{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2LF3X5UWQ6ZCDYCCCNXPLSQFBE","short_pith_number":"pith:2LF3X5UW","schema_version":"1.0","canonical_sha256":"d2cbbbf69687b221e042136ef5ca050916fb54d827b8ac5d92c38a54e8c153ac","source":{"kind":"arxiv","id":"2412.08591","version":2},"attestation_state":"computed","paper":{"title":"RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ekaterina Radionova, Ivan Laptev, Jingyi Zhang, Kamila Zhumakhanova, Liang Ma, Mingfei Han, Xiaodan Liang, Xiaojun Chang","submitted_at":"2024-12-11T18:10:21Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) suffers from the limited diversity and scale of training data, primarily constrained by the manual curation of existing simulators. To address this, we introduce RoomTour3D, a video-instruction dataset derived from web-based room tour videos that capture real-world indoor spaces and human walking demonstrations. Unlike existing VLN datasets, RoomTour3D leverages the scale and diversity of online videos to generate open-ended human walking trajectories and open-world navigable instructions. To compensate for the lack of navigation data in online videos, we p"},"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":"2412.08591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:10:21Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"65aff648abc3c7342a0c7ee0a664120b9cbe26029d5e36dcbbe2ffa07a495c2c","abstract_canon_sha256":"0471557ead9348367da84f355ad1e08997fde0cb561278942c92af2b0f45e950"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:13.341594Z","signature_b64":"mwiU8cVkktvja8cAeMCwFUh1Pqf7k+fYf/uOCaI2I4rh31nAYrBGpdYKcXO9Y/g+dZA0FTz4DlM5M7pjN0IVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2cbbbf69687b221e042136ef5ca050916fb54d827b8ac5d92c38a54e8c153ac","last_reissued_at":"2026-07-05T10:34:13.341063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:13.341063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ekaterina Radionova, Ivan Laptev, Jingyi Zhang, Kamila Zhumakhanova, Liang Ma, Mingfei Han, Xiaodan Liang, Xiaojun Chang","submitted_at":"2024-12-11T18:10:21Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) suffers from the limited diversity and scale of training data, primarily constrained by the manual curation of existing simulators. To address this, we introduce RoomTour3D, a video-instruction dataset derived from web-based room tour videos that capture real-world indoor spaces and human walking demonstrations. Unlike existing VLN datasets, RoomTour3D leverages the scale and diversity of online videos to generate open-ended human walking trajectories and open-world navigable instructions. To compensate for the lack of navigation data in online videos, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08591","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/2412.08591/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":"2412.08591","created_at":"2026-07-05T10:34:13.341117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08591v2","created_at":"2026-07-05T10:34:13.341117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08591","created_at":"2026-07-05T10:34:13.341117+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LF3X5UWQ6ZC","created_at":"2026-07-05T10:34:13.341117+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LF3X5UWQ6ZCDYCC","created_at":"2026-07-05T10:34:13.341117+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LF3X5UW","created_at":"2026-07-05T10:34:13.341117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19600","citing_title":"FlyMirage: A Fully Automated Generation Pipeline for Diverse and Scalable UAV Flight Data via Generative World Model","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE","json":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE.json","graph_json":"https://pith.science/api/pith-number/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/graph.json","events_json":"https://pith.science/api/pith-number/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/events.json","paper":"https://pith.science/paper/2LF3X5UW"},"agent_actions":{"view_html":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE","download_json":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE.json","view_paper":"https://pith.science/paper/2LF3X5UW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08591&json=true","fetch_graph":"https://pith.science/api/pith-number/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/graph.json","fetch_events":"https://pith.science/api/pith-number/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/action/storage_attestation","attest_author":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/action/author_attestation","sign_citation":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/action/citation_signature","submit_replication":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/action/replication_record"}},"created_at":"2026-07-05T10:34:13.341117+00:00","updated_at":"2026-07-05T10:34:13.341117+00:00"}