{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z75F4ZURKII3XS7Q5PVYEEA4J6","short_pith_number":"pith:Z75F4ZUR","schema_version":"1.0","canonical_sha256":"cffa5e66915211bbcbf0ebeb82101c4f903d6f26d218b91bfb05326899e848d7","source":{"kind":"arxiv","id":"2604.09411","version":2},"attestation_state":"computed","paper":{"title":"SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Models trained only on synthetic LiDAR scene flow data match or beat real supervised baselines on multiple benchmarks.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhan Jiang, Patric Jensfelt, Qingwen Zhang, Xiaomeng Zhu","submitted_at":"2026-04-10T15:25:33Z","abstract_excerpt":"Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers a path forward, empirical evidence suggests that scaling unlabeled data fails to close the performance gap due to noisy proxy signals. In this paper, we propose learning robust real-world motion priors entirely from scalable simulation. We introduce SynFlow, a data generation pipeline for large-scale synthetic LiDAR scene flow. Unlike prior works that prior"},"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":"2604.09411","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-10T15:25:33Z","cross_cats_sorted":[],"title_canon_sha256":"4fcca4be4135038bbfd733efc6b29b0f452be5467862f2fbfbaa011ae98e121b","abstract_canon_sha256":"410d1cbdc6d7555edb70a37b6b2e004a412f9a472255dc7008635df5475a9cac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:25:37.084941Z","signature_b64":"rZcceXluFu35y9l+oSnZekACdqnNQbjBBVQzh6mMPUXlpOBii6/USrH0tPL+N3etEz+DhGbSLKqtDSjx44BeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cffa5e66915211bbcbf0ebeb82101c4f903d6f26d218b91bfb05326899e848d7","last_reissued_at":"2026-07-29T01:25:37.084031Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:25:37.084031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Models trained only on synthetic LiDAR scene flow data match or beat real supervised baselines on multiple benchmarks.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhan Jiang, Patric Jensfelt, Qingwen Zhang, Xiaomeng Zhu","submitted_at":"2026-04-10T15:25:33Z","abstract_excerpt":"Reliable 3D dynamic perception requires models that can anticipate motion beyond predefined categories, yet progress is hindered by the scarcity of dense, high-quality motion annotations. While self-supervision on unlabeled real data offers a path forward, empirical evidence suggests that scaling unlabeled data fails to close the performance gap due to noisy proxy signals. In this paper, we propose learning robust real-world motion priors entirely from scalable simulation. We introduce SynFlow, a data generation pipeline for large-scale synthetic LiDAR scene flow. Unlike prior works that prior"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Models trained exclusively on SynFlow-4k generalize across multiple real-world benchmarks in a zero-shot regime, rivaling in-domain supervised baselines on nuScenes and outperforming state-of-the-art methods on TruckScenes by 31.8%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthetic motion patterns generated by the pipeline are sufficiently representative of real-world kinematic distributions that models can learn domain-invariant priors without explicit domain adaptation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SynFlow creates a 34-times larger synthetic LiDAR scene flow dataset that lets models trained only on simulation match or beat supervised real-data baselines on multiple benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Models trained only on synthetic LiDAR scene flow data match or beat real supervised baselines on multiple benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"67f048427326bc8d26176c07c9b29485f617148dcb622e080a68f20edba66541"},"source":{"id":"2604.09411","kind":"arxiv","version":2},"verdict":{"id":"89315fb4-017f-41e9-b28f-9a91310a29e5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:41:12.457339Z","strongest_claim":"Models trained exclusively on SynFlow-4k generalize across multiple real-world benchmarks in a zero-shot regime, rivaling in-domain supervised baselines on nuScenes and outperforming state-of-the-art methods on TruckScenes by 31.8%.","one_line_summary":"SynFlow creates a 34-times larger synthetic LiDAR scene flow dataset that lets models trained only on simulation match or beat supervised real-data baselines on multiple benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthetic motion patterns generated by the pipeline are sufficiently representative of real-world kinematic distributions that models can learn domain-invariant priors without explicit domain adaptation.","pith_extraction_headline":"Models trained only on synthetic LiDAR scene flow data match or beat real supervised baselines on multiple benchmarks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09411/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":"2604.09411","created_at":"2026-07-29T01:25:37.084460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09411v2","created_at":"2026-07-29T01:25:37.084460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09411","created_at":"2026-07-29T01:25:37.084460+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z75F4ZURKII3","created_at":"2026-07-29T01:25:37.084460+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z75F4ZURKII3XS7Q","created_at":"2026-07-29T01:25:37.084460+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z75F4ZUR","created_at":"2026-07-29T01:25:37.084460+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/Z75F4ZURKII3XS7Q5PVYEEA4J6","json":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6.json","graph_json":"https://pith.science/api/pith-number/Z75F4ZURKII3XS7Q5PVYEEA4J6/graph.json","events_json":"https://pith.science/api/pith-number/Z75F4ZURKII3XS7Q5PVYEEA4J6/events.json","paper":"https://pith.science/paper/Z75F4ZUR"},"agent_actions":{"view_html":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6","download_json":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6.json","view_paper":"https://pith.science/paper/Z75F4ZUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09411&json=true","fetch_graph":"https://pith.science/api/pith-number/Z75F4ZURKII3XS7Q5PVYEEA4J6/graph.json","fetch_events":"https://pith.science/api/pith-number/Z75F4ZURKII3XS7Q5PVYEEA4J6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6/action/storage_attestation","attest_author":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6/action/author_attestation","sign_citation":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6/action/citation_signature","submit_replication":"https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6/action/replication_record"}},"created_at":"2026-07-29T01:25:37.084460+00:00","updated_at":"2026-07-29T01:25:37.084460+00:00"}