{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YIZ5K3WCH4BEDLKMARGLN4DAXU","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":"0b9884a355d8f36bb8d094c0c0a3eba488ccae33120e6b512698447f45186eb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T03:05:50Z","title_canon_sha256":"cd11328836e2f4db25dfe2d794aba9bb01e4b0b07b9ec73753d009468f54e1e7"},"schema_version":"1.0","source":{"id":"2406.06908","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06908","created_at":"2026-07-05T08:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06908v1","created_at":"2026-07-05T08:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06908","created_at":"2026-07-05T08:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"YIZ5K3WCH4BE","created_at":"2026-07-05T08:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"YIZ5K3WCH4BEDLKM","created_at":"2026-07-05T08:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"YIZ5K3WC","created_at":"2026-07-05T08:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:589cb3c1cf35b24b67eee0c119fbcc9d864a17979141f2d21e4037dc677188eb","target":"graph","created_at":"2026-07-05T08:30:15Z","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/2406.06908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video instance segmentation requires classifying, segmenting, and tracking every object across video frames. Unlike existing approaches that rely on masks, boxes, or category labels, we propose UVIS, a novel Unsupervised Video Instance Segmentation (UVIS) framework that can perform video instance segmentation without any video annotations or dense label-based pretraining. Our key insight comes from leveraging the dense shape prior from the self-supervised vision foundation model DINO and the openset recognition ability from the image-caption supervised vision-language model CLIP. Our UVIS fram","authors_text":"Abhinav Shrivastava, Kamal Gupta, Sai Saketh Rambhatla, Saksham Suri, Ser-Nam Lim, Shuaiyi Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T03:05:50Z","title":"UVIS: Unsupervised Video Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06908","kind":"arxiv","version":1},"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:b1e2f89ec0ce62458987d05ada19699a1bb881ccfb6b8364c208277624175179","target":"record","created_at":"2026-07-05T08:30:15Z","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":"0b9884a355d8f36bb8d094c0c0a3eba488ccae33120e6b512698447f45186eb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T03:05:50Z","title_canon_sha256":"cd11328836e2f4db25dfe2d794aba9bb01e4b0b07b9ec73753d009468f54e1e7"},"schema_version":"1.0","source":{"id":"2406.06908","kind":"arxiv","version":1}},"canonical_sha256":"c233d56ec23f0241ad4c044cb6f060bd1b741c71675900ef61ee8b0a840a72ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c233d56ec23f0241ad4c044cb6f060bd1b741c71675900ef61ee8b0a840a72ba","first_computed_at":"2026-07-05T08:30:15.292876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:15.292876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m4HEj4iWNpv+/9mJp3lI8W0Bg79FKSB/dlORSicPdP9GVLAifHAzIDKa11zVvlDlLtx4z+KhBSSo1nySNYSpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:15.293362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06908","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1e2f89ec0ce62458987d05ada19699a1bb881ccfb6b8364c208277624175179","sha256:589cb3c1cf35b24b67eee0c119fbcc9d864a17979141f2d21e4037dc677188eb"],"state_sha256":"6365e73f0d661a30dd7183fcb471b6876c885f6a85e02eb670851ef024935b35"}