{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YRBLCGRJVSW2X5A4K552R5M362","short_pith_number":"pith:YRBLCGRJ","schema_version":"1.0","canonical_sha256":"c442b11a29acadabf41c577ba8f59bf6ae7f86b93b125eb8b52c9d9888f88ed5","source":{"kind":"arxiv","id":"2403.18454","version":1},"attestation_state":"computed","paper":{"title":"Scaling Vision-and-Language Navigation With Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Biplab Banerjee, Mahesh Bhupati, Valay Bundele","submitted_at":"2024-03-27T11:13:20Z","abstract_excerpt":"The study of vision-and-language navigation (VLN) has typically relied on expert trajectories, which may not always be available in real-world situations due to the significant effort required to collect them. On the other hand, existing approaches to training VLN agents that go beyond available expert data involve data augmentations or online exploration which can be tedious and risky. In contrast, it is easy to access large repositories of suboptimal offline trajectories. Inspired by research in offline reinforcement learning (ORL), we introduce a new problem setup of VLN-ORL which studies V"},"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":"2403.18454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T11:13:20Z","cross_cats_sorted":[],"title_canon_sha256":"c6c393846df846284a6ccb00f1136dd6c699563320eb71a0268ba77634b9be00","abstract_canon_sha256":"b28cc6ff69fd94a5e0148a008478acb8682cfd212b8f5f9122318ca900651554"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:22.913147Z","signature_b64":"To9g3XLpwTCVa5nKdJbSDgfiv3C6dw3lr8vXUCL/ckzbZHrkTUxQepOOlQ0yacC+hhWE7/mM111zgWaVJbn1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c442b11a29acadabf41c577ba8f59bf6ae7f86b93b125eb8b52c9d9888f88ed5","last_reissued_at":"2026-07-05T08:01:22.912687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:22.912687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Vision-and-Language Navigation With Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Grover, Biplab Banerjee, Mahesh Bhupati, Valay Bundele","submitted_at":"2024-03-27T11:13:20Z","abstract_excerpt":"The study of vision-and-language navigation (VLN) has typically relied on expert trajectories, which may not always be available in real-world situations due to the significant effort required to collect them. On the other hand, existing approaches to training VLN agents that go beyond available expert data involve data augmentations or online exploration which can be tedious and risky. In contrast, it is easy to access large repositories of suboptimal offline trajectories. Inspired by research in offline reinforcement learning (ORL), we introduce a new problem setup of VLN-ORL which studies V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18454","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/2403.18454/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":"2403.18454","created_at":"2026-07-05T08:01:22.912744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18454v1","created_at":"2026-07-05T08:01:22.912744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18454","created_at":"2026-07-05T08:01:22.912744+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRBLCGRJVSW2","created_at":"2026-07-05T08:01:22.912744+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRBLCGRJVSW2X5A4","created_at":"2026-07-05T08:01:22.912744+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRBLCGRJ","created_at":"2026-07-05T08:01:22.912744+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01754","citing_title":"Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362","json":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362.json","graph_json":"https://pith.science/api/pith-number/YRBLCGRJVSW2X5A4K552R5M362/graph.json","events_json":"https://pith.science/api/pith-number/YRBLCGRJVSW2X5A4K552R5M362/events.json","paper":"https://pith.science/paper/YRBLCGRJ"},"agent_actions":{"view_html":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362","download_json":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362.json","view_paper":"https://pith.science/paper/YRBLCGRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18454&json=true","fetch_graph":"https://pith.science/api/pith-number/YRBLCGRJVSW2X5A4K552R5M362/graph.json","fetch_events":"https://pith.science/api/pith-number/YRBLCGRJVSW2X5A4K552R5M362/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362/action/storage_attestation","attest_author":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362/action/author_attestation","sign_citation":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362/action/citation_signature","submit_replication":"https://pith.science/pith/YRBLCGRJVSW2X5A4K552R5M362/action/replication_record"}},"created_at":"2026-07-05T08:01:22.912744+00:00","updated_at":"2026-07-05T08:01:22.912744+00:00"}