{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LTG7HVJNM7BFKHGGVGJV7DDRWY","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":"9cc353972e1a83eac0440a1c1dc00302f939a0c8b4d05ac6bbf7e7e91fcbbaba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:59Z","title_canon_sha256":"6e852310a52152ef282e0695f2f89fae75be489b6b5def1188a21a871675c76e"},"schema_version":"1.0","source":{"id":"2506.17221","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17221","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17221v2","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17221","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"pith_short_12","alias_value":"LTG7HVJNM7BF","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"LTG7HVJNM7BFKHGG","created_at":"2026-07-05T11:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"LTG7HVJN","created_at":"2026-07-05T11:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:c13dcaafaee66262a95ab771cca2b749216d36509a04bcc1b38c0a650d3ba3ce","target":"graph","created_at":"2026-07-05T11:26:53Z","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/2506.17221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Navigation (VLN) is a core challenge in embodied AI, requiring agents to navigate real-world environments using natural language instructions. Current language model-based navigation systems operate on discrete topological graphs, limiting path planning to predefined node connections. We propose VLN-R1, an end-to-end framework that leverages Large Vision-Language Models (LVLM) to directly translate egocentric video streams into continuous navigation actions, adopting GRPO-based training inspired by DeepSeek-R1. To enable effective training, we first construct the VLN-Ego datase","authors_text":"Hengshuang Zhao, Jiaqi Wang, Yizhou Yu, Zhangyang Qi, Zhixiong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:59Z","title":"VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17221","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:e7436246fd53721aeca92ea7172d10637c805b191f2f53f6aa742cd09772c886","target":"record","created_at":"2026-07-05T11:26:53Z","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":"9cc353972e1a83eac0440a1c1dc00302f939a0c8b4d05ac6bbf7e7e91fcbbaba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:59:59Z","title_canon_sha256":"6e852310a52152ef282e0695f2f89fae75be489b6b5def1188a21a871675c76e"},"schema_version":"1.0","source":{"id":"2506.17221","kind":"arxiv","version":2}},"canonical_sha256":"5ccdf3d52d67c2551cc6a9935f8c71b6293cf591d2dea225968dc56b48aec784","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ccdf3d52d67c2551cc6a9935f8c71b6293cf591d2dea225968dc56b48aec784","first_computed_at":"2026-07-05T11:26:53.241113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:53.241113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1nzTP9hhCr/1fP0HIWmgOFWbt9Z2/K+KkI7RQ6T2nijAFEg0GRPyO+iyFX2iYHQwtZxFzHdVKXPPuoYO9b83Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:53.241605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17221","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7436246fd53721aeca92ea7172d10637c805b191f2f53f6aa742cd09772c886","sha256:c13dcaafaee66262a95ab771cca2b749216d36509a04bcc1b38c0a650d3ba3ce"],"state_sha256":"985a6b959cdad57cab8f7f22a5c8fb795d00a8a91d3518b18f928d5b6a9750cd"}