{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z6EMEU7G5LNGRVIJAQCGYBV22M","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":"f3db0d0069e2de8459eed34ddead03deb61d9a681b36908bdc1c19ca7704abb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T17:30:08Z","title_canon_sha256":"5e741099f603f4b0b1eec5361370c314f710add69da90da202fd91f2661b1db5"},"schema_version":"1.0","source":{"id":"2308.13505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13505","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13505v2","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13505","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"Z6EMEU7G5LNG","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z6EMEU7G5LNGRVIJ","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z6EMEU7G","created_at":"2026-07-05T10:56:04Z"}],"graph_snapshots":[{"event_id":"sha256:dfbbb9e68473aeb568fc56c979a2d5edb13a608a638bb499b8cc108cbdf67725","target":"graph","created_at":"2026-07-05T10:56:04Z","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/2308.13505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current prevailing Video Object Segmentation methods follow the pipeline of extraction-then-matching, which first extracts features on current and reference frames independently, and then performs dense matching between them. This decoupled pipeline limits information propagation between frames to high-level features, hindering fine-grained details for matching. Furthermore, the pixel-wise matching lacks holistic target understanding, making it prone to disturbance by similar distractors. To address these issues, we propose a unified VOS framework, coined as JointFormer, for jointly modeling f","authors_text":"Gangshan Wu, Jiaming Zhang, Limin Wang, Yutao Cui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T17:30:08Z","title":"Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13505","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":"sha256:0934ab5e9b160c2e6641a1cb955572c6f9e36e84f927cb679cfff4a54d38e810","target":"record","created_at":"2026-07-05T10:56:04Z","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":"f3db0d0069e2de8459eed34ddead03deb61d9a681b36908bdc1c19ca7704abb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-25T17:30:08Z","title_canon_sha256":"5e741099f603f4b0b1eec5361370c314f710add69da90da202fd91f2661b1db5"},"schema_version":"1.0","source":{"id":"2308.13505","kind":"arxiv","version":2}},"canonical_sha256":"cf88c253e6eada68d50904046c06bad31ca0e28d1091d2713d6efd2f1a941619","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf88c253e6eada68d50904046c06bad31ca0e28d1091d2713d6efd2f1a941619","first_computed_at":"2026-07-05T10:56:04.354888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:04.354888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"osnez+cJQWEGEU054SfFG/i16szdBpJNmyCVRk72oFkX99zwPPpPzYBq05/Ss9/V+7tiOR6jp8Obc7ETYfFNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:04.355372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0934ab5e9b160c2e6641a1cb955572c6f9e36e84f927cb679cfff4a54d38e810","sha256:dfbbb9e68473aeb568fc56c979a2d5edb13a608a638bb499b8cc108cbdf67725"],"state_sha256":"1784e5871a84bb67c51cecd300f7b4819863983657754513205cec47d694c999"}