{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OLA2PBSQCMWFQHXY5VYQI5SYCT","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":"7e040144e7a0123aded77ab6bba1a8d3fc75d426f2fe0a6db43db55195bbab4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:56:10Z","title_canon_sha256":"94ac98ca6d9d58938c8c8715e3f615a8e4fca34a5d096c27a4bb0a3303abaee1"},"schema_version":"1.0","source":{"id":"2503.10616","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10616","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10616v3","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10616","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_12","alias_value":"OLA2PBSQCMWF","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_16","alias_value":"OLA2PBSQCMWFQHXY","created_at":"2026-07-05T10:41:21Z"},{"alias_kind":"pith_short_8","alias_value":"OLA2PBSQ","created_at":"2026-07-05T10:41:21Z"}],"graph_snapshots":[{"event_id":"sha256:61980a612c63ebcebefb6e2e73f6048c88f8439ab64412ceed0c99641f6e95c9","target":"graph","created_at":"2026-07-05T10:41:21Z","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/2503.10616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary multiple object tracking aims to generalize trackers to unseen categories during training, enabling their application across a variety of real-world scenarios. However, the existing open-vocabulary tracker is constrained by its framework structure, isolated frame-level perception, and insufficient modal interactions, which hinder its performance in open-vocabulary classification and tracking. In this paper, we propose OVTR (End-to-End Open-Vocabulary Multiple Object Tracking with TRansformer), the first end-to-end open-vocabulary tracker that models motion, appearance, and cate","authors_text":"En Yu, Jinyang Li, Sijia Chen, Wenbing Tao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:56:10Z","title":"OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10616","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:a568cbfd98eaefe86007c5f1ae6ae7aa5a72992dafc92fe37c86ac85fb9437d0","target":"record","created_at":"2026-07-05T10:41:21Z","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":"7e040144e7a0123aded77ab6bba1a8d3fc75d426f2fe0a6db43db55195bbab4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:56:10Z","title_canon_sha256":"94ac98ca6d9d58938c8c8715e3f615a8e4fca34a5d096c27a4bb0a3303abaee1"},"schema_version":"1.0","source":{"id":"2503.10616","kind":"arxiv","version":3}},"canonical_sha256":"72c1a78650132c581ef8ed7104765814e0c2619b83fba1c7881fec90a59f93b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72c1a78650132c581ef8ed7104765814e0c2619b83fba1c7881fec90a59f93b1","first_computed_at":"2026-07-05T10:41:21.544305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:21.544305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QDerd7yx2+kwYNum9SmHLD6jP5/+iZROFoNYl5PfjWMn64FJvjxYJyU9sc1qrotSGXJp9/e20WFvBR0KJQCIAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:21.544831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10616","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a568cbfd98eaefe86007c5f1ae6ae7aa5a72992dafc92fe37c86ac85fb9437d0","sha256:61980a612c63ebcebefb6e2e73f6048c88f8439ab64412ceed0c99641f6e95c9"],"state_sha256":"d2ca40529bfb69b4e8eb1b2e96f17f4625d6c72202fe0d001f2af08d8b263fb7"}