{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5TFXVOT3AGWHUD544BCBJS5OOB","short_pith_number":"pith:5TFXVOT3","schema_version":"1.0","canonical_sha256":"eccb7aba7b01ac7a0fbce04414cbae7052f7547d52b2e282dda5994448063adb","source":{"kind":"arxiv","id":"2203.11591","version":1},"attestation_state":"computed","paper":{"title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Peng Wang, Qi Wu, Yanyuan Qiao, Yicong Hong, Yuankai Qi, Zheng Yu","submitted_at":"2022-03-22T10:17:12Z","abstract_excerpt":"Pre-training has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, previous pre-training methods for VLN either lack the ability to predict future actions or ignore the trajectory contexts, which are essential for a greedy navigation process. In this work, to promote the learning of spatio-temporal visual-textual correspondence as well as the agent's capability of decision making, we propose a novel history-and-order aware pre-training paradigm (HOP) with VLN-specific objectives that exploit the past observations and support future action prediction. Spec"},"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":"2203.11591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T10:17:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7967175f150c99b71ec45e996aa3e9072d13588bcb4a8a484f7fe8fc1a2b249e","abstract_canon_sha256":"77833134081e0b7f55f215a1ec9721175256ed688584290d0cef6299bc0a358c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:13.680208Z","signature_b64":"IcWfQ47zV19Ed0yA4RTS0IZke74w+/uvnhVJP7iLpLs6xDP6Hga85EZTUMFyBTW9SBdIfWyJxsn1cAkbw9JKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eccb7aba7b01ac7a0fbce04414cbae7052f7547d52b2e282dda5994448063adb","last_reissued_at":"2026-07-05T04:07:13.679873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:13.679873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Peng Wang, Qi Wu, Yanyuan Qiao, Yicong Hong, Yuankai Qi, Zheng Yu","submitted_at":"2022-03-22T10:17:12Z","abstract_excerpt":"Pre-training has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, previous pre-training methods for VLN either lack the ability to predict future actions or ignore the trajectory contexts, which are essential for a greedy navigation process. In this work, to promote the learning of spatio-temporal visual-textual correspondence as well as the agent's capability of decision making, we propose a novel history-and-order aware pre-training paradigm (HOP) with VLN-specific objectives that exploit the past observations and support future action prediction. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11591","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/2203.11591/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":"2203.11591","created_at":"2026-07-05T04:07:13.679928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.11591v1","created_at":"2026-07-05T04:07:13.679928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11591","created_at":"2026-07-05T04:07:13.679928+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TFXVOT3AGWH","created_at":"2026-07-05T04:07:13.679928+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TFXVOT3AGWHUD54","created_at":"2026-07-05T04:07:13.679928+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TFXVOT3","created_at":"2026-07-05T04:07:13.679928+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/5TFXVOT3AGWHUD544BCBJS5OOB","json":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB.json","graph_json":"https://pith.science/api/pith-number/5TFXVOT3AGWHUD544BCBJS5OOB/graph.json","events_json":"https://pith.science/api/pith-number/5TFXVOT3AGWHUD544BCBJS5OOB/events.json","paper":"https://pith.science/paper/5TFXVOT3"},"agent_actions":{"view_html":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB","download_json":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB.json","view_paper":"https://pith.science/paper/5TFXVOT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.11591&json=true","fetch_graph":"https://pith.science/api/pith-number/5TFXVOT3AGWHUD544BCBJS5OOB/graph.json","fetch_events":"https://pith.science/api/pith-number/5TFXVOT3AGWHUD544BCBJS5OOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB/action/storage_attestation","attest_author":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB/action/author_attestation","sign_citation":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB/action/citation_signature","submit_replication":"https://pith.science/pith/5TFXVOT3AGWHUD544BCBJS5OOB/action/replication_record"}},"created_at":"2026-07-05T04:07:13.679928+00:00","updated_at":"2026-07-05T04:07:13.679928+00:00"}