{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G7DMDYRAGAFND6KVETP7CBR7CO","short_pith_number":"pith:G7DMDYRA","schema_version":"1.0","canonical_sha256":"37c6c1e220300ad1f95524dff1063f13b02e67d43a340424a686bacb2e35569a","source":{"kind":"arxiv","id":"2212.04385","version":2},"attestation_state":"computed","paper":{"title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dong An, Jing Shao, Liang Wang, Tieniu Tan, Yangguang Li, Yan Huang, Yuankai Qi","submitted_at":"2022-12-08T16:27:54Z","abstract_excerpt":"Large-scale pre-training has shown promising results on the vision-and-language navigation (VLN) task. However, most existing pre-training methods employ discrete panoramas to learn visual-textual associations. This requires the model to implicitly correlate incomplete, duplicate observations within the panoramas, which may impair an agent's spatial understanding. Thus, we propose a new map-based pre-training paradigm that is spatial-aware for use in VLN. Concretely, we build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dep"},"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":"2212.04385","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T16:27:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"71a64561198914cc85a38c053b17e0b0e544431c33cea39b5e323ada7ef842c3","abstract_canon_sha256":"f3efd0752627389a1fd00bde231e07eeb5d9ba4db57ec2a3ff1c8367ce21ecb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:11.784820Z","signature_b64":"7KnvdYf/qpTHRJzi+bkqE706N9e2N+PY1iIvPwLRfNq+lqd5X4ZZVh3mvPEUC7m8mcaiIaCn5mOhLmNTChLOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37c6c1e220300ad1f95524dff1063f13b02e67d43a340424a686bacb2e35569a","last_reissued_at":"2026-07-05T06:37:11.784323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:11.784323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEVBert: Multimodal Map Pre-training for Language-guided Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dong An, Jing Shao, Liang Wang, Tieniu Tan, Yangguang Li, Yan Huang, Yuankai Qi","submitted_at":"2022-12-08T16:27:54Z","abstract_excerpt":"Large-scale pre-training has shown promising results on the vision-and-language navigation (VLN) task. However, most existing pre-training methods employ discrete panoramas to learn visual-textual associations. This requires the model to implicitly correlate incomplete, duplicate observations within the panoramas, which may impair an agent's spatial understanding. Thus, we propose a new map-based pre-training paradigm that is spatial-aware for use in VLN. Concretely, we build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04385","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/2212.04385/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":"2212.04385","created_at":"2026-07-05T06:37:11.784387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04385v2","created_at":"2026-07-05T06:37:11.784387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04385","created_at":"2026-07-05T06:37:11.784387+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7DMDYRAGAFN","created_at":"2026-07-05T06:37:11.784387+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7DMDYRAGAFND6KV","created_at":"2026-07-05T06:37:11.784387+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7DMDYRA","created_at":"2026-07-05T06:37:11.784387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01043","citing_title":"DART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03175","citing_title":"Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27807","citing_title":"SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30115","citing_title":"Large Depth Completion Model from Sparse Observations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22036","citing_title":"GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16947","citing_title":"LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2402.15852","citing_title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17097","citing_title":"Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09053","citing_title":"LCGNav: Local Candidate-Aware Geometric Enhancement for General Topological Planning in Vision-Language Navigation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15823","citing_title":"Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17473","citing_title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO","json":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO.json","graph_json":"https://pith.science/api/pith-number/G7DMDYRAGAFND6KVETP7CBR7CO/graph.json","events_json":"https://pith.science/api/pith-number/G7DMDYRAGAFND6KVETP7CBR7CO/events.json","paper":"https://pith.science/paper/G7DMDYRA"},"agent_actions":{"view_html":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO","download_json":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO.json","view_paper":"https://pith.science/paper/G7DMDYRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04385&json=true","fetch_graph":"https://pith.science/api/pith-number/G7DMDYRAGAFND6KVETP7CBR7CO/graph.json","fetch_events":"https://pith.science/api/pith-number/G7DMDYRAGAFND6KVETP7CBR7CO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO/action/storage_attestation","attest_author":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO/action/author_attestation","sign_citation":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO/action/citation_signature","submit_replication":"https://pith.science/pith/G7DMDYRAGAFND6KVETP7CBR7CO/action/replication_record"}},"created_at":"2026-07-05T06:37:11.784387+00:00","updated_at":"2026-07-05T06:37:11.784387+00:00"}