{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KBRODWMTZYM3G7YRTB4R5GS7TF","short_pith_number":"pith:KBRODWMT","schema_version":"1.0","canonical_sha256":"5062e1d993ce19b37f1198791e9a5f995824133b104fdc354cf34651594f4d3b","source":{"kind":"arxiv","id":"2504.11326","version":2},"attestation_state":"computed","paper":{"title":"PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Fang Liu, Haichao Jiang, Haobo Yuan, Hao Fang, Henghui Ding, Jian-Fang Hu, Jiaxuan Zhao, Junpei Zhang, Kehuan Song, Kexin Zhang, Licheng Jiao, Lingling Li, Linnan Zhao, Lu Qi, Mengjiao Wang, Mengru Ma, Ming-Hsuan Yang, Nikhila Ravi, Philip Torr, Runmin Cong, Shuting He, Shuyuan Yang, Song Bai, Tao Zhang, Tianming Liang, Wei-Shi Zheng, Wei Zhang, Xiangtai Li, Xiankai Lu, Xinglin Xie, Xu Liu, Xuqiang Cao, Yunchao Wei, Yuting Yang, Zhiyang Chen","submitted_at":"2025-04-15T16:02:47Z","abstract_excerpt":"This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The challenge features two tracks: MOSE, which focuses on complex scene video object segmentation, and MeViS, which targets motion-guided, language-based video segmentation. Both tracks introduce new, more challenging datasets designed to better reflect real-world scenarios. Through detailed evaluation and analysis, the challenge offers valuabl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.11326","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-15T16:02:47Z","cross_cats_sorted":[],"title_canon_sha256":"b974ff844bb1e9d18b3e4fef9ae86f7213423308aaa405f9c538f02ba987ae35","abstract_canon_sha256":"cf8021b5f7042e59764e57b8c82bd97338cb4b1bef72f6306cf4ea5672016baf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:37.370729Z","signature_b64":"uFQQALscc7aDD6kck6HcQxxiq9Sye5ux9+z8df0NWF0Ql1rmYYJdwwZeOjYtQZfRq35JCbiOA2ZRAPKN5Gp7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5062e1d993ce19b37f1198791e9a5f995824133b104fdc354cf34651594f4d3b","last_reissued_at":"2026-07-05T10:51:37.370180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:37.370180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Fang Liu, Haichao Jiang, Haobo Yuan, Hao Fang, Henghui Ding, Jian-Fang Hu, Jiaxuan Zhao, Junpei Zhang, Kehuan Song, Kexin Zhang, Licheng Jiao, Lingling Li, Linnan Zhao, Lu Qi, Mengjiao Wang, Mengru Ma, Ming-Hsuan Yang, Nikhila Ravi, Philip Torr, Runmin Cong, Shuting He, Shuyuan Yang, Song Bai, Tao Zhang, Tianming Liang, Wei-Shi Zheng, Wei Zhang, Xiangtai Li, Xiankai Lu, Xinglin Xie, Xu Liu, Xuqiang Cao, Yunchao Wei, Yuting Yang, Zhiyang Chen","submitted_at":"2025-04-15T16:02:47Z","abstract_excerpt":"This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The challenge features two tracks: MOSE, which focuses on complex scene video object segmentation, and MeViS, which targets motion-guided, language-based video segmentation. Both tracks introduce new, more challenging datasets designed to better reflect real-world scenarios. Through detailed evaluation and analysis, the challenge offers valuabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11326","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.11326/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.11326","created_at":"2026-07-05T10:51:37.370243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11326v2","created_at":"2026-07-05T10:51:37.370243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11326","created_at":"2026-07-05T10:51:37.370243+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBRODWMTZYM3","created_at":"2026-07-05T10:51:37.370243+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBRODWMTZYM3G7YR","created_at":"2026-07-05T10:51:37.370243+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBRODWMT","created_at":"2026-07-05T10:51:37.370243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14471","citing_title":"Dense360: Dense Understanding from Omnidirectional Panoramas","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF","json":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF.json","graph_json":"https://pith.science/api/pith-number/KBRODWMTZYM3G7YRTB4R5GS7TF/graph.json","events_json":"https://pith.science/api/pith-number/KBRODWMTZYM3G7YRTB4R5GS7TF/events.json","paper":"https://pith.science/paper/KBRODWMT"},"agent_actions":{"view_html":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF","download_json":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF.json","view_paper":"https://pith.science/paper/KBRODWMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11326&json=true","fetch_graph":"https://pith.science/api/pith-number/KBRODWMTZYM3G7YRTB4R5GS7TF/graph.json","fetch_events":"https://pith.science/api/pith-number/KBRODWMTZYM3G7YRTB4R5GS7TF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF/action/storage_attestation","attest_author":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF/action/author_attestation","sign_citation":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF/action/citation_signature","submit_replication":"https://pith.science/pith/KBRODWMTZYM3G7YRTB4R5GS7TF/action/replication_record"}},"created_at":"2026-07-05T10:51:37.370243+00:00","updated_at":"2026-07-05T10:51:37.370243+00:00"}