{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IIBJR3N6E75HMCWCRZLUM5ZGYX","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":"36f1a20205b6b0fd5f02f9269c3eb0ab7070d8c276bf55f10c9be088013b5c90","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-12T11:08:24Z","title_canon_sha256":"1ffb15ccf54bda059eb5e82704c1a28a1e2a47b8a9b7a9ee39ce656023000d4b"},"schema_version":"1.0","source":{"id":"2307.06082","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06082","created_at":"2026-07-05T07:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06082v2","created_at":"2026-07-05T07:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06082","created_at":"2026-07-05T07:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"IIBJR3N6E75H","created_at":"2026-07-05T07:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"IIBJR3N6E75HMCWC","created_at":"2026-07-05T07:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"IIBJR3N6","created_at":"2026-07-05T07:36:52Z"}],"graph_snapshots":[{"event_id":"sha256:05933b9994b904d6cd42c9222d78348829eabb2df4f549106939dea176383e4c","target":"graph","created_at":"2026-07-05T07:36:52Z","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/2307.06082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation~(VLN) which requires visual and natural language understanding as well as spatial and temporal reasoning capabilities. The embodied agent needs to ground its understanding of navigation instructions in observations of a real-world environment like Street View. Despite the impressive results of LLMs in other research areas, it is an ongoing problem of how to best connect them with an interactive vis","authors_text":"Raphael Schumann, Stefan Riezler, Tsu-Jui Fu, Wanrong Zhu, Weixi Feng, William Yang Wang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-12T11:08:24Z","title":"VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06082","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:a7364dffe6ddfad3aa97e8da0bfc0a8a3c0acfca817748ea2e04a111229133df","target":"record","created_at":"2026-07-05T07:36:52Z","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":"36f1a20205b6b0fd5f02f9269c3eb0ab7070d8c276bf55f10c9be088013b5c90","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-12T11:08:24Z","title_canon_sha256":"1ffb15ccf54bda059eb5e82704c1a28a1e2a47b8a9b7a9ee39ce656023000d4b"},"schema_version":"1.0","source":{"id":"2307.06082","kind":"arxiv","version":2}},"canonical_sha256":"420298edbe27fa760ac28e57467726c5d941d3783ebbb1edd50a7a64d07d0317","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"420298edbe27fa760ac28e57467726c5d941d3783ebbb1edd50a7a64d07d0317","first_computed_at":"2026-07-05T07:36:52.532808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:52.532808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Oa0ytrzbu6rgK6Y+EkLMJMSk2ww1P3QCleH9MoHGiPo/G7v/S00ZC8b6MIfS59+WPO9/uOP39YbRoIIBoH+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:52.533303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06082","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7364dffe6ddfad3aa97e8da0bfc0a8a3c0acfca817748ea2e04a111229133df","sha256:05933b9994b904d6cd42c9222d78348829eabb2df4f549106939dea176383e4c"],"state_sha256":"a8748171f56560e8b13813ab096e9ac7709773b9c0fc06d0b4fd7cb6efcb52b7"}