{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6VKZ7I3QQQ4BDQ3OI56P23XQ7G","short_pith_number":"pith:6VKZ7I3Q","schema_version":"1.0","canonical_sha256":"f5559fa370843811c36e477cfd6ef0f9bec33cd5c4c48e8c4f05f1cb17fdd8cb","source":{"kind":"arxiv","id":"2606.18426","version":1},"attestation_state":"computed","paper":{"title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dinesh Manocha, Gershom Seneviratne, Jianyu An, Vaibhav Shende, Yohan Abeysinghe","submitted_at":"2026-06-16T19:21:14Z","abstract_excerpt":"We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocentric navigation videos. Internet-scale egocentric videos provide a scalable source of navigation-relevant visual observations, capturing cluttered scenes, close-range obstacles, and natural human motion through real-world spaces. However, these videos are not directly usable for policy learning because they do not provide obstacle-aware trajectories conditioned on explicit navigation goals in the robot's coordinate frame. VEGA addresses this gap by reconstructing local scene geometry "},"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":"2606.18426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-16T19:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"80b540ae0241179a3d3a2dcdc78e9190bd4f0f71b3f7cdcb7bd9f3ec7641a061","abstract_canon_sha256":"f63422a0c0500cbcf33980d561d34e2ec6c7f274cb1ae15209d1f57cc157268a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:00.957512Z","signature_b64":"P8E4wM3oAxJsRWYT0FJ2okI7wLshvS2eUdXLUkHlUHjpYQbioH5x0jaj2D/nenfXiCHBYSq6978N8/LTr5G1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5559fa370843811c36e477cfd6ef0f9bec33cd5c4c48e8c4f05f1cb17fdd8cb","last_reissued_at":"2026-06-19T16:11:00.957152Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:00.957152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dinesh Manocha, Gershom Seneviratne, Jianyu An, Vaibhav Shende, Yohan Abeysinghe","submitted_at":"2026-06-16T19:21:14Z","abstract_excerpt":"We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocentric navigation videos. Internet-scale egocentric videos provide a scalable source of navigation-relevant visual observations, capturing cluttered scenes, close-range obstacles, and natural human motion through real-world spaces. However, these videos are not directly usable for policy learning because they do not provide obstacle-aware trajectories conditioned on explicit navigation goals in the robot's coordinate frame. VEGA addresses this gap by reconstructing local scene geometry "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18426","kind":"arxiv","version":1},"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/2606.18426/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":"2606.18426","created_at":"2026-06-19T16:11:00.957213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18426v1","created_at":"2026-06-19T16:11:00.957213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18426","created_at":"2026-06-19T16:11:00.957213+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VKZ7I3QQQ4B","created_at":"2026-06-19T16:11:00.957213+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VKZ7I3QQQ4BDQ3O","created_at":"2026-06-19T16:11:00.957213+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VKZ7I3Q","created_at":"2026-06-19T16:11:00.957213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G","json":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G.json","graph_json":"https://pith.science/api/pith-number/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/graph.json","events_json":"https://pith.science/api/pith-number/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/events.json","paper":"https://pith.science/paper/6VKZ7I3Q"},"agent_actions":{"view_html":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G","download_json":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G.json","view_paper":"https://pith.science/paper/6VKZ7I3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18426&json=true","fetch_graph":"https://pith.science/api/pith-number/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/graph.json","fetch_events":"https://pith.science/api/pith-number/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/action/storage_attestation","attest_author":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/action/author_attestation","sign_citation":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/action/citation_signature","submit_replication":"https://pith.science/pith/6VKZ7I3QQQ4BDQ3OI56P23XQ7G/action/replication_record"}},"created_at":"2026-06-19T16:11:00.957213+00:00","updated_at":"2026-06-19T16:11:00.957213+00:00"}