{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PGAL6F6CSHQQ7MLEE5S3QGXDJQ","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":"2ab7c7348e24c5b4b1c7d8feb5a2b6b9993aeb75c6070a41d88a95e130a5d6b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T17:56:35Z","title_canon_sha256":"54989ba1763dd5385ef3213e03299218dd00ffe899dd5ce6329315db9e66bbf1"},"schema_version":"1.0","source":{"id":"2103.17263","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.17263","created_at":"2026-07-05T03:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"2103.17263v5","created_at":"2026-07-05T03:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.17263","created_at":"2026-07-05T03:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"PGAL6F6CSHQQ","created_at":"2026-07-05T03:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"PGAL6F6CSHQQ7MLE","created_at":"2026-07-05T03:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"PGAL6F6C","created_at":"2026-07-05T03:22:34Z"}],"graph_snapshots":[{"event_id":"sha256:db51bc79f9694b39de96b733e51c171b27a3da73a74a3b2b174f397a6672548f","target":"graph","created_at":"2026-07-05T03:22:34Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.17263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning a good representation for space-time correspondence is the key for various computer vision tasks, including tracking object bounding boxes and performing video object pixel segmentation. To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning. Instead of following the previous literature, we propose to learn correspondence using Video Frame-level Similarity (VFS) learning, i.e, simply learning from comparing video frames. Our work is inspired b","authors_text":"Jiarui Xu, Xiaolong Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T17:56:35Z","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.17263","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":"sha256:71d9d181c7839f248c76b7da082b32899cc2b69f92db5624d292ee43c1bdfef6","target":"record","created_at":"2026-07-05T03:22:34Z","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":"2ab7c7348e24c5b4b1c7d8feb5a2b6b9993aeb75c6070a41d88a95e130a5d6b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T17:56:35Z","title_canon_sha256":"54989ba1763dd5385ef3213e03299218dd00ffe899dd5ce6329315db9e66bbf1"},"schema_version":"1.0","source":{"id":"2103.17263","kind":"arxiv","version":5}},"canonical_sha256":"7980bf17c291e10fb1642765b81ae34c00d46de44c515b0c88a471f804a9c1dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7980bf17c291e10fb1642765b81ae34c00d46de44c515b0c88a471f804a9c1dc","first_computed_at":"2026-07-05T03:22:34.455479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:34.455479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fOLm8nVcfMfQ2Au7gv4owPrzyBcdy+WN9PV5sUwrMvH1U86EFp8re8J9gRnWEcsgUIk0uTPjouITH7aa1LLNAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:34.455879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.17263","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71d9d181c7839f248c76b7da082b32899cc2b69f92db5624d292ee43c1bdfef6","sha256:db51bc79f9694b39de96b733e51c171b27a3da73a74a3b2b174f397a6672548f"],"state_sha256":"2df52283803b321e1bd3f56d90aa5693fbaa6b0682bddd7ec7910061585267de"}