{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J4IKBLKAZEKYEIY2MQCBNL7N7J","short_pith_number":"pith:J4IKBLKA","canonical_record":{"source":{"id":"1905.00875","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-02T17:45:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1ac3439c6b59cfa5af5f92bb45777d82daa155a70265a17070562b31be83ec38","abstract_canon_sha256":"d5b861fc424abcf6ecf90c032272dee1f03126ab0e63a1b114a94990ba41fe0f"},"schema_version":"1.0"},"canonical_sha256":"4f10a0ad40c91582231a640416afedfa7e3b4793ed294c89b8701b31b18298ac","source":{"kind":"arxiv","id":"1905.00875","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00875","created_at":"2026-05-17T23:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00875v5","created_at":"2026-05-17T23:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00875","created_at":"2026-05-17T23:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"J4IKBLKAZEKY","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J4IKBLKAZEKYEIY2","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J4IKBLKA","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J4IKBLKAZEKYEIY2MQCBNL7N7J","target":"record","payload":{"canonical_record":{"source":{"id":"1905.00875","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-02T17:45:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1ac3439c6b59cfa5af5f92bb45777d82daa155a70265a17070562b31be83ec38","abstract_canon_sha256":"d5b861fc424abcf6ecf90c032272dee1f03126ab0e63a1b114a94990ba41fe0f"},"schema_version":"1.0"},"canonical_sha256":"4f10a0ad40c91582231a640416afedfa7e3b4793ed294c89b8701b31b18298ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:24.276688Z","signature_b64":"1RWlRLVGAe3gpS7LBAGyB631B7evEvwjh5dTVT0AfoqDWB5D+7nIEHn2vkk+X8dfO1daATI369YX2KvmT+iiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f10a0ad40c91582231a640416afedfa7e3b4793ed294c89b8701b31b18298ac","last_reissued_at":"2026-05-17T23:39:24.276072Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:24.276072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.00875","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kk/IVv0Y/Hmf/vaShY7Mk0TQwAL3Idbe0LKtWZVVBsj/WwSUybBriZr1/Jtf6l1BSo/LoG9Cbtpe8rBDK3luAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T18:11:30.388827Z"},"content_sha256":"18843edc58d1e2bcf28bdc8340f7e734dc6c637db54c12737368d3b3b181ae4f","schema_version":"1.0","event_id":"sha256:18843edc58d1e2bcf28bdc8340f7e734dc6c637db54c12737368d3b3b181ae4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J4IKBLKAZEKYEIY2MQCBNL7N7J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised Learning for Video Correspondence Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Weidi Xie, Zihang Lai","submitted_at":"2019-05-02T17:45:16Z","abstract_excerpt":"The objective of this paper is self-supervised learning of feature embeddings that are suitable for matching correspondences along the videos, which we term correspondence flow. By leveraging the natural spatial-temporal coherence in videos, we propose to train a ``pointer'' that reconstructs a target frame by copying pixels from a reference frame.\n  We make the following contributions: First, we introduce a simple information bottleneck that forces the model to learn robust features for correspondence matching, and prevent it from learning trivial solutions, \\eg matching based on low-level co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00875","kind":"arxiv","version":5},"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":"2026-05-17T23:39:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BoMHzTURrwWsOvUcYqHpzdqIp9ldagiv1ENd3vsUL2oOZ++WQpOuLUDs1j84U3xGt3UD7smOJxWQGhKLmZ52Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T18:11:30.389488Z"},"content_sha256":"e26468bf8f89e5672f9e6f70155991a47a80c6b4ee963f59bf3647876da8cbae","schema_version":"1.0","event_id":"sha256:e26468bf8f89e5672f9e6f70155991a47a80c6b4ee963f59bf3647876da8cbae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J4IKBLKAZEKYEIY2MQCBNL7N7J/bundle.json","state_url":"https://pith.science/pith/J4IKBLKAZEKYEIY2MQCBNL7N7J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J4IKBLKAZEKYEIY2MQCBNL7N7J/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":"2026-06-08T18:11:30Z","links":{"resolver":"https://pith.science/pith/J4IKBLKAZEKYEIY2MQCBNL7N7J","bundle":"https://pith.science/pith/J4IKBLKAZEKYEIY2MQCBNL7N7J/bundle.json","state":"https://pith.science/pith/J4IKBLKAZEKYEIY2MQCBNL7N7J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J4IKBLKAZEKYEIY2MQCBNL7N7J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J4IKBLKAZEKYEIY2MQCBNL7N7J","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":"d5b861fc424abcf6ecf90c032272dee1f03126ab0e63a1b114a94990ba41fe0f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-02T17:45:16Z","title_canon_sha256":"1ac3439c6b59cfa5af5f92bb45777d82daa155a70265a17070562b31be83ec38"},"schema_version":"1.0","source":{"id":"1905.00875","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00875","created_at":"2026-05-17T23:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00875v5","created_at":"2026-05-17T23:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00875","created_at":"2026-05-17T23:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"J4IKBLKAZEKY","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J4IKBLKAZEKYEIY2","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J4IKBLKA","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:e26468bf8f89e5672f9e6f70155991a47a80c6b4ee963f59bf3647876da8cbae","target":"graph","created_at":"2026-05-17T23:39:24Z","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":"The objective of this paper is self-supervised learning of feature embeddings that are suitable for matching correspondences along the videos, which we term correspondence flow. By leveraging the natural spatial-temporal coherence in videos, we propose to train a ``pointer'' that reconstructs a target frame by copying pixels from a reference frame.\n  We make the following contributions: First, we introduce a simple information bottleneck that forces the model to learn robust features for correspondence matching, and prevent it from learning trivial solutions, \\eg matching based on low-level co","authors_text":"Weidi Xie, Zihang Lai","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-02T17:45:16Z","title":"Self-supervised Learning for Video Correspondence Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00875","kind":"arxiv","version":5},"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":"sha256:18843edc58d1e2bcf28bdc8340f7e734dc6c637db54c12737368d3b3b181ae4f","target":"record","created_at":"2026-05-17T23:39:24Z","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":"d5b861fc424abcf6ecf90c032272dee1f03126ab0e63a1b114a94990ba41fe0f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-05-02T17:45:16Z","title_canon_sha256":"1ac3439c6b59cfa5af5f92bb45777d82daa155a70265a17070562b31be83ec38"},"schema_version":"1.0","source":{"id":"1905.00875","kind":"arxiv","version":5}},"canonical_sha256":"4f10a0ad40c91582231a640416afedfa7e3b4793ed294c89b8701b31b18298ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f10a0ad40c91582231a640416afedfa7e3b4793ed294c89b8701b31b18298ac","first_computed_at":"2026-05-17T23:39:24.276072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:24.276072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1RWlRLVGAe3gpS7LBAGyB631B7evEvwjh5dTVT0AfoqDWB5D+7nIEHn2vkk+X8dfO1daATI369YX2KvmT+iiCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:24.276688Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.00875","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18843edc58d1e2bcf28bdc8340f7e734dc6c637db54c12737368d3b3b181ae4f","sha256:e26468bf8f89e5672f9e6f70155991a47a80c6b4ee963f59bf3647876da8cbae"],"state_sha256":"01a9881844ea6e0e13cf41b0c9975ac0963171cb635a669006c2df9edd510a85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C99K4mbI3GnYI1w8o5UeGAclhN+OyyMtFoziP68DPjjxLAJKwrCFxu13EqAOceWDHGpmjojP6k3CIQp9EO+rDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T18:11:30.393033Z","bundle_sha256":"425562cc17c5f61b345725bd6e202911bff7085a963306e54fa99cd4a1bdd403"}}