{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KONLH2XJTEKYCWNCYKABSGSBGX","short_pith_number":"pith:KONLH2XJ","canonical_record":{"source":{"id":"1905.07853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T03:07:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0328a592428dbaba84fda84deb80476b3a1e626eb6de886ff0d6b14a693238d","abstract_canon_sha256":"1b09ec1dd34088a994dca3835690bbaacb139f92c6bad74760073618a05c5abc"},"schema_version":"1.0"},"canonical_sha256":"539ab3eae999158159a2c280191a4135f46dccf64e04944f59eb1d2657855502","source":{"kind":"arxiv","id":"1905.07853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07853","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07853v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07853","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"KONLH2XJTEKY","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KONLH2XJTEKYCWNC","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KONLH2XJ","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KONLH2XJTEKYCWNCYKABSGSBGX","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T03:07:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e0328a592428dbaba84fda84deb80476b3a1e626eb6de886ff0d6b14a693238d","abstract_canon_sha256":"1b09ec1dd34088a994dca3835690bbaacb139f92c6bad74760073618a05c5abc"},"schema_version":"1.0"},"canonical_sha256":"539ab3eae999158159a2c280191a4135f46dccf64e04944f59eb1d2657855502","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.326152Z","signature_b64":"xRAj3KRhndzgfgfV1SQcuIizPwLxyPuAwAyycSNJorZrlcqmltO7MNdwEcfsPFCPXTJHMLbfgHQjqxeT7NIwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"539ab3eae999158159a2c280191a4135f46dccf64e04944f59eb1d2657855502","last_reissued_at":"2026-05-17T23:45:48.325467Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.325467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07853","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bvHKuIGmbQxo8mNPEz/LKmDEjb5Y+lzGISk4k64Y4oDmODtK+popalXfCJ0T4D6expG/vmGuVCGWWf4Cv00eDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:30:09.201607Z"},"content_sha256":"2fcc8b9c5e41139bac21027ab3614998261a51f05da489758f8a2ee2dca3466e","schema_version":"1.0","event_id":"sha256:2fcc8b9c5e41139bac21027ab3614998261a51f05da489758f8a2ee2dca3466e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KONLH2XJTEKYCWNCYKABSGSBGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Video Representations from Correspondence Proposals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hailin Jin, Joon-Young Lee, Xingyu Liu","submitted_at":"2019-05-20T03:07:51Z","abstract_excerpt":"Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular structure and complex dynamics. In this paper, we propose a novel neural network that learns video representations by aggregating information from potential correspondences. This network, named $CPNet$, can learn evolving 2D fields with temporal consistency. In particular, it can effectively learn representations for videos by mixing appearance and long-range motion with an RGB-only input. We provide extensive ablation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07853","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VfaeQDUqh26doGjO/cGoK8xS8PsYkwSUgLqlBIGkZsgumXLgUZEmpcgtn+1As3JInztJCp3GoC27nwzZLvHwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:30:09.202159Z"},"content_sha256":"8c155a0b21faa3849fa32f540dc0bdf9a0cdbc9da8db6a4b648d7e80469147cc","schema_version":"1.0","event_id":"sha256:8c155a0b21faa3849fa32f540dc0bdf9a0cdbc9da8db6a4b648d7e80469147cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KONLH2XJTEKYCWNCYKABSGSBGX/bundle.json","state_url":"https://pith.science/pith/KONLH2XJTEKYCWNCYKABSGSBGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KONLH2XJTEKYCWNCYKABSGSBGX/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":"2026-05-26T04:30:09Z","links":{"resolver":"https://pith.science/pith/KONLH2XJTEKYCWNCYKABSGSBGX","bundle":"https://pith.science/pith/KONLH2XJTEKYCWNCYKABSGSBGX/bundle.json","state":"https://pith.science/pith/KONLH2XJTEKYCWNCYKABSGSBGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KONLH2XJTEKYCWNCYKABSGSBGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KONLH2XJTEKYCWNCYKABSGSBGX","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":"1b09ec1dd34088a994dca3835690bbaacb139f92c6bad74760073618a05c5abc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T03:07:51Z","title_canon_sha256":"e0328a592428dbaba84fda84deb80476b3a1e626eb6de886ff0d6b14a693238d"},"schema_version":"1.0","source":{"id":"1905.07853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07853","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07853v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07853","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"KONLH2XJTEKY","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KONLH2XJTEKYCWNC","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KONLH2XJ","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:8c155a0b21faa3849fa32f540dc0bdf9a0cdbc9da8db6a4b648d7e80469147cc","target":"graph","created_at":"2026-05-17T23:45:48Z","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":"Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular structure and complex dynamics. In this paper, we propose a novel neural network that learns video representations by aggregating information from potential correspondences. This network, named $CPNet$, can learn evolving 2D fields with temporal consistency. In particular, it can effectively learn representations for videos by mixing appearance and long-range motion with an RGB-only input. We provide extensive ablation ","authors_text":"Hailin Jin, Joon-Young Lee, Xingyu Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T03:07:51Z","title":"Learning Video Representations from Correspondence Proposals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07853","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":"sha256:2fcc8b9c5e41139bac21027ab3614998261a51f05da489758f8a2ee2dca3466e","target":"record","created_at":"2026-05-17T23:45:48Z","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":"1b09ec1dd34088a994dca3835690bbaacb139f92c6bad74760073618a05c5abc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-20T03:07:51Z","title_canon_sha256":"e0328a592428dbaba84fda84deb80476b3a1e626eb6de886ff0d6b14a693238d"},"schema_version":"1.0","source":{"id":"1905.07853","kind":"arxiv","version":1}},"canonical_sha256":"539ab3eae999158159a2c280191a4135f46dccf64e04944f59eb1d2657855502","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"539ab3eae999158159a2c280191a4135f46dccf64e04944f59eb1d2657855502","first_computed_at":"2026-05-17T23:45:48.325467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:48.325467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xRAj3KRhndzgfgfV1SQcuIizPwLxyPuAwAyycSNJorZrlcqmltO7MNdwEcfsPFCPXTJHMLbfgHQjqxeT7NIwBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:48.326152Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fcc8b9c5e41139bac21027ab3614998261a51f05da489758f8a2ee2dca3466e","sha256:8c155a0b21faa3849fa32f540dc0bdf9a0cdbc9da8db6a4b648d7e80469147cc"],"state_sha256":"ff9b550abaa28ae75bcfef43d8530ac417ddef31cc7bdbc929f5c87f0e8d49b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EllyQ00tA9wfsygwbkTto+3lVOdky7pobwF62CetgFzNt/7Nps0+BRZ+0rChGkjxJheKTqn8VV3SH8s67eGeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:30:09.205171Z","bundle_sha256":"c5f5ffd2e364f7c77dc1471f205e275a7473e772a41d3d27a56d7c6c027523c7"}}