{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UJS7QCPOT7ZPBWBLLFVMT2BMGX","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":"b1dd82045f26d8e27dffc948541fff11005e1f1cac0928b303a03167296a048d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-10T16:04:49Z","title_canon_sha256":"dbe3b9389b35a0c523b88041d8430bdc649f2dbae2f066b02cf09167bfe31caf"},"schema_version":"1.0","source":{"id":"2111.05759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05759","created_at":"2026-07-05T04:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05759v2","created_at":"2026-07-05T04:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05759","created_at":"2026-07-05T04:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"UJS7QCPOT7ZP","created_at":"2026-07-05T04:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"UJS7QCPOT7ZPBWBL","created_at":"2026-07-05T04:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"UJS7QCPO","created_at":"2026-07-05T04:40:47Z"}],"graph_snapshots":[{"event_id":"sha256:b91d95b8b53463a106a41a42fc2d7b2a308a4ed4e6bb1d12af18ba9ce9b5ff37","target":"graph","created_at":"2026-07-05T04:40:47Z","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/2111.05759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language Navigation (VLN) is a task that an agent is required to follow a language instruction to navigate to the goal position, which relies on the ongoing interactions with the environment during moving. Recent Transformer-based VLN methods have made great progress benefiting from the direct connections between visual observations and the language instruction via the multimodal cross-attention mechanism. However, these methods usually represent temporal context as a fixed-length vector by using an LSTM decoder or using manually designed hidden states to build a recurrent Transform","authors_text":"Chuang Lin, Gholamreza Haffari, Jianfei Cai, Lizhen Qu, Yi Jiang, Zehuan Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-10T16:04:49Z","title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05759","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:e2909bcf64b90826266cb5b001e419a10ff6f46e8ad70b8dcdc7f0fec4efe15a","target":"record","created_at":"2026-07-05T04:40:47Z","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":"b1dd82045f26d8e27dffc948541fff11005e1f1cac0928b303a03167296a048d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-10T16:04:49Z","title_canon_sha256":"dbe3b9389b35a0c523b88041d8430bdc649f2dbae2f066b02cf09167bfe31caf"},"schema_version":"1.0","source":{"id":"2111.05759","kind":"arxiv","version":2}},"canonical_sha256":"a265f809ee9ff2f0d82b596ac9e82c35c8b6452d390f11b5a461bfa1b1c3440e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a265f809ee9ff2f0d82b596ac9e82c35c8b6452d390f11b5a461bfa1b1c3440e","first_computed_at":"2026-07-05T04:40:47.687652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:47.687652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k4VBGVh2mZ4gbo7LM/3otaPlNZwizDn60ffnFeFROuAa5F3HOQisUkhvUY2ihGRJkws1yTobMTK/D5QwXtSIAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:47.688047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.05759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2909bcf64b90826266cb5b001e419a10ff6f46e8ad70b8dcdc7f0fec4efe15a","sha256:b91d95b8b53463a106a41a42fc2d7b2a308a4ed4e6bb1d12af18ba9ce9b5ff37"],"state_sha256":"6a7af60223681b4ee94bac154c6433798a57b1c547a94659b169eb98541aaef1"}