{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:535ZF3U2Z6K3QVM5RE4NWF2ICT","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":"b1d3367a38d8511e46faf4581bc2487d3c9da6595cf25d6e882ac00021dff541","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T07:05:27Z","title_canon_sha256":"fd29f7525afd5855345273e5cc7e5ddcce856e12c78900750e9c5c6dcc2c280c"},"schema_version":"1.0","source":{"id":"2402.18115","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18115","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18115v2","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18115","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"pith_short_12","alias_value":"535ZF3U2Z6K3","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"pith_short_16","alias_value":"535ZF3U2Z6K3QVM5","created_at":"2026-07-05T08:29:23Z"},{"alias_kind":"pith_short_8","alias_value":"535ZF3U2","created_at":"2026-07-05T08:29:23Z"}],"graph_snapshots":[{"event_id":"sha256:e7b1569bb32d1f6d54a6be698b7b059f51145ea3f3e55c49eccb632f964c5be5","target":"graph","created_at":"2026-07-05T08:29:23Z","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/2402.18115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts throughout the entire video, making it hard to handle the different tasks with the same architecture. We make an attempt to address these issues and present a novel unified VS architecture, namely UniVS, by using prompts as queries. UniVS averages ","authors_text":"Lei Zhang, Minghan Li, Shuai Li, Xindong Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T07:05:27Z","title":"UniVS: Unified and Universal Video Segmentation with Prompts as Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18115","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":"sha256:4524844da0f1f1e088e57a817ba2d31f54bde1329547b73cdeb6164165dbc2a1","target":"record","created_at":"2026-07-05T08:29:23Z","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":"b1d3367a38d8511e46faf4581bc2487d3c9da6595cf25d6e882ac00021dff541","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T07:05:27Z","title_canon_sha256":"fd29f7525afd5855345273e5cc7e5ddcce856e12c78900750e9c5c6dcc2c280c"},"schema_version":"1.0","source":{"id":"2402.18115","kind":"arxiv","version":2}},"canonical_sha256":"eefb92ee9acf95b8559d8938db174814f31a226c16c66d358667325e1623142c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eefb92ee9acf95b8559d8938db174814f31a226c16c66d358667325e1623142c","first_computed_at":"2026-07-05T08:29:23.311923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:23.311923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CuJpVxPzl1lvA07ETw9yOycYVLSNvlgv9+BuPBqAFrxRayK9NeHgqTnTYiT3R6/C9NyGFPg6vcxGuc+dpg8RCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:23.312406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18115","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4524844da0f1f1e088e57a817ba2d31f54bde1329547b73cdeb6164165dbc2a1","sha256:e7b1569bb32d1f6d54a6be698b7b059f51145ea3f3e55c49eccb632f964c5be5"],"state_sha256":"390a92347a346f1610c7204831b786f3fa99ba3a1a1951811c9ec1d6b907209b"}