{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D7YQFKUCHXUSFWXFGIVPAYU2AW","short_pith_number":"pith:D7YQFKUC","schema_version":"1.0","canonical_sha256":"1ff102aa823de922dae5322af0629a05b8dc41e11b1794a044ca33ab3380e5d4","source":{"kind":"arxiv","id":"2408.10125","version":2},"attestation_state":"computed","paper":{"title":"Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyu Pan, Hao Fang, Runmin Cong, Wei Zhang, Xiankai Lu","submitted_at":"2024-08-19T16:13:14Z","abstract_excerpt":"Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame. Recently, Segment Anything Model 2 (SAM 2) is proposed, which is a foundation model towards solving promptable visual segmentation in images and videos. SAM 2 builds a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. SAM 2 is a simple transformer architecture with streaming memory for real-time video processing, which trained on the date provides strong "},"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":"2408.10125","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T16:13:14Z","cross_cats_sorted":[],"title_canon_sha256":"a67ff5920eee1bd8ecdfdb91525106c8fb8750ba4a4e9d24f74fc6e4951b7c2b","abstract_canon_sha256":"b76c645202d2da1417fd7aa5ae35974bae4cbce9e8776440b9c7aeec0576de08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:46.885877Z","signature_b64":"a8mbrTVtivvEIBm6Tx/Vf7llR2UrXV353hBV1+uy2/Gb+/dzm8FgUMudBqZdeMAi8NASXQYoLSuVXwNImtB9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ff102aa823de922dae5322af0629a05b8dc41e11b1794a044ca33ab3380e5d4","last_reissued_at":"2026-07-05T08:58:46.885399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:46.885399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feiyu Pan, Hao Fang, Runmin Cong, Wei Zhang, Xiankai Lu","submitted_at":"2024-08-19T16:13:14Z","abstract_excerpt":"Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame. Recently, Segment Anything Model 2 (SAM 2) is proposed, which is a foundation model towards solving promptable visual segmentation in images and videos. SAM 2 builds a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. SAM 2 is a simple transformer architecture with streaming memory for real-time video processing, which trained on the date provides strong "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10125","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/2408.10125/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":"2408.10125","created_at":"2026-07-05T08:58:46.885454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10125v2","created_at":"2026-07-05T08:58:46.885454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10125","created_at":"2026-07-05T08:58:46.885454+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7YQFKUCHXUS","created_at":"2026-07-05T08:58:46.885454+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7YQFKUCHXUSFWXF","created_at":"2026-07-05T08:58:46.885454+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7YQFKUC","created_at":"2026-07-05T08:58:46.885454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10950","citing_title":"Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW","json":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW.json","graph_json":"https://pith.science/api/pith-number/D7YQFKUCHXUSFWXFGIVPAYU2AW/graph.json","events_json":"https://pith.science/api/pith-number/D7YQFKUCHXUSFWXFGIVPAYU2AW/events.json","paper":"https://pith.science/paper/D7YQFKUC"},"agent_actions":{"view_html":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW","download_json":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW.json","view_paper":"https://pith.science/paper/D7YQFKUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10125&json=true","fetch_graph":"https://pith.science/api/pith-number/D7YQFKUCHXUSFWXFGIVPAYU2AW/graph.json","fetch_events":"https://pith.science/api/pith-number/D7YQFKUCHXUSFWXFGIVPAYU2AW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW/action/storage_attestation","attest_author":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW/action/author_attestation","sign_citation":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW/action/citation_signature","submit_replication":"https://pith.science/pith/D7YQFKUCHXUSFWXFGIVPAYU2AW/action/replication_record"}},"created_at":"2026-07-05T08:58:46.885454+00:00","updated_at":"2026-07-05T08:58:46.885454+00:00"}