{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HIH2XWUJB4MK2Y4NTSC7Y7PUDP","short_pith_number":"pith:HIH2XWUJ","schema_version":"1.0","canonical_sha256":"3a0fabda890f18ad638d9c85fc7df41bdcb118aaa57a2a88e87d76af8996dae0","source":{"kind":"arxiv","id":"2503.03921","version":2},"attestation_state":"computed","paper":{"title":"CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Amy Zhang, Arthur Zhang, Harshit Sikchi, Joydeep Biswas","submitted_at":"2025-03-05T21:42:46Z","abstract_excerpt":"We introduce CREStE, a scalable learning-based mapless navigation framework to address the open-world generalization and robustness challenges of outdoor urban navigation. Key to achieving this is learning perceptual representations that generalize to open-set factors (e.g. novel semantic classes, terrains, dynamic entities) and inferring expert-aligned navigation costs from limited demonstrations. CREStE addresses both these issues, introducing 1) a visual foundation model (VFM) distillation objective for learning open-set structured bird's-eye-view perceptual representations, and 2) counterf"},"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":"2503.03921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-05T21:42:46Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"fda98878bffc3d219968d3d1ed2a3b22342694d602fb17b562eba313daca5147","abstract_canon_sha256":"7e799446ef9571e47dee1c56ebf2be385126ce0b962015df92babeab42b96557"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:24.788838Z","signature_b64":"HzIK8WxhGIYF3lLE4e3IAHEHcFfSkKfb4f3wTwr1/cVvOLh742/u04d4pgbmwfQUCYbGkTkB+sxqqVyoIatLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a0fabda890f18ad638d9c85fc7df41bdcb118aaa57a2a88e87d76af8996dae0","last_reissued_at":"2026-07-05T11:27:24.788330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:24.788330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Amy Zhang, Arthur Zhang, Harshit Sikchi, Joydeep Biswas","submitted_at":"2025-03-05T21:42:46Z","abstract_excerpt":"We introduce CREStE, a scalable learning-based mapless navigation framework to address the open-world generalization and robustness challenges of outdoor urban navigation. Key to achieving this is learning perceptual representations that generalize to open-set factors (e.g. novel semantic classes, terrains, dynamic entities) and inferring expert-aligned navigation costs from limited demonstrations. CREStE addresses both these issues, introducing 1) a visual foundation model (VFM) distillation objective for learning open-set structured bird's-eye-view perceptual representations, and 2) counterf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03921","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/2503.03921/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":"2503.03921","created_at":"2026-07-05T11:27:24.788390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03921v2","created_at":"2026-07-05T11:27:24.788390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03921","created_at":"2026-07-05T11:27:24.788390+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIH2XWUJB4MK","created_at":"2026-07-05T11:27:24.788390+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIH2XWUJB4MK2Y4N","created_at":"2026-07-05T11:27:24.788390+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIH2XWUJ","created_at":"2026-07-05T11:27:24.788390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18426","citing_title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03096","citing_title":"An Open-Source LiDAR and Monocular Off-Road Autonomous Navigation Stack","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP","json":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP.json","graph_json":"https://pith.science/api/pith-number/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/graph.json","events_json":"https://pith.science/api/pith-number/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/events.json","paper":"https://pith.science/paper/HIH2XWUJ"},"agent_actions":{"view_html":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP","download_json":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP.json","view_paper":"https://pith.science/paper/HIH2XWUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03921&json=true","fetch_graph":"https://pith.science/api/pith-number/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/graph.json","fetch_events":"https://pith.science/api/pith-number/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/action/storage_attestation","attest_author":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/action/author_attestation","sign_citation":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/action/citation_signature","submit_replication":"https://pith.science/pith/HIH2XWUJB4MK2Y4NTSC7Y7PUDP/action/replication_record"}},"created_at":"2026-07-05T11:27:24.788390+00:00","updated_at":"2026-07-05T11:27:24.788390+00:00"}