{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IIBJR3N6E75HMCWCRZLUM5ZGYX","short_pith_number":"pith:IIBJR3N6","schema_version":"1.0","canonical_sha256":"420298edbe27fa760ac28e57467726c5d941d3783ebbb1edd50a7a64d07d0317","source":{"kind":"arxiv","id":"2307.06082","version":2},"attestation_state":"computed","paper":{"title":"VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Raphael Schumann, Stefan Riezler, Tsu-Jui Fu, Wanrong Zhu, Weixi Feng, William Yang Wang","submitted_at":"2023-07-12T11:08:24Z","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"},"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":"2307.06082","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-12T11:08:24Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"1ffb15ccf54bda059eb5e82704c1a28a1e2a47b8a9b7a9ee39ce656023000d4b","abstract_canon_sha256":"36f1a20205b6b0fd5f02f9269c3eb0ab7070d8c276bf55f10c9be088013b5c90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:52.533303Z","signature_b64":"/Oa0ytrzbu6rgK6Y+EkLMJMSk2ww1P3QCleH9MoHGiPo/G7v/S00ZC8b6MIfS59+WPO9/uOP39YbRoIIBoH+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"420298edbe27fa760ac28e57467726c5d941d3783ebbb1edd50a7a64d07d0317","last_reissued_at":"2026-07-05T07:36:52.532808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:52.532808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Raphael Schumann, Stefan Riezler, Tsu-Jui Fu, Wanrong Zhu, Weixi Feng, William Yang Wang","submitted_at":"2023-07-12T11:08:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06082","kind":"arxiv","version":2},"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/2307.06082/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":"2307.06082","created_at":"2026-07-05T07:36:52.532866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06082v2","created_at":"2026-07-05T07:36:52.532866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06082","created_at":"2026-07-05T07:36:52.532866+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIBJR3N6E75H","created_at":"2026-07-05T07:36:52.532866+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIBJR3N6E75HMCWC","created_at":"2026-07-05T07:36:52.532866+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIBJR3N6","created_at":"2026-07-05T07:36:52.532866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.15852","citing_title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX","json":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX.json","graph_json":"https://pith.science/api/pith-number/IIBJR3N6E75HMCWCRZLUM5ZGYX/graph.json","events_json":"https://pith.science/api/pith-number/IIBJR3N6E75HMCWCRZLUM5ZGYX/events.json","paper":"https://pith.science/paper/IIBJR3N6"},"agent_actions":{"view_html":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX","download_json":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX.json","view_paper":"https://pith.science/paper/IIBJR3N6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06082&json=true","fetch_graph":"https://pith.science/api/pith-number/IIBJR3N6E75HMCWCRZLUM5ZGYX/graph.json","fetch_events":"https://pith.science/api/pith-number/IIBJR3N6E75HMCWCRZLUM5ZGYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX/action/storage_attestation","attest_author":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX/action/author_attestation","sign_citation":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX/action/citation_signature","submit_replication":"https://pith.science/pith/IIBJR3N6E75HMCWCRZLUM5ZGYX/action/replication_record"}},"created_at":"2026-07-05T07:36:52.532866+00:00","updated_at":"2026-07-05T07:36:52.532866+00:00"}