{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AHTZHRWDVIP4G7SX2NFI3RPSQF","short_pith_number":"pith:AHTZHRWD","schema_version":"1.0","canonical_sha256":"01e793c6c3aa1fc37e57d34a8dc5f28142a1e1509c6b84987ef4c5741a152447","source":{"kind":"arxiv","id":"2410.13002","version":2},"attestation_state":"computed","paper":{"title":"Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alaa Maalouf, Alex Quach, Daniela Rus, Makram Chahine, Tsun-Hsuan Wang","submitted_at":"2024-10-16T19:59:31Z","abstract_excerpt":"End-to-end learning directly maps sensory inputs to actions, creating highly integrated and efficient policies for complex robotics tasks. However, such models often struggle to generalize beyond their training scenarios, limiting adaptability to new environments, tasks, and concepts. In this work, we investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies under unseen text instructions and visual distribution shifts. Our findings are synthesized in Flex (Fly lexically), a framework that uses"},"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":"2410.13002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-16T19:59:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4cce6108f906d3d94981b2eef9cb03d385accf1e74771be93ed96853426cac2f","abstract_canon_sha256":"80f50a459fa350768beb56aa9a05a06774ea8c7bd87b758b09a210f6d512de2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:52.683486Z","signature_b64":"twT44gsy3S6cqGs4787BiQa33nvMIOHPCRy1SydzOJPWsCS7y87kf++8CXYMbMfhxgacT/2nKff459DM3OASBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e793c6c3aa1fc37e57d34a8dc5f28142a1e1509c6b84987ef4c5741a152447","last_reissued_at":"2026-07-05T11:03:52.682981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:52.682981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alaa Maalouf, Alex Quach, Daniela Rus, Makram Chahine, Tsun-Hsuan Wang","submitted_at":"2024-10-16T19:59:31Z","abstract_excerpt":"End-to-end learning directly maps sensory inputs to actions, creating highly integrated and efficient policies for complex robotics tasks. However, such models often struggle to generalize beyond their training scenarios, limiting adaptability to new environments, tasks, and concepts. In this work, we investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies under unseen text instructions and visual distribution shifts. Our findings are synthesized in Flex (Fly lexically), a framework that uses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13002","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/2410.13002/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":"2410.13002","created_at":"2026-07-05T11:03:52.683039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13002v2","created_at":"2026-07-05T11:03:52.683039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13002","created_at":"2026-07-05T11:03:52.683039+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHTZHRWDVIP4","created_at":"2026-07-05T11:03:52.683039+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHTZHRWDVIP4G7SX","created_at":"2026-07-05T11:03:52.683039+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHTZHRWD","created_at":"2026-07-05T11:03:52.683039+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/AHTZHRWDVIP4G7SX2NFI3RPSQF","json":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF.json","graph_json":"https://pith.science/api/pith-number/AHTZHRWDVIP4G7SX2NFI3RPSQF/graph.json","events_json":"https://pith.science/api/pith-number/AHTZHRWDVIP4G7SX2NFI3RPSQF/events.json","paper":"https://pith.science/paper/AHTZHRWD"},"agent_actions":{"view_html":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF","download_json":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF.json","view_paper":"https://pith.science/paper/AHTZHRWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13002&json=true","fetch_graph":"https://pith.science/api/pith-number/AHTZHRWDVIP4G7SX2NFI3RPSQF/graph.json","fetch_events":"https://pith.science/api/pith-number/AHTZHRWDVIP4G7SX2NFI3RPSQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF/action/storage_attestation","attest_author":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF/action/author_attestation","sign_citation":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF/action/citation_signature","submit_replication":"https://pith.science/pith/AHTZHRWDVIP4G7SX2NFI3RPSQF/action/replication_record"}},"created_at":"2026-07-05T11:03:52.683039+00:00","updated_at":"2026-07-05T11:03:52.683039+00:00"}