{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EZMAV2T7UVQN4WQZYRC2Y4RFTX","short_pith_number":"pith:EZMAV2T7","schema_version":"1.0","canonical_sha256":"26580aea7fa560de5a19c445ac72259def090474d9e18ddca38efeb0e6638455","source":{"kind":"arxiv","id":"2104.14544","version":1},"attestation_state":"computed","paper":{"title":"AutoFlow: Learning a Better Training Set for Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Liu, Charles Herrmann, Daniel Vlasic, Deqing Sun, Huiwen Chang, Michael Krainin, Ramin Zabih, Varun Jampani, William T. Freeman","submitted_at":"2021-04-29T17:55:23Z","abstract_excerpt":"Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to render training data for optical flow that optimizes the performance of a model on a target dataset. AutoFlow takes a layered approach to render synthetic data, where the motion, shape, and appearance of each layer are controlled by learnable hyperparameters. Experimental results show that AutoFlow achieves state-of-the-art accuracy in pre-training both PWC-"},"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":"2104.14544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-29T17:55:23Z","cross_cats_sorted":[],"title_canon_sha256":"d3b5343debedb00095842412ca50ed258f90a74aa9009e3ac7cb782c5eb6c95d","abstract_canon_sha256":"85df95adf37b700b46cff3df459f1212264e24ae27f918cc0ff8c5f2c16acb92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:17.698830Z","signature_b64":"wxZxnA4JlQSBOadp3R3zV4sOLTj3Dslqie4JqxFdYu6pwJjOIv5nZmAd88YO7pj4Y/kw2tzXAq6QvlaCEXf2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26580aea7fa560de5a19c445ac72259def090474d9e18ddca38efeb0e6638455","last_reissued_at":"2026-07-05T02:36:17.698423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:17.698423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoFlow: Learning a Better Training Set for Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Liu, Charles Herrmann, Daniel Vlasic, Deqing Sun, Huiwen Chang, Michael Krainin, Ramin Zabih, Varun Jampani, William T. Freeman","submitted_at":"2021-04-29T17:55:23Z","abstract_excerpt":"Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to render training data for optical flow that optimizes the performance of a model on a target dataset. AutoFlow takes a layered approach to render synthetic data, where the motion, shape, and appearance of each layer are controlled by learnable hyperparameters. Experimental results show that AutoFlow achieves state-of-the-art accuracy in pre-training both PWC-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14544","kind":"arxiv","version":1},"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/2104.14544/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":"2104.14544","created_at":"2026-07-05T02:36:17.698478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.14544v1","created_at":"2026-07-05T02:36:17.698478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14544","created_at":"2026-07-05T02:36:17.698478+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZMAV2T7UVQN","created_at":"2026-07-05T02:36:17.698478+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZMAV2T7UVQN4WQZ","created_at":"2026-07-05T02:36:17.698478+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZMAV2T7","created_at":"2026-07-05T02:36:17.698478+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/EZMAV2T7UVQN4WQZYRC2Y4RFTX","json":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX.json","graph_json":"https://pith.science/api/pith-number/EZMAV2T7UVQN4WQZYRC2Y4RFTX/graph.json","events_json":"https://pith.science/api/pith-number/EZMAV2T7UVQN4WQZYRC2Y4RFTX/events.json","paper":"https://pith.science/paper/EZMAV2T7"},"agent_actions":{"view_html":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX","download_json":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX.json","view_paper":"https://pith.science/paper/EZMAV2T7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.14544&json=true","fetch_graph":"https://pith.science/api/pith-number/EZMAV2T7UVQN4WQZYRC2Y4RFTX/graph.json","fetch_events":"https://pith.science/api/pith-number/EZMAV2T7UVQN4WQZYRC2Y4RFTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX/action/storage_attestation","attest_author":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX/action/author_attestation","sign_citation":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX/action/citation_signature","submit_replication":"https://pith.science/pith/EZMAV2T7UVQN4WQZYRC2Y4RFTX/action/replication_record"}},"created_at":"2026-07-05T02:36:17.698478+00:00","updated_at":"2026-07-05T02:36:17.698478+00:00"}