{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UJS7QCPOT7ZPBWBLLFVMT2BMGX","short_pith_number":"pith:UJS7QCPO","schema_version":"1.0","canonical_sha256":"a265f809ee9ff2f0d82b596ac9e82c35c8b6452d390f11b5a461bfa1b1c3440e","source":{"kind":"arxiv","id":"2111.05759","version":2},"attestation_state":"computed","paper":{"title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Lin, Gholamreza Haffari, Jianfei Cai, Lizhen Qu, Yi Jiang, Zehuan Yuan","submitted_at":"2021-11-10T16:04:49Z","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"},"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":"2111.05759","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-10T16:04:49Z","cross_cats_sorted":[],"title_canon_sha256":"dbe3b9389b35a0c523b88041d8430bdc649f2dbae2f066b02cf09167bfe31caf","abstract_canon_sha256":"b1dd82045f26d8e27dffc948541fff11005e1f1cac0928b303a03167296a048d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:47.688047Z","signature_b64":"k4VBGVh2mZ4gbo7LM/3otaPlNZwizDn60ffnFeFROuAa5F3HOQisUkhvUY2ihGRJkws1yTobMTK/D5QwXtSIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a265f809ee9ff2f0d82b596ac9e82c35c8b6452d390f11b5a461bfa1b1c3440e","last_reissued_at":"2026-07-05T04:40:47.687652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:47.687652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Lin, Gholamreza Haffari, Jianfei Cai, Lizhen Qu, Yi Jiang, Zehuan Yuan","submitted_at":"2021-11-10T16:04:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05759","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/2111.05759/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":"2111.05759","created_at":"2026-07-05T04:40:47.687708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.05759v2","created_at":"2026-07-05T04:40:47.687708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05759","created_at":"2026-07-05T04:40:47.687708+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJS7QCPOT7ZP","created_at":"2026-07-05T04:40:47.687708+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJS7QCPOT7ZPBWBL","created_at":"2026-07-05T04:40:47.687708+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJS7QCPO","created_at":"2026-07-05T04:40:47.687708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX","json":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX.json","graph_json":"https://pith.science/api/pith-number/UJS7QCPOT7ZPBWBLLFVMT2BMGX/graph.json","events_json":"https://pith.science/api/pith-number/UJS7QCPOT7ZPBWBLLFVMT2BMGX/events.json","paper":"https://pith.science/paper/UJS7QCPO"},"agent_actions":{"view_html":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX","download_json":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX.json","view_paper":"https://pith.science/paper/UJS7QCPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.05759&json=true","fetch_graph":"https://pith.science/api/pith-number/UJS7QCPOT7ZPBWBLLFVMT2BMGX/graph.json","fetch_events":"https://pith.science/api/pith-number/UJS7QCPOT7ZPBWBLLFVMT2BMGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX/action/storage_attestation","attest_author":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX/action/author_attestation","sign_citation":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX/action/citation_signature","submit_replication":"https://pith.science/pith/UJS7QCPOT7ZPBWBLLFVMT2BMGX/action/replication_record"}},"created_at":"2026-07-05T04:40:47.687708+00:00","updated_at":"2026-07-05T04:40:47.687708+00:00"}