{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RD4D44XSSQVZ6D7HFAHO3ZGWAL","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":"2b9f9cd67e849cdae027dec278aeb726bdd7a823b0f63507b829384f4fd64849","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T11:25:59Z","title_canon_sha256":"5e2f08ef07ab3f6d65e7cd2c29be452d85ad9f8e8a61f67c488e6356396b4252"},"schema_version":"1.0","source":{"id":"2305.16835","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16835","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16835v3","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16835","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"RD4D44XSSQVZ","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_16","alias_value":"RD4D44XSSQVZ6D7H","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_8","alias_value":"RD4D44XS","created_at":"2026-07-05T08:56:12Z"}],"graph_snapshots":[{"event_id":"sha256:aab8dbd91b9ddc71912c746c43b7a4cf30b9a381ae9fca9574f4a9fbbff31340","target":"graph","created_at":"2026-07-05T08:56:12Z","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/2305.16835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary Video Instance Segmentation (OpenVIS) can simultaneously detect, segment, and track arbitrary object categories in a video, without being constrained to categories seen during training. In this work, we propose InstFormer, a carefully designed framework for the OpenVIS task that achieves powerful open-vocabulary capabilities through lightweight fine-tuning with limited-category data. InstFormer begins with the open-world mask proposal network, encouraged to propose all potential instance class-agnostic masks by the contrastive instance margin loss. Next, we introduce InstCLIP, ","authors_text":"Peiyang He, Pinxue Guo, Tianjun Xiao, Tony Huang, Wenqiang Zhang, Xuefeng Liu, Zhaoyu Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T11:25:59Z","title":"OpenVIS: Open-vocabulary Video Instance Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16835","kind":"arxiv","version":3},"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:fba7928c78f1cd3a8b87d5a87a9043341350c66865f6f82d9830c42f6976946f","target":"record","created_at":"2026-07-05T08:56:12Z","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":"2b9f9cd67e849cdae027dec278aeb726bdd7a823b0f63507b829384f4fd64849","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T11:25:59Z","title_canon_sha256":"5e2f08ef07ab3f6d65e7cd2c29be452d85ad9f8e8a61f67c488e6356396b4252"},"schema_version":"1.0","source":{"id":"2305.16835","kind":"arxiv","version":3}},"canonical_sha256":"88f83e72f2942b9f0fe7280eede4d602f42e9bd2abc003adf662d10b9b0acd07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88f83e72f2942b9f0fe7280eede4d602f42e9bd2abc003adf662d10b9b0acd07","first_computed_at":"2026-07-05T08:56:12.745536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:12.745536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GxK3JSifotekL3Rc5tw1mcobfnSKixIHrn0I3nlYcPhOmgMvuMEzFyD5XpDYSmewuZzZbDhh2/F+X/byPi2MCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:12.746041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16835","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fba7928c78f1cd3a8b87d5a87a9043341350c66865f6f82d9830c42f6976946f","sha256:aab8dbd91b9ddc71912c746c43b7a4cf30b9a381ae9fca9574f4a9fbbff31340"],"state_sha256":"e7188bf390bb0d5a358098da3275baa8305063fbc30dd31c9f3e3dbe8dfcd7ae"}