{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:575MPIKYUREC5UGEBZFVFUYHED","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"02d0dd534ff209788e77b0a531b0b23578b37a96c2054da37a3a46534ee16384","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-26T00:23:00Z","title_canon_sha256":"2368a43d7d7078d6a7f445e7a789bafb8a43a897cb5cea4daf53a0c7827daa7b"},"schema_version":"1.0","source":{"id":"2011.13922","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13922","created_at":"2026-07-05T02:26:52Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13922v2","created_at":"2026-07-05T02:26:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13922","created_at":"2026-07-05T02:26:52Z"},{"alias_kind":"pith_short_12","alias_value":"575MPIKYUREC","created_at":"2026-07-05T02:26:52Z"},{"alias_kind":"pith_short_16","alias_value":"575MPIKYUREC5UGE","created_at":"2026-07-05T02:26:52Z"},{"alias_kind":"pith_short_8","alias_value":"575MPIKY","created_at":"2026-07-05T02:26:52Z"}],"graph_snapshots":[{"event_id":"sha256:7128b15eac0e1ac23529135bcfdec85cd44b1b70e4c606a38c1f2af405f89058","target":"graph","created_at":"2026-07-05T02:26:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.13922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cristian Rodriguez-Opazo, Qi Wu, Stephen Gould, Yicong Hong, Yuankai Qi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-26T00:23:00Z","title":"A Recurrent Vision-and-Language BERT for Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13922","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2e7b612afca5f395fa691aa29ffa3f25fa4a7f164317bad45a8e8131bdf69e2","target":"record","created_at":"2026-07-05T02:26:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"02d0dd534ff209788e77b0a531b0b23578b37a96c2054da37a3a46534ee16384","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-26T00:23:00Z","title_canon_sha256":"2368a43d7d7078d6a7f445e7a789bafb8a43a897cb5cea4daf53a0c7827daa7b"},"schema_version":"1.0","source":{"id":"2011.13922","kind":"arxiv","version":2}},"canonical_sha256":"effac7a158a4482ed0c40e4b52d30720d502c544d88b02b08bb9d4361397f6e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"effac7a158a4482ed0c40e4b52d30720d502c544d88b02b08bb9d4361397f6e7","first_computed_at":"2026-07-05T02:26:52.639920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:52.639920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KNEa09PEt8nzxVRKx1aXlmzAg2UeMUB7LjNSca8RTAg38HoSdqk8mHqNSXFLzg6CfgUQXnZWMdQR+fpD0qp4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:52.640307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.13922","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2e7b612afca5f395fa691aa29ffa3f25fa4a7f164317bad45a8e8131bdf69e2","sha256:7128b15eac0e1ac23529135bcfdec85cd44b1b70e4c606a38c1f2af405f89058"],"state_sha256":"c7b4276387bcbbf5b1b00c8e66182fe6d257b3473a80e8f151070551f0256030"}