{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:UNHYMI6LN43CTR6C567VU2VSQA","short_pith_number":"pith:UNHYMI6L","canonical_record":{"source":{"id":"1612.03777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T16:45:08Z","cross_cats_sorted":[],"title_canon_sha256":"978b29e72809354ba640e3417dabb693979e1b4cafd96433db35220e42bb26cc","abstract_canon_sha256":"6a4b125e17f489a5cef98719f88546fa5c42258525ccbcbc81cd775931a7f936"},"schema_version":"1.0"},"canonical_sha256":"a34f8623cb6f3629c7c2efbf5a6ab280195c689124fffb585b7f6b51299f74dc","source":{"kind":"arxiv","id":"1612.03777","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.03777","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"1612.03777v2","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03777","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"UNHYMI6LN43C","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UNHYMI6LN43CTR6C","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UNHYMI6L","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:UNHYMI6LN43CTR6C567VU2VSQA","target":"record","payload":{"canonical_record":{"source":{"id":"1612.03777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T16:45:08Z","cross_cats_sorted":[],"title_canon_sha256":"978b29e72809354ba640e3417dabb693979e1b4cafd96433db35220e42bb26cc","abstract_canon_sha256":"6a4b125e17f489a5cef98719f88546fa5c42258525ccbcbc81cd775931a7f936"},"schema_version":"1.0"},"canonical_sha256":"a34f8623cb6f3629c7c2efbf5a6ab280195c689124fffb585b7f6b51299f74dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:51.450665Z","signature_b64":"9DaHE6HZG6OqSCXzUzX8TIeBaXWk2lIh0HtsraSSD/uuRErSgcbzMg7HSy3+DoiFbjN5yF8a4l6mWYry1QkXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a34f8623cb6f3629c7c2efbf5a6ab280195c689124fffb585b7f6b51299f74dc","last_reissued_at":"2026-05-18T00:46:51.449920Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:51.449920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.03777","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZiDgKspNWi+3YogWpvSsnD8DAkt+54XcyCLE4Vq/elUno0Wp1xTbiODTz2DMSePdf8GvLwodxKvgIenl6tMDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:47:25.389963Z"},"content_sha256":"ce9d92240efb3a53184449009197803abcec56db4495087292f45e2dea86b743","schema_version":"1.0","event_id":"sha256:ce9d92240efb3a53184449009197803abcec56db4495087292f45e2dea86b743"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:UNHYMI6LN43CTR6C567VU2VSQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mohammadreza Zolfaghari, Nima Sedaghat, Thomas Brox","submitted_at":"2016-12-12T16:45:08Z","abstract_excerpt":"CNN-based optical flow estimation has attracted attention recently, mainly due to its impressively high frame rates. These networks perform well on synthetic datasets, but they are still far behind the classical methods in real-world videos. This is because there is no ground truth optical flow for training these networks on real data. In this paper, we boost CNN-based optical flow estimation in real scenes with the help of the freely available self-supervised task of next-frame prediction. To this end, we train the network in a hybrid way, providing it with a mixture of synthetic and real vid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03777","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CZYsHnMY0dbnuuwreSxIdo+9v56qo07t+/PmpXdeNAKo7h3WRnn0LiasJAOtjPzIv6obl9gEpGCopNlmFcuYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:47:25.390553Z"},"content_sha256":"eff3714c8dc05a84fb915c4d8b8438b20a0d1f4781f78de8ce08c2814cc6bae6","schema_version":"1.0","event_id":"sha256:eff3714c8dc05a84fb915c4d8b8438b20a0d1f4781f78de8ce08c2814cc6bae6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNHYMI6LN43CTR6C567VU2VSQA/bundle.json","state_url":"https://pith.science/pith/UNHYMI6LN43CTR6C567VU2VSQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNHYMI6LN43CTR6C567VU2VSQA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T18:47:25Z","links":{"resolver":"https://pith.science/pith/UNHYMI6LN43CTR6C567VU2VSQA","bundle":"https://pith.science/pith/UNHYMI6LN43CTR6C567VU2VSQA/bundle.json","state":"https://pith.science/pith/UNHYMI6LN43CTR6C567VU2VSQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNHYMI6LN43CTR6C567VU2VSQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:UNHYMI6LN43CTR6C567VU2VSQA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6a4b125e17f489a5cef98719f88546fa5c42258525ccbcbc81cd775931a7f936","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T16:45:08Z","title_canon_sha256":"978b29e72809354ba640e3417dabb693979e1b4cafd96433db35220e42bb26cc"},"schema_version":"1.0","source":{"id":"1612.03777","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.03777","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"1612.03777v2","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.03777","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"UNHYMI6LN43C","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UNHYMI6LN43CTR6C","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UNHYMI6L","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:eff3714c8dc05a84fb915c4d8b8438b20a0d1f4781f78de8ce08c2814cc6bae6","target":"graph","created_at":"2026-05-18T00:46:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"CNN-based optical flow estimation has attracted attention recently, mainly due to its impressively high frame rates. These networks perform well on synthetic datasets, but they are still far behind the classical methods in real-world videos. This is because there is no ground truth optical flow for training these networks on real data. In this paper, we boost CNN-based optical flow estimation in real scenes with the help of the freely available self-supervised task of next-frame prediction. To this end, we train the network in a hybrid way, providing it with a mixture of synthetic and real vid","authors_text":"Mohammadreza Zolfaghari, Nima Sedaghat, Thomas Brox","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T16:45:08Z","title":"Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.03777","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ce9d92240efb3a53184449009197803abcec56db4495087292f45e2dea86b743","target":"record","created_at":"2026-05-18T00:46:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6a4b125e17f489a5cef98719f88546fa5c42258525ccbcbc81cd775931a7f936","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-12T16:45:08Z","title_canon_sha256":"978b29e72809354ba640e3417dabb693979e1b4cafd96433db35220e42bb26cc"},"schema_version":"1.0","source":{"id":"1612.03777","kind":"arxiv","version":2}},"canonical_sha256":"a34f8623cb6f3629c7c2efbf5a6ab280195c689124fffb585b7f6b51299f74dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a34f8623cb6f3629c7c2efbf5a6ab280195c689124fffb585b7f6b51299f74dc","first_computed_at":"2026-05-18T00:46:51.449920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:51.449920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9DaHE6HZG6OqSCXzUzX8TIeBaXWk2lIh0HtsraSSD/uuRErSgcbzMg7HSy3+DoiFbjN5yF8a4l6mWYry1QkXDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:51.450665Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.03777","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce9d92240efb3a53184449009197803abcec56db4495087292f45e2dea86b743","sha256:eff3714c8dc05a84fb915c4d8b8438b20a0d1f4781f78de8ce08c2814cc6bae6"],"state_sha256":"15d97e31e6e89f4dcba4b47e03bbca4889a88d8683404b19635c04051a22bb58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cdsi4SFN9wY/rqwCr4kE0e2IKDSRzlYf5bOIYFHuygEer8YvhGwaoFS4T/G1kzVxHXLDtiajua5FoU8JwlOXAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:47:25.395044Z","bundle_sha256":"6ee6ef692417ac156f74c66c08eb2b68df17cb3a57ae4d2ba407d285befabaa6"}}