{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UIMMWXDHMCU5EJVU4IZRFIFMJL","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":"4816fb60393b60a255dc023d5b60154d18f5eec4718fa1d392f4d8120732a196","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T11:48:07Z","title_canon_sha256":"5e0ad4f99d5fca98b6334173a95d9857a9b33d46387e8ddd0a1614d130bf0836"},"schema_version":"1.0","source":{"id":"2303.15904","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15904","created_at":"2026-07-05T05:55:29Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15904v1","created_at":"2026-07-05T05:55:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15904","created_at":"2026-07-05T05:55:29Z"},{"alias_kind":"pith_short_12","alias_value":"UIMMWXDHMCU5","created_at":"2026-07-05T05:55:29Z"},{"alias_kind":"pith_short_16","alias_value":"UIMMWXDHMCU5EJVU","created_at":"2026-07-05T05:55:29Z"},{"alias_kind":"pith_short_8","alias_value":"UIMMWXDH","created_at":"2026-07-05T05:55:29Z"}],"graph_snapshots":[{"event_id":"sha256:94ea29d381b5ef1578d0b3d129388821e7eccd41b2f7834b3c8dfb7583b2ffa9","target":"graph","created_at":"2026-07-05T05:55:29Z","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/2303.15904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advancement in Video Instance Segmentation (VIS) has largely been driven by the use of deeper and increasingly data-hungry transformer-based models. However, video masks are tedious and expensive to annotate, limiting the scale and diversity of existing VIS datasets. In this work, we aim to remove the mask-annotation requirement. We propose MaskFreeVIS, achieving highly competitive VIS performance, while only using bounding box annotations for the object state. We leverage the rich temporal mask consistency constraints in videos by introducing the Temporal KNN-patch Loss (TK-Loss), ","authors_text":"Chi-Keung Tang, Fisher Yu, Henghui Ding, Lei Ke, Martin Danelljan, Yu-Wing Tai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T11:48:07Z","title":"Mask-Free Video Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15904","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:cdf0c12fe8b0da4e548c998a6f035883637e6c3f3dc43b5764ac103ea69646a4","target":"record","created_at":"2026-07-05T05:55:29Z","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":"4816fb60393b60a255dc023d5b60154d18f5eec4718fa1d392f4d8120732a196","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T11:48:07Z","title_canon_sha256":"5e0ad4f99d5fca98b6334173a95d9857a9b33d46387e8ddd0a1614d130bf0836"},"schema_version":"1.0","source":{"id":"2303.15904","kind":"arxiv","version":1}},"canonical_sha256":"a218cb5c6760a9d226b4e23312a0ac4ad4bc3b590c279fbd74223c4f40f02a2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a218cb5c6760a9d226b4e23312a0ac4ad4bc3b590c279fbd74223c4f40f02a2a","first_computed_at":"2026-07-05T05:55:29.726368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:29.726368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"33fl8XKK6SxCS4bYlYI4MSrNSuMv0zDHPOSw/Fz6ky/7uWAEPgFIW+sGBv9UKwIW7hgFb1xesxBKa3NfVeSvBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:29.726800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15904","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdf0c12fe8b0da4e548c998a6f035883637e6c3f3dc43b5764ac103ea69646a4","sha256:94ea29d381b5ef1578d0b3d129388821e7eccd41b2f7834b3c8dfb7583b2ffa9"],"state_sha256":"df1fe3a9d88bbf64acf6b315a9ab5ca22660682253556391b489b9dd5895b7b0"}