{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AO45UUZGPBS43RWUOQKISKZB4S","short_pith_number":"pith:AO45UUZG","schema_version":"1.0","canonical_sha256":"03b9da53267865cdc6d47414892b21e48cece4234a72083e5377cb7cc9c47b7e","source":{"kind":"arxiv","id":"2511.18254","version":3},"attestation_state":"computed","paper":{"title":"UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deva Ramanan, Eric Eaton, Ishan Khatri, Kyle Vedder, Neehar Peri, Qingwen Zhang, Siyi Li","submitted_at":"2025-11-23T02:51:42Z","abstract_excerpt":"LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a single sensor. In this paper, we aim to learn general motion priors that transfer to diverse and unseen LiDAR sensors. However, prior work in LiDAR semantic segmentation and 3D object detection demonstrate that naively training on multiple datasets yields worse performance than single dataset models. Interestingly, we find that this conventional wisdom does"},"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":"2511.18254","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-23T02:51:42Z","cross_cats_sorted":[],"title_canon_sha256":"e8e0e8a37c2d5014338ef3337962c1f17fbfa0003a2ea8374a8732e366ff5884","abstract_canon_sha256":"31d26e515c77b28cf900e45a9a64a77566922139e65cb634eeae9474e6edd981"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:16.140037Z","signature_b64":"5qzS7cog7SlUyd3ymRjZJWhghzR0F7NmCUzbQyuteUBivqyj1I9fcoC/dS1KFl/kBxOHm10stoY49EMW1dzZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03b9da53267865cdc6d47414892b21e48cece4234a72083e5377cb7cc9c47b7e","last_reissued_at":"2026-06-26T01:15:16.139522Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:16.139522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deva Ramanan, Eric Eaton, Ishan Khatri, Kyle Vedder, Neehar Peri, Qingwen Zhang, Siyi Li","submitted_at":"2025-11-23T02:51:42Z","abstract_excerpt":"LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a single sensor. In this paper, we aim to learn general motion priors that transfer to diverse and unseen LiDAR sensors. However, prior work in LiDAR semantic segmentation and 3D object detection demonstrate that naively training on multiple datasets yields worse performance than single dataset models. Interestingly, we find that this conventional wisdom does"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18254","kind":"arxiv","version":3},"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/2511.18254/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":"2511.18254","created_at":"2026-06-26T01:15:16.139589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.18254v3","created_at":"2026-06-26T01:15:16.139589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18254","created_at":"2026-06-26T01:15:16.139589+00:00"},{"alias_kind":"pith_short_12","alias_value":"AO45UUZGPBS4","created_at":"2026-06-26T01:15:16.139589+00:00"},{"alias_kind":"pith_short_16","alias_value":"AO45UUZGPBS43RWU","created_at":"2026-06-26T01:15:16.139589+00:00"},{"alias_kind":"pith_short_8","alias_value":"AO45UUZG","created_at":"2026-06-26T01:15:16.139589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2512.03210","citing_title":"Flux4D: Flow-based Unsupervised 4D Reconstruction","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09411","citing_title":"SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S","json":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S.json","graph_json":"https://pith.science/api/pith-number/AO45UUZGPBS43RWUOQKISKZB4S/graph.json","events_json":"https://pith.science/api/pith-number/AO45UUZGPBS43RWUOQKISKZB4S/events.json","paper":"https://pith.science/paper/AO45UUZG"},"agent_actions":{"view_html":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S","download_json":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S.json","view_paper":"https://pith.science/paper/AO45UUZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.18254&json=true","fetch_graph":"https://pith.science/api/pith-number/AO45UUZGPBS43RWUOQKISKZB4S/graph.json","fetch_events":"https://pith.science/api/pith-number/AO45UUZGPBS43RWUOQKISKZB4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S/action/storage_attestation","attest_author":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S/action/author_attestation","sign_citation":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S/action/citation_signature","submit_replication":"https://pith.science/pith/AO45UUZGPBS43RWUOQKISKZB4S/action/replication_record"}},"created_at":"2026-06-26T01:15:16.139589+00:00","updated_at":"2026-06-26T01:15:16.139589+00:00"}