{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KG72DH5E5II4VTABQGXHLRBLAP","short_pith_number":"pith:KG72DH5E","schema_version":"1.0","canonical_sha256":"51bfa19fa4ea11cacc0181ae75c42b03d78352985ba46aa27f64022a3fb55620","source":{"kind":"arxiv","id":"2303.08409","version":1},"attestation_state":"computed","paper":{"title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiayi Shao, Wenguan Wang, Xiaohan Wang, Yi Yang","submitted_at":"2023-03-15T07:21:28Z","abstract_excerpt":"Recently, visual-language navigation (VLN) -- entailing robot agents to follow navigation instructions -- has shown great advance. However, existing literature put most emphasis on interpreting instructions into actions, only delivering \"dumb\" wayfinding agents. In this article, we devise LANA, a language-capable navigation agent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respective"},"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":"2303.08409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-15T07:21:28Z","cross_cats_sorted":["cs.MM","cs.RO"],"title_canon_sha256":"f845aaaf5cae1e78691f48541c0abdf4de60582813017fead5fa9f59fa6693db","abstract_canon_sha256":"7a26eb7452e1541ef1d9399a72ac7d7457f4d8482ddb2526524fa34911589b4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:32.682964Z","signature_b64":"Djh5QpGfxV0s8Cdh0lGEu4ikVLQWF1K9gBBa3XADdfJq82p2QnSfKlUKphsqh1Bn60pnO90syOLB73RpKa48Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51bfa19fa4ea11cacc0181ae75c42b03d78352985ba46aa27f64022a3fb55620","last_reissued_at":"2026-07-05T05:51:32.682541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:32.682541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lana: A Language-Capable Navigator for Instruction Following and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiayi Shao, Wenguan Wang, Xiaohan Wang, Yi Yang","submitted_at":"2023-03-15T07:21:28Z","abstract_excerpt":"Recently, visual-language navigation (VLN) -- entailing robot agents to follow navigation instructions -- has shown great advance. However, existing literature put most emphasis on interpreting instructions into actions, only delivering \"dumb\" wayfinding agents. In this article, we devise LANA, a language-capable navigation agent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08409","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/2303.08409/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":"2303.08409","created_at":"2026-07-05T05:51:32.682599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08409v1","created_at":"2026-07-05T05:51:32.682599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08409","created_at":"2026-07-05T05:51:32.682599+00:00"},{"alias_kind":"pith_short_12","alias_value":"KG72DH5E5II4","created_at":"2026-07-05T05:51:32.682599+00:00"},{"alias_kind":"pith_short_16","alias_value":"KG72DH5E5II4VTAB","created_at":"2026-07-05T05:51:32.682599+00:00"},{"alias_kind":"pith_short_8","alias_value":"KG72DH5E","created_at":"2026-07-05T05:51:32.682599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.09547","citing_title":"GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP","json":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP.json","graph_json":"https://pith.science/api/pith-number/KG72DH5E5II4VTABQGXHLRBLAP/graph.json","events_json":"https://pith.science/api/pith-number/KG72DH5E5II4VTABQGXHLRBLAP/events.json","paper":"https://pith.science/paper/KG72DH5E"},"agent_actions":{"view_html":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP","download_json":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP.json","view_paper":"https://pith.science/paper/KG72DH5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08409&json=true","fetch_graph":"https://pith.science/api/pith-number/KG72DH5E5II4VTABQGXHLRBLAP/graph.json","fetch_events":"https://pith.science/api/pith-number/KG72DH5E5II4VTABQGXHLRBLAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP/action/storage_attestation","attest_author":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP/action/author_attestation","sign_citation":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP/action/citation_signature","submit_replication":"https://pith.science/pith/KG72DH5E5II4VTABQGXHLRBLAP/action/replication_record"}},"created_at":"2026-07-05T05:51:32.682599+00:00","updated_at":"2026-07-05T05:51:32.682599+00:00"}