{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:X3VJMGDYVULN2CFBTMMJQOEWOO","short_pith_number":"pith:X3VJMGDY","canonical_record":{"source":{"id":"1504.06852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-26T17:30:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0162cd28d3815e7a30532b2ffbd5d0aee22d7143e090834a84a79c4110bb74de","abstract_canon_sha256":"6fca25f6c9f4ffc5b18ea21846a4930cd1c2ca6cbd66579373a2bd4fe6d9acf4"},"schema_version":"1.0"},"canonical_sha256":"beea961878ad16dd08a19b1898389673819968d1ae54e10ec543174fa273ff00","source":{"kind":"arxiv","id":"1504.06852","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.06852","created_at":"2026-05-18T01:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"1504.06852v2","created_at":"2026-05-18T01:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06852","created_at":"2026-05-18T01:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"X3VJMGDYVULN","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"X3VJMGDYVULN2CFB","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"X3VJMGDY","created_at":"2026-05-18T12:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:X3VJMGDYVULN2CFBTMMJQOEWOO","target":"record","payload":{"canonical_record":{"source":{"id":"1504.06852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-26T17:30:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0162cd28d3815e7a30532b2ffbd5d0aee22d7143e090834a84a79c4110bb74de","abstract_canon_sha256":"6fca25f6c9f4ffc5b18ea21846a4930cd1c2ca6cbd66579373a2bd4fe6d9acf4"},"schema_version":"1.0"},"canonical_sha256":"beea961878ad16dd08a19b1898389673819968d1ae54e10ec543174fa273ff00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:46:13.325884Z","signature_b64":"Q70HtMe0OCP2PWt3d9r5tM0SKgGRrNq2EwAqGobgMUqOq6ugLUFxwLBFnfbIP2J91YnvOBnhk2lN0sPxG5J0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beea961878ad16dd08a19b1898389673819968d1ae54e10ec543174fa273ff00","last_reissued_at":"2026-05-18T01:46:13.325067Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:46:13.325067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.06852","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":"2026-05-18T01:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0nqJt5PT6jVttpJuu5jK5y63Iu13oi67P6ztFmMkaKiB+Z/PAgUTWe5DqB0c5xwA6+jHdRiuoFxkAxgp4ecxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:11:59.520718Z"},"content_sha256":"64e6eafa5a539f7a18d18c4eb14725f22245af5a213ad11751c143da92dd4f8a","schema_version":"1.0","event_id":"sha256:64e6eafa5a539f7a18d18c4eb14725f22245af5a213ad11751c143da92dd4f8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:X3VJMGDYVULN2CFBTMMJQOEWOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FlowNet: Learning Optical Flow with Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexey Dosovitskiy, Caner Haz{\\i}rba\\c{s}, Daniel Cremers, Eddy Ilg, Patrick van der Smagt, Philip H\\\"ausser, Philipp Fischer, Thomas Brox, Vladimir Golkov","submitted_at":"2015-04-26T17:30:32Z","abstract_excerpt":"Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not been among the tasks where CNNs were successful. In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.\n  Since existing ground truth data sets are not sufficiently lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06852","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":"2026-05-18T01:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7/DDUw6yo+QzyaU8jv5mg0e8b3o4NHun9jUfFD8lIpbgQkdwht4avWRC9lvUxKwxS0VTN7KU0sMnVPDp4qJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:11:59.521273Z"},"content_sha256":"09c91f2b2bcf0512c342742cbfcadd422aeac6f2eeed858670961b6b92488b3f","schema_version":"1.0","event_id":"sha256:09c91f2b2bcf0512c342742cbfcadd422aeac6f2eeed858670961b6b92488b3f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3VJMGDYVULN2CFBTMMJQOEWOO/bundle.json","state_url":"https://pith.science/pith/X3VJMGDYVULN2CFBTMMJQOEWOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3VJMGDYVULN2CFBTMMJQOEWOO/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":"2026-05-25T23:11:59Z","links":{"resolver":"https://pith.science/pith/X3VJMGDYVULN2CFBTMMJQOEWOO","bundle":"https://pith.science/pith/X3VJMGDYVULN2CFBTMMJQOEWOO/bundle.json","state":"https://pith.science/pith/X3VJMGDYVULN2CFBTMMJQOEWOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3VJMGDYVULN2CFBTMMJQOEWOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:X3VJMGDYVULN2CFBTMMJQOEWOO","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":"6fca25f6c9f4ffc5b18ea21846a4930cd1c2ca6cbd66579373a2bd4fe6d9acf4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-26T17:30:32Z","title_canon_sha256":"0162cd28d3815e7a30532b2ffbd5d0aee22d7143e090834a84a79c4110bb74de"},"schema_version":"1.0","source":{"id":"1504.06852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.06852","created_at":"2026-05-18T01:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"1504.06852v2","created_at":"2026-05-18T01:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.06852","created_at":"2026-05-18T01:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"X3VJMGDYVULN","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"X3VJMGDYVULN2CFB","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"X3VJMGDY","created_at":"2026-05-18T12:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:09c91f2b2bcf0512c342742cbfcadd422aeac6f2eeed858670961b6b92488b3f","target":"graph","created_at":"2026-05-18T01:46:13Z","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":"Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not been among the tasks where CNNs were successful. In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.\n  Since existing ground truth data sets are not sufficiently lar","authors_text":"Alexey Dosovitskiy, Caner Haz{\\i}rba\\c{s}, Daniel Cremers, Eddy Ilg, Patrick van der Smagt, Philip H\\\"ausser, Philipp Fischer, Thomas Brox, Vladimir Golkov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-26T17:30:32Z","title":"FlowNet: Learning Optical Flow with Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.06852","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":"sha256:64e6eafa5a539f7a18d18c4eb14725f22245af5a213ad11751c143da92dd4f8a","target":"record","created_at":"2026-05-18T01:46:13Z","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":"6fca25f6c9f4ffc5b18ea21846a4930cd1c2ca6cbd66579373a2bd4fe6d9acf4","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-04-26T17:30:32Z","title_canon_sha256":"0162cd28d3815e7a30532b2ffbd5d0aee22d7143e090834a84a79c4110bb74de"},"schema_version":"1.0","source":{"id":"1504.06852","kind":"arxiv","version":2}},"canonical_sha256":"beea961878ad16dd08a19b1898389673819968d1ae54e10ec543174fa273ff00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"beea961878ad16dd08a19b1898389673819968d1ae54e10ec543174fa273ff00","first_computed_at":"2026-05-18T01:46:13.325067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:46:13.325067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q70HtMe0OCP2PWt3d9r5tM0SKgGRrNq2EwAqGobgMUqOq6ugLUFxwLBFnfbIP2J91YnvOBnhk2lN0sPxG5J0AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:46:13.325884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.06852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64e6eafa5a539f7a18d18c4eb14725f22245af5a213ad11751c143da92dd4f8a","sha256:09c91f2b2bcf0512c342742cbfcadd422aeac6f2eeed858670961b6b92488b3f"],"state_sha256":"caadd8aa4fdc9bee90ada0159fbcfcc8c303addb5adf54271d344814656d5b18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hjrvZ8/8gotfudzmOv33/rcITd5eXigcf0mh/pY9ERIKKvwJcfJuxrP1Wdl5CY9mym5jVxHwChlqb3waASDKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:11:59.524836Z","bundle_sha256":"72723b4338efab36dde48f98d53cd4c3547eb226e218e08bb346f9cf453a2fa9"}}