{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:575MPIKYUREC5UGEBZFVFUYHED","short_pith_number":"pith:575MPIKY","schema_version":"1.0","canonical_sha256":"effac7a158a4482ed0c40e4b52d30720d502c544d88b02b08bb9d4361397f6e7","source":{"kind":"arxiv","id":"2011.13922","version":2},"attestation_state":"computed","paper":{"title":"A Recurrent Vision-and-Language BERT for Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cristian Rodriguez-Opazo, Qi Wu, Stephen Gould, Yicong Hong, Yuankai Qi","submitted_at":"2020-11-26T00:23:00Z","abstract_excerpt":"Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language(V&L) BERT. However, its application for the task of vision-and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state informa"},"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":"2011.13922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-26T00:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"2368a43d7d7078d6a7f445e7a789bafb8a43a897cb5cea4daf53a0c7827daa7b","abstract_canon_sha256":"02d0dd534ff209788e77b0a531b0b23578b37a96c2054da37a3a46534ee16384"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:52.640307Z","signature_b64":"KNEa09PEt8nzxVRKx1aXlmzAg2UeMUB7LjNSca8RTAg38HoSdqk8mHqNSXFLzg6CfgUQXnZWMdQR+fpD0qp4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"effac7a158a4482ed0c40e4b52d30720d502c544d88b02b08bb9d4361397f6e7","last_reissued_at":"2026-07-05T02:26:52.639920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:52.639920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Recurrent Vision-and-Language BERT for Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cristian Rodriguez-Opazo, Qi Wu, Stephen Gould, Yicong Hong, Yuankai Qi","submitted_at":"2020-11-26T00:23:00Z","abstract_excerpt":"Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language(V&L) BERT. However, its application for the task of vision-and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13922","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/2011.13922/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":"2011.13922","created_at":"2026-07-05T02:26:52.639975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.13922v2","created_at":"2026-07-05T02:26:52.639975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13922","created_at":"2026-07-05T02:26:52.639975+00:00"},{"alias_kind":"pith_short_12","alias_value":"575MPIKYUREC","created_at":"2026-07-05T02:26:52.639975+00:00"},{"alias_kind":"pith_short_16","alias_value":"575MPIKYUREC5UGE","created_at":"2026-07-05T02:26:52.639975+00:00"},{"alias_kind":"pith_short_8","alias_value":"575MPIKY","created_at":"2026-07-05T02:26:52.639975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17473","citing_title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","ref_index":122,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED","json":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED.json","graph_json":"https://pith.science/api/pith-number/575MPIKYUREC5UGEBZFVFUYHED/graph.json","events_json":"https://pith.science/api/pith-number/575MPIKYUREC5UGEBZFVFUYHED/events.json","paper":"https://pith.science/paper/575MPIKY"},"agent_actions":{"view_html":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED","download_json":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED.json","view_paper":"https://pith.science/paper/575MPIKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.13922&json=true","fetch_graph":"https://pith.science/api/pith-number/575MPIKYUREC5UGEBZFVFUYHED/graph.json","fetch_events":"https://pith.science/api/pith-number/575MPIKYUREC5UGEBZFVFUYHED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED/action/storage_attestation","attest_author":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED/action/author_attestation","sign_citation":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED/action/citation_signature","submit_replication":"https://pith.science/pith/575MPIKYUREC5UGEBZFVFUYHED/action/replication_record"}},"created_at":"2026-07-05T02:26:52.639975+00:00","updated_at":"2026-07-05T02:26:52.639975+00:00"}