{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:X5ZLUS6KI44NTVRJ2BMMLJK7RI","short_pith_number":"pith:X5ZLUS6K","canonical_record":{"source":{"id":"1806.00800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T14:38:17Z","cross_cats_sorted":[],"title_canon_sha256":"0b1568979c852d5392b1813daf5dc5fd9c810dbe4ead5e30c99984a60b4411ed","abstract_canon_sha256":"62b108bb5a5835ca837bdb47f2bc970178dd4efaebd8bcdd7c6fbf75b4b236af"},"schema_version":"1.0"},"canonical_sha256":"bf72ba4bca4738d9d629d058c5a55f8a198f4517c216031f12c3bb7bf0426d91","source":{"kind":"arxiv","id":"1806.00800","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00800","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00800v1","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00800","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"pith_short_12","alias_value":"X5ZLUS6KI44N","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"X5ZLUS6KI44NTVRJ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"X5ZLUS6K","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:X5ZLUS6KI44NTVRJ2BMMLJK7RI","target":"record","payload":{"canonical_record":{"source":{"id":"1806.00800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T14:38:17Z","cross_cats_sorted":[],"title_canon_sha256":"0b1568979c852d5392b1813daf5dc5fd9c810dbe4ead5e30c99984a60b4411ed","abstract_canon_sha256":"62b108bb5a5835ca837bdb47f2bc970178dd4efaebd8bcdd7c6fbf75b4b236af"},"schema_version":"1.0"},"canonical_sha256":"bf72ba4bca4738d9d629d058c5a55f8a198f4517c216031f12c3bb7bf0426d91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:18.375971Z","signature_b64":"L0uPQCHeWEBAqif1nmNb1IeLBYe3AdEK5z/UD1Pi3UWYZqlch+E2g5yIQSuIQOAC0P+1rBRaV1vVxVFxCsVVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf72ba4bca4738d9d629d058c5a55f8a198f4517c216031f12c3bb7bf0426d91","last_reissued_at":"2026-05-18T00:14:18.375535Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:18.375535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.00800","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ehj57VZ5aBJjNmZdQuNlEIf2yeRbCbXHoDLendEsKWzTcfUGKZi05qBr70OgyJI5C7WsR/YFJkyzkpNolOP6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:55:22.184015Z"},"content_sha256":"0917590d3fa6811e93d1afeeb97a1cf9d8590fc0671bbfebfc208891966d128b","schema_version":"1.0","event_id":"sha256:0917590d3fa6811e93d1afeeb97a1cf9d8590fc0671bbfebfc208891966d128b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:X5ZLUS6KI44NTVRJ2BMMLJK7RI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProFlow: Learning to Predict Optical Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'es Bruhn, Daniel Maurer","submitted_at":"2018-06-03T14:38:17Z","abstract_excerpt":"Temporal coherence is a valuable source of information in the context of optical flow estimation. However, finding a suitable motion model to leverage this information is a non-trivial task. In this paper we propose an unsupervised online learning approach based on a convolutional neural network (CNN) that estimates such a motion model individually for each frame. By relating forward and backward motion these learned models not only allow to infer valuable motion information based on the backward flow, they also help to improve the performance at occlusions, where a reliable prediction is part"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00800","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"44ddSA+63Lb8PXg9PCLimC5mg/8W/gwM9Sz34WhjcN82FDF0adO2Sd6PvB3KGaLhwqk7M7Hezi8rjR8DzvsHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:55:22.184695Z"},"content_sha256":"aa95ae06ea2232b0288da3f807b33067b0ac3cd0f10cee8bad98cad1a4ce0d89","schema_version":"1.0","event_id":"sha256:aa95ae06ea2232b0288da3f807b33067b0ac3cd0f10cee8bad98cad1a4ce0d89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5ZLUS6KI44NTVRJ2BMMLJK7RI/bundle.json","state_url":"https://pith.science/pith/X5ZLUS6KI44NTVRJ2BMMLJK7RI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5ZLUS6KI44NTVRJ2BMMLJK7RI/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":"2026-05-25T19:55:22Z","links":{"resolver":"https://pith.science/pith/X5ZLUS6KI44NTVRJ2BMMLJK7RI","bundle":"https://pith.science/pith/X5ZLUS6KI44NTVRJ2BMMLJK7RI/bundle.json","state":"https://pith.science/pith/X5ZLUS6KI44NTVRJ2BMMLJK7RI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5ZLUS6KI44NTVRJ2BMMLJK7RI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:X5ZLUS6KI44NTVRJ2BMMLJK7RI","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":"62b108bb5a5835ca837bdb47f2bc970178dd4efaebd8bcdd7c6fbf75b4b236af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T14:38:17Z","title_canon_sha256":"0b1568979c852d5392b1813daf5dc5fd9c810dbe4ead5e30c99984a60b4411ed"},"schema_version":"1.0","source":{"id":"1806.00800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00800","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00800v1","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00800","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"pith_short_12","alias_value":"X5ZLUS6KI44N","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"X5ZLUS6KI44NTVRJ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"X5ZLUS6K","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:aa95ae06ea2232b0288da3f807b33067b0ac3cd0f10cee8bad98cad1a4ce0d89","target":"graph","created_at":"2026-05-18T00:14:18Z","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":"Temporal coherence is a valuable source of information in the context of optical flow estimation. However, finding a suitable motion model to leverage this information is a non-trivial task. In this paper we propose an unsupervised online learning approach based on a convolutional neural network (CNN) that estimates such a motion model individually for each frame. By relating forward and backward motion these learned models not only allow to infer valuable motion information based on the backward flow, they also help to improve the performance at occlusions, where a reliable prediction is part","authors_text":"Andr\\'es Bruhn, Daniel Maurer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T14:38:17Z","title":"ProFlow: Learning to Predict Optical Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00800","kind":"arxiv","version":1},"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":"sha256:0917590d3fa6811e93d1afeeb97a1cf9d8590fc0671bbfebfc208891966d128b","target":"record","created_at":"2026-05-18T00:14:18Z","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":"62b108bb5a5835ca837bdb47f2bc970178dd4efaebd8bcdd7c6fbf75b4b236af","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T14:38:17Z","title_canon_sha256":"0b1568979c852d5392b1813daf5dc5fd9c810dbe4ead5e30c99984a60b4411ed"},"schema_version":"1.0","source":{"id":"1806.00800","kind":"arxiv","version":1}},"canonical_sha256":"bf72ba4bca4738d9d629d058c5a55f8a198f4517c216031f12c3bb7bf0426d91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf72ba4bca4738d9d629d058c5a55f8a198f4517c216031f12c3bb7bf0426d91","first_computed_at":"2026-05-18T00:14:18.375535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:18.375535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L0uPQCHeWEBAqif1nmNb1IeLBYe3AdEK5z/UD1Pi3UWYZqlch+E2g5yIQSuIQOAC0P+1rBRaV1vVxVFxCsVVBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:18.375971Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.00800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0917590d3fa6811e93d1afeeb97a1cf9d8590fc0671bbfebfc208891966d128b","sha256:aa95ae06ea2232b0288da3f807b33067b0ac3cd0f10cee8bad98cad1a4ce0d89"],"state_sha256":"f61e13b025c71d4ba5b53f67fe26099c4d55b1a56acb1a5a8c6944df1d7f0953"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0fxr5W36k2w1wX3qYRbQuWzJ9mrHtK0nDFg2hdVhj5tyZbrr5ul2JNsY3g6p86rcgu7aD3t4B8xksfvLw2l8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:55:22.188362Z","bundle_sha256":"54ad41a1006e22b1ab99698071e83d189ef528ffcc93db6cd829e1da4002311d"}}