{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FXRS5CRXC7B5DITRZGAK6U66YH","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":"6f409b4ad837c6905fcb147db76bab68f2c679dda3edaa39e4697227065168f8","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-22T05:26:50Z","title_canon_sha256":"e2bea99bca756b4b2196489c39f1c2b4ef4cc8e30e8b9744a2823bb948142128"},"schema_version":"1.0","source":{"id":"2307.11984","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11984","created_at":"2026-07-05T06:33:37Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11984v1","created_at":"2026-07-05T06:33:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11984","created_at":"2026-07-05T06:33:37Z"},{"alias_kind":"pith_short_12","alias_value":"FXRS5CRXC7B5","created_at":"2026-07-05T06:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FXRS5CRXC7B5DITR","created_at":"2026-07-05T06:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FXRS5CRX","created_at":"2026-07-05T06:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:86f6642a230780a89b7ae1e40166fb42a6d4e648f6f9a68a74da03b94dea86ae","target":"graph","created_at":"2026-07-05T06:33:37Z","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/2307.11984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language navigation (VLN) requires an embodied agent to navigate in realistic 3D environments using natural language instructions. Existing VLN methods suffer from training on small-scale environments or unreasonable path-instruction datasets, limiting the generalization to unseen environments. There are massive house tour videos on YouTube, providing abundant real navigation experiences and layout information. However, these videos have not been explored for VLN before. In this paper, we propose to learn an agent from these videos by creating a large-scale dataset which comprises r","authors_text":"Chuang Gan, Diwei Huang, Kunyang Lin, Mingkui Tan, Peihao Chen, Thomas H. Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-22T05:26:50Z","title":"Learning Vision-and-Language Navigation from YouTube Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11984","kind":"arxiv","version":1},"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":"sha256:3b67a9b826ccb4c6d1db95f726a2bef5f4a96146c5b634e4efc8e3c3ff02b215","target":"record","created_at":"2026-07-05T06:33:37Z","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":"6f409b4ad837c6905fcb147db76bab68f2c679dda3edaa39e4697227065168f8","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-22T05:26:50Z","title_canon_sha256":"e2bea99bca756b4b2196489c39f1c2b4ef4cc8e30e8b9744a2823bb948142128"},"schema_version":"1.0","source":{"id":"2307.11984","kind":"arxiv","version":1}},"canonical_sha256":"2de32e8a3717c3d1a271c980af53dec1cd8c49e8de6229349f5ed25ef5bc40b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2de32e8a3717c3d1a271c980af53dec1cd8c49e8de6229349f5ed25ef5bc40b2","first_computed_at":"2026-07-05T06:33:37.152993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:37.152993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iGDVTXqUWrXHZRR8q9UBkwlbYksEkpNpeKp/b5LO4aMuN34ZeNDaMOuB1UPtZ0LjLRPq5WmYYifqw/1q5WzyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:37.153447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.11984","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b67a9b826ccb4c6d1db95f726a2bef5f4a96146c5b634e4efc8e3c3ff02b215","sha256:86f6642a230780a89b7ae1e40166fb42a6d4e648f6f9a68a74da03b94dea86ae"],"state_sha256":"ff38b53e20bfe620b275071454f482e8495bf4522a94a3379b090a147e05042b"}