{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RTXUJEYKJGKTUEVWTWYY2E6RHS","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":"7b94fbead62481434c87f63af7c85d2ebb33de4d57142ccc8d9801f463c95ffe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-15T17:09:18Z","title_canon_sha256":"600d8046f242c32b019c3379c0ab89a3a66d64ed5f45c8a50b3a16c5b4012bad"},"schema_version":"1.0","source":{"id":"2112.08275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08275","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08275v2","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08275","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"RTXUJEYKJGKT","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_16","alias_value":"RTXUJEYKJGKTUEVW","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_8","alias_value":"RTXUJEYK","created_at":"2026-07-05T04:42:15Z"}],"graph_snapshots":[{"event_id":"sha256:5f2a76823d396a07fbc66d033a2123127ef71515ba066f5a9f93b0680cfbbe2a","target":"graph","created_at":"2026-07-05T04:42:15Z","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/2112.08275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently. To achieve this, SeqFormer locates an instance in each frame and aggregates temporal information to learn a powerful representation of a video-level instance, which is used to predict the mask sequences on each frame dynamically. ","authors_text":"Junfeng Wu, Song Bai, Wenqing Zhang, Xiang Bai, Yi Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-15T17:09:18Z","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08275","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":"sha256:9b961ba06d0b5c535f265044e9ab44d06724d65d74d7ea752c6584949eb473cc","target":"record","created_at":"2026-07-05T04:42:15Z","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":"7b94fbead62481434c87f63af7c85d2ebb33de4d57142ccc8d9801f463c95ffe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-15T17:09:18Z","title_canon_sha256":"600d8046f242c32b019c3379c0ab89a3a66d64ed5f45c8a50b3a16c5b4012bad"},"schema_version":"1.0","source":{"id":"2112.08275","kind":"arxiv","version":2}},"canonical_sha256":"8cef44930a49953a12b69db18d13d13c8e9892ba039901a54e047b06607add75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cef44930a49953a12b69db18d13d13c8e9892ba039901a54e047b06607add75","first_computed_at":"2026-07-05T04:42:15.742664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:15.742664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HpLXW3R3Me04O7VHWp0Su3TpQFw6jYLg3fgMBmXNavN2+zL8uHRb1kEG1pCbAorLUndUyGSQhMbRmUIBITTgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:15.743064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b961ba06d0b5c535f265044e9ab44d06724d65d74d7ea752c6584949eb473cc","sha256:5f2a76823d396a07fbc66d033a2123127ef71515ba066f5a9f93b0680cfbbe2a"],"state_sha256":"31a3a5b84d6f8c6cea1cf883d554786f4b7921e76e70113be04264560eabd84f"}