{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LDXO7ENT5EODD35NIWXQDABGTS","short_pith_number":"pith:LDXO7ENT","schema_version":"1.0","canonical_sha256":"58eeef91b3e91c31efad45af0180269c8e51b718e44a31872181a22e2bdd2f38","source":{"kind":"arxiv","id":"2003.12039","version":3},"attestation_state":"computed","paper":{"title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Deng, Zachary Teed","submitted_at":"2020-03-26T17:12:42Z","abstract_excerpt":"We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance. On KITTI, RAFT achieves an F1-all error of 5.10%, a 16% error reduction from the best published result (6.10%). On Sintel (final pass), RAFT obtains an end-point-error of 2.855 pixels, a 30% error reduction from the best published resu"},"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":"2003.12039","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-26T17:12:42Z","cross_cats_sorted":[],"title_canon_sha256":"a384fffa07104f423207f5b13670675dddb92cc58fd1cc65503dbfe7c5792415","abstract_canon_sha256":"be3ba841f4f26019575540be25ea112206d48d1e478a9f1f54582428b34b94fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:57.375596Z","signature_b64":"e2SaiPjUQgPFf1+wtYRPhgZLzYpUHBKWRHBEVdWHGyENqYPGFaXtFFEpvlmJ4/SsYT6y6r9jCoQKwkJAICQoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58eeef91b3e91c31efad45af0180269c8e51b718e44a31872181a22e2bdd2f38","last_reissued_at":"2026-07-05T01:29:57.375080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:57.375080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Deng, Zachary Teed","submitted_at":"2020-03-26T17:12:42Z","abstract_excerpt":"We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance. On KITTI, RAFT achieves an F1-all error of 5.10%, a 16% error reduction from the best published result (6.10%). On Sintel (final pass), RAFT obtains an end-point-error of 2.855 pixels, a 30% error reduction from the best published resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12039","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/2003.12039/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":"2003.12039","created_at":"2026-07-05T01:29:57.375140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.12039v3","created_at":"2026-07-05T01:29:57.375140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12039","created_at":"2026-07-05T01:29:57.375140+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDXO7ENT5EOD","created_at":"2026-07-05T01:29:57.375140+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDXO7ENT5EODD35N","created_at":"2026-07-05T01:29:57.375140+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDXO7ENT","created_at":"2026-07-05T01:29:57.375140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31672","citing_title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09162","citing_title":"Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31672","citing_title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27817","citing_title":"Turning Video Models into Generalist Robot Policies","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17816","citing_title":"Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13294","citing_title":"VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17427","citing_title":"AV1 Motion Vector Fidelity and Application for Efficient Optical Flow","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01383","citing_title":"CaRLi-V: Camera-RADAR-LiDAR Point-Wise 3D Velocity Estimation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":216,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22851","citing_title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS","json":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS.json","graph_json":"https://pith.science/api/pith-number/LDXO7ENT5EODD35NIWXQDABGTS/graph.json","events_json":"https://pith.science/api/pith-number/LDXO7ENT5EODD35NIWXQDABGTS/events.json","paper":"https://pith.science/paper/LDXO7ENT"},"agent_actions":{"view_html":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS","download_json":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS.json","view_paper":"https://pith.science/paper/LDXO7ENT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.12039&json=true","fetch_graph":"https://pith.science/api/pith-number/LDXO7ENT5EODD35NIWXQDABGTS/graph.json","fetch_events":"https://pith.science/api/pith-number/LDXO7ENT5EODD35NIWXQDABGTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS/action/storage_attestation","attest_author":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS/action/author_attestation","sign_citation":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS/action/citation_signature","submit_replication":"https://pith.science/pith/LDXO7ENT5EODD35NIWXQDABGTS/action/replication_record"}},"created_at":"2026-07-05T01:29:57.375140+00:00","updated_at":"2026-07-05T01:29:57.375140+00:00"}