining the precise spatial perception of a Bird's-Eye-View (BEV) model with the general intelligence of VLMs, our framework 1) eliminates the dependency on pre-built maps, 2) interprets semantic environmental contexts in parking scenarios, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17767","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/2607.17767/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":"2607.17767","created_at":"2026-07-21T02:21:59.129835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17767v1","created_at":"2026-07-21T02:21:59.129835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17767","created_at":"2026-07-21T02:21:59.129835+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5E4D5APQDKD","created_at":"2026-07-21T02:21:59.129835+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5E4D5APQDKDFNUA","created_at":"2026-07-21T02:21:59.129835+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5E4D5AP","created_at":"2026-07-21T02:21:59.129835+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/G5E4D5APQDKDFNUAWRMFEO4EU4","json":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4.json","graph_json":"https://pith.science/api/pith-number/G5E4D5APQDKDFNUAWRMFEO4EU4/graph.json","events_json":"https://pith.science/api/pith-number/G5E4D5APQDKDFNUAWRMFEO4EU4/events.json","paper":"https://pith.science/paper/G5E4D5AP"},"agent_actions":{"view_html":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4","download_json":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4.json","view_paper":"https://pith.science/paper/G5E4D5AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17767&json=true","fetch_graph":"https://pith.science/api/pith-number/G5E4D5APQDKDFNUAWRMFEO4EU4/graph.json","fetch_events":"https://pith.science/api/pith-number/G5E4D5APQDKDFNUAWRMFEO4EU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4/action/storage_attestation","attest_author":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4/action/author_attestation","sign_citation":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4/action/citation_signature","submit_replication":"https://pith.science/pith/G5E4D5APQDKDFNUAWRMFEO4EU4/action/replication_record"}},"created_at":"2026-07-21T02:21:59.129835+00:00","updated_at":"2026-07-21T02:21:59.129835+00:00"}