{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N5DUEMWQGAO7NHBM4B7SXBYYEZ","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":"1822c677edb092c52c8a9892574597432d9e01be4183af74b847b1c80bd84dc2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T18:59:59Z","title_canon_sha256":"917b5e45644cbb39c0921e350a4df562f130326f53e457dde5b9d0d7603eac95"},"schema_version":"1.0","source":{"id":"2112.10764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10764","created_at":"2026-07-05T03:42:18Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10764v1","created_at":"2026-07-05T03:42:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10764","created_at":"2026-07-05T03:42:18Z"},{"alias_kind":"pith_short_12","alias_value":"N5DUEMWQGAO7","created_at":"2026-07-05T03:42:18Z"},{"alias_kind":"pith_short_16","alias_value":"N5DUEMWQGAO7NHBM","created_at":"2026-07-05T03:42:18Z"},{"alias_kind":"pith_short_8","alias_value":"N5DUEMWQ","created_at":"2026-07-05T03:42:18Z"}],"graph_snapshots":[{"event_id":"sha256:9ae229edba2b41b0d9d7f9f681a7d3d8e7745c4b570e0a2f89a05c3de49f9aa2","target":"graph","created_at":"2026-07-05T03:42:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.10764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline. In this report, we show universal image segmentation architectures trivially generalize to video segmentation by directly predicting 3D segmentation volumes. Specifically, Mask2Former sets a new state-of-the-art of 60.4 AP on YouTubeVIS-2019 and 52.6 AP on YouTubeVIS-2021. We believe Mask2Former is also capable of handling video semantic and panoptic segmentation, given its versatility in image segmentation. We hope this will ","authors_text":"Alexander G. Schwing, Alexander Kirillov, Anwesa Choudhuri, Bowen Cheng, Ishan Misra, Rohit Girdhar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T18:59:59Z","title":"Mask2Former for Video Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10764","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:fb0ccdf980fbe29e2225b67bd70631ed661b410405110679e85096064232d950","target":"record","created_at":"2026-07-05T03:42:18Z","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":"1822c677edb092c52c8a9892574597432d9e01be4183af74b847b1c80bd84dc2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T18:59:59Z","title_canon_sha256":"917b5e45644cbb39c0921e350a4df562f130326f53e457dde5b9d0d7603eac95"},"schema_version":"1.0","source":{"id":"2112.10764","kind":"arxiv","version":1}},"canonical_sha256":"6f474232d0301df69c2ce07f2b87182640cb5e3a56ddb20816a1aa58b6f608b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f474232d0301df69c2ce07f2b87182640cb5e3a56ddb20816a1aa58b6f608b6","first_computed_at":"2026-07-05T03:42:18.692092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:42:18.692092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AtpeATQXOUUw0y4gV/Aut271pDpjCnaOQ3sY2Dvkpxw4pDeb1SZDZGrRp8b0u6kivHpmhVFURlj3e/mrE/63BA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:42:18.692776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.10764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb0ccdf980fbe29e2225b67bd70631ed661b410405110679e85096064232d950","sha256:9ae229edba2b41b0d9d7f9f681a7d3d8e7745c4b570e0a2f89a05c3de49f9aa2"],"state_sha256":"374d7117b739dee04fd6157bee997fa9e658f6d477d5b92e533269d8e38a9192"}