{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Y5FBDEIR7U2JXUQOYPUPJF4DLO","short_pith_number":"pith:Y5FBDEIR","schema_version":"1.0","canonical_sha256":"c74a119111fd349bd20ec3e8f497835bad677a68cfa67a1ddfe49d24e4014d98","source":{"kind":"arxiv","id":"1608.05842","version":1},"attestation_state":"computed","paper":{"title":"Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam W. Harley, Jason J. Yu, Konstantinos G. Derpanis","submitted_at":"2016-08-20T15:25:31Z","abstract_excerpt":"Recently, convolutional networks (convnets) have proven useful for predicting optical flow. Much of this success is predicated on the availability of large datasets that require expensive and involved data acquisition and laborious la- beling. To bypass these challenges, we propose an unsuper- vised approach (i.e., without leveraging groundtruth flow) to train a convnet end-to-end for predicting optical flow be- tween two images. We use a loss function that combines a data term that measures photometric constancy over time with a spatial term that models the expected variation of flow across t"},"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":"1608.05842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-20T15:25:31Z","cross_cats_sorted":[],"title_canon_sha256":"d17deb6f209dadf1120b10c2dcb5b4b25661033f39999904c07d4c52e235badc","abstract_canon_sha256":"f8acd8120bf55aa1942e4a4a70f5f5c4ab8961a1cdec90ddfc0dde4c296cd723"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:23.032954Z","signature_b64":"/LIIU5oSvUvBhmh4n/BBpb1UUcuZYOEnpzXFxIXGzDsPsnewngtqYQ99EdR5Gxx/9QXBSofs91YvUKcpMo8uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c74a119111fd349bd20ec3e8f497835bad677a68cfa67a1ddfe49d24e4014d98","last_reissued_at":"2026-05-18T01:08:23.032400Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:23.032400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam W. Harley, Jason J. Yu, Konstantinos G. Derpanis","submitted_at":"2016-08-20T15:25:31Z","abstract_excerpt":"Recently, convolutional networks (convnets) have proven useful for predicting optical flow. Much of this success is predicated on the availability of large datasets that require expensive and involved data acquisition and laborious la- beling. To bypass these challenges, we propose an unsuper- vised approach (i.e., without leveraging groundtruth flow) to train a convnet end-to-end for predicting optical flow be- tween two images. We use a loss function that combines a data term that measures photometric constancy over time with a spatial term that models the expected variation of flow across t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05842","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":""},"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":"1608.05842","created_at":"2026-05-18T01:08:23.032484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.05842v1","created_at":"2026-05-18T01:08:23.032484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05842","created_at":"2026-05-18T01:08:23.032484+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5FBDEIR7U2J","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5FBDEIR7U2JXUQO","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5FBDEIR","created_at":"2026-05-18T12:30:53.716459+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/Y5FBDEIR7U2JXUQOYPUPJF4DLO","json":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO.json","graph_json":"https://pith.science/api/pith-number/Y5FBDEIR7U2JXUQOYPUPJF4DLO/graph.json","events_json":"https://pith.science/api/pith-number/Y5FBDEIR7U2JXUQOYPUPJF4DLO/events.json","paper":"https://pith.science/paper/Y5FBDEIR"},"agent_actions":{"view_html":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO","download_json":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO.json","view_paper":"https://pith.science/paper/Y5FBDEIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.05842&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5FBDEIR7U2JXUQOYPUPJF4DLO/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5FBDEIR7U2JXUQOYPUPJF4DLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO/action/storage_attestation","attest_author":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO/action/author_attestation","sign_citation":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO/action/citation_signature","submit_replication":"https://pith.science/pith/Y5FBDEIR7U2JXUQOYPUPJF4DLO/action/replication_record"}},"created_at":"2026-05-18T01:08:23.032484+00:00","updated_at":"2026-05-18T01:08:23.032484+00:00"}