{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QPHCFXIT7HZQZIQIGB7DMN3CQE","short_pith_number":"pith:QPHCFXIT","schema_version":"1.0","canonical_sha256":"83ce22dd13f9f30ca208307e3637628114715413c422a6b2f009e240a9a90b59","source":{"kind":"arxiv","id":"2607.13461","version":1},"attestation_state":"computed","paper":{"title":"Joint On-and-Off Policy Learning for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kevin Zheng, Liang Lin, Lin Zhao, Qingrong He","submitted_at":"2026-07-15T05:46:34Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) necessitates an embodied agent to navigate in the physical world by adhering to natural language instructions. Recent advancements in Vision-Language Models (VLM) have propelled the development of VLM-based VLN methods with two predominant paradigms: (1) imitation learning (IL) on expert demonstrations, followed by the Dataset Aggregation (DAgger) algorithm to bolster error recovery capabilities; (2) reinforcement learning (RL) driven by verifiable rewards to enhance reasoning and exploration. A notable gap is the absence of integration between these two di"},"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":"2607.13461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-15T05:46:34Z","cross_cats_sorted":[],"title_canon_sha256":"c5f50a47d45003b9e59c5aa03c1c7d11cb2f12b36c11749e8ba20b8ab3cc4b63","abstract_canon_sha256":"1033f1e5321655acabfc1e24e4a6ce8c757293013ca9c8c4b2c3d91b86ce42ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:14.219541Z","signature_b64":"eY3/AgSsUTAYgluCsHl0sWskQVXgt/9CdqgxXPCPC6yMSuQPgs3Q2+YBg1qVWbkJyaVt0bSrW9MTPhLRVa/3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83ce22dd13f9f30ca208307e3637628114715413c422a6b2f009e240a9a90b59","last_reissued_at":"2026-07-16T01:22:14.218665Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:14.218665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint On-and-Off Policy Learning for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Kevin Zheng, Liang Lin, Lin Zhao, Qingrong He","submitted_at":"2026-07-15T05:46:34Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) necessitates an embodied agent to navigate in the physical world by adhering to natural language instructions. Recent advancements in Vision-Language Models (VLM) have propelled the development of VLM-based VLN methods with two predominant paradigms: (1) imitation learning (IL) on expert demonstrations, followed by the Dataset Aggregation (DAgger) algorithm to bolster error recovery capabilities; (2) reinforcement learning (RL) driven by verifiable rewards to enhance reasoning and exploration. A notable gap is the absence of integration between these two di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13461","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/2607.13461/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":"2607.13461","created_at":"2026-07-16T01:22:14.219114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13461v1","created_at":"2026-07-16T01:22:14.219114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13461","created_at":"2026-07-16T01:22:14.219114+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPHCFXIT7HZQ","created_at":"2026-07-16T01:22:14.219114+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPHCFXIT7HZQZIQI","created_at":"2026-07-16T01:22:14.219114+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPHCFXIT","created_at":"2026-07-16T01:22:14.219114+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/QPHCFXIT7HZQZIQIGB7DMN3CQE","json":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE.json","graph_json":"https://pith.science/api/pith-number/QPHCFXIT7HZQZIQIGB7DMN3CQE/graph.json","events_json":"https://pith.science/api/pith-number/QPHCFXIT7HZQZIQIGB7DMN3CQE/events.json","paper":"https://pith.science/paper/QPHCFXIT"},"agent_actions":{"view_html":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE","download_json":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE.json","view_paper":"https://pith.science/paper/QPHCFXIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13461&json=true","fetch_graph":"https://pith.science/api/pith-number/QPHCFXIT7HZQZIQIGB7DMN3CQE/graph.json","fetch_events":"https://pith.science/api/pith-number/QPHCFXIT7HZQZIQIGB7DMN3CQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE/action/storage_attestation","attest_author":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE/action/author_attestation","sign_citation":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE/action/citation_signature","submit_replication":"https://pith.science/pith/QPHCFXIT7HZQZIQIGB7DMN3CQE/action/replication_record"}},"created_at":"2026-07-16T01:22:14.219114+00:00","updated_at":"2026-07-16T01:22:14.219114+00:00"}