{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HEYRHD6775FNNGLZ5264LIAEUH","short_pith_number":"pith:HEYRHD67","schema_version":"1.0","canonical_sha256":"3931138fdfff4ad69979eebdc5a004a1f1f75b2a29beebddf0dbdb843d40ccfd","source":{"kind":"arxiv","id":"2506.03834","version":4},"attestation_state":"computed","paper":{"title":"CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Changjoo Nam, Joonkyung Kim, Joonyeol Sim, Katia Sycara, Woojun Kim","submitted_at":"2025-06-04T11:02:15Z","abstract_excerpt":"We propose CARE (Collision Avoidance via Repulsive Estimation) to improve the robustness of learning-based visual navigation methods. Recently, visual navigation models, particularly foundation models, have demonstrated promising performance by generating viable trajectories using only RGB images. However, these policies can generalize poorly to environments containing out-of-distribution (OOD) scenes characterized by unseen objects or different camera setups (e.g., variations in field of view, camera pose, or focal length). Without fine-tuning, such models could produce trajectories that lead"},"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":"2506.03834","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-04T11:02:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a837f9aaa246a3b8f74d9d0d1831cdd16f0727be591d71978766108b6d77e8a3","abstract_canon_sha256":"ca8332dbc711aa63e8d91d13be5e79d31afb46444894a175fb107f77d683fee5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:37.498839Z","signature_b64":"lsXPv21LC7k/Q9wnqm+1sV+DA4KZ9qAHe759RKI26t2LwkP38LW91JGa2Ddp/eyuBd0bhmFZ1kd93oj9ulZHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3931138fdfff4ad69979eebdc5a004a1f1f75b2a29beebddf0dbdb843d40ccfd","last_reissued_at":"2026-07-05T11:50:37.498374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:37.498374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARE: Enhancing Safety of Visual Navigation through Collision Avoidance via Repulsive Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Changjoo Nam, Joonkyung Kim, Joonyeol Sim, Katia Sycara, Woojun Kim","submitted_at":"2025-06-04T11:02:15Z","abstract_excerpt":"We propose CARE (Collision Avoidance via Repulsive Estimation) to improve the robustness of learning-based visual navigation methods. Recently, visual navigation models, particularly foundation models, have demonstrated promising performance by generating viable trajectories using only RGB images. However, these policies can generalize poorly to environments containing out-of-distribution (OOD) scenes characterized by unseen objects or different camera setups (e.g., variations in field of view, camera pose, or focal length). Without fine-tuning, such models could produce trajectories that lead"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03834","kind":"arxiv","version":4},"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/2506.03834/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":"2506.03834","created_at":"2026-07-05T11:50:37.498434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03834v4","created_at":"2026-07-05T11:50:37.498434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03834","created_at":"2026-07-05T11:50:37.498434+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEYRHD6775FN","created_at":"2026-07-05T11:50:37.498434+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEYRHD6775FNNGLZ","created_at":"2026-07-05T11:50:37.498434+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEYRHD67","created_at":"2026-07-05T11:50:37.498434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16993","citing_title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH","json":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH.json","graph_json":"https://pith.science/api/pith-number/HEYRHD6775FNNGLZ5264LIAEUH/graph.json","events_json":"https://pith.science/api/pith-number/HEYRHD6775FNNGLZ5264LIAEUH/events.json","paper":"https://pith.science/paper/HEYRHD67"},"agent_actions":{"view_html":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH","download_json":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH.json","view_paper":"https://pith.science/paper/HEYRHD67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03834&json=true","fetch_graph":"https://pith.science/api/pith-number/HEYRHD6775FNNGLZ5264LIAEUH/graph.json","fetch_events":"https://pith.science/api/pith-number/HEYRHD6775FNNGLZ5264LIAEUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH/action/storage_attestation","attest_author":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH/action/author_attestation","sign_citation":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH/action/citation_signature","submit_replication":"https://pith.science/pith/HEYRHD6775FNNGLZ5264LIAEUH/action/replication_record"}},"created_at":"2026-07-05T11:50:37.498434+00:00","updated_at":"2026-07-05T11:50:37.498434+00:00"}