{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2XE64ERXFLQDJRZMHPM7PGPIQX","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":"9390e78b48bba929d850260696e6abeb70c017bc326985afbcbd0ae35583f380","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T13:20:54Z","title_canon_sha256":"4b0728a1055d33342bfff9dce54a894ae796a8add8c76c252329eea38b637d97"},"schema_version":"1.0","source":{"id":"2401.11228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11228","created_at":"2026-07-05T07:35:47Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11228v1","created_at":"2026-07-05T07:35:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11228","created_at":"2026-07-05T07:35:47Z"},{"alias_kind":"pith_short_12","alias_value":"2XE64ERXFLQD","created_at":"2026-07-05T07:35:47Z"},{"alias_kind":"pith_short_16","alias_value":"2XE64ERXFLQDJRZM","created_at":"2026-07-05T07:35:47Z"},{"alias_kind":"pith_short_8","alias_value":"2XE64ERX","created_at":"2026-07-05T07:35:47Z"}],"graph_snapshots":[{"event_id":"sha256:c00fa21ddf2d9b58a727aa16ba801ae8b881dae9e7cad5a558cecad79aa1b537","target":"graph","created_at":"2026-07-05T07:35:47Z","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/2401.11228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Single object tracking aims to locate the target object in a video sequence according to the state specified by different modal references, including the initial bounding box (BBOX), natural language (NL), or both (NL+BBOX). Due to the gap between different modalities, most existing trackers are designed for single or partial of these reference settings and overspecialize on the specific modality. Differently, we present a unified tracker called UVLTrack, which can simultaneously handle all three reference settings (BBOX, NL, NL+BBOX) with the same parameters. The proposed UVLTrack enjoys seve","authors_text":"Jinpeng Zhang, Mengxue Kang, Tianzhu Zhang, Wenfei Yang, Yinchao Ma, Yuyang Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T13:20:54Z","title":"Unifying Visual and Vision-Language Tracking via Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11228","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":"sha256:0538df8d8a2c48827460800c7856144eb06d065e5c6d4cdb41356faee81a5346","target":"record","created_at":"2026-07-05T07:35:47Z","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":"9390e78b48bba929d850260696e6abeb70c017bc326985afbcbd0ae35583f380","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-20T13:20:54Z","title_canon_sha256":"4b0728a1055d33342bfff9dce54a894ae796a8add8c76c252329eea38b637d97"},"schema_version":"1.0","source":{"id":"2401.11228","kind":"arxiv","version":1}},"canonical_sha256":"d5c9ee12372ae034c72c3bd9f799e885ff34a7823b9dabd82dce6037058cf9ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5c9ee12372ae034c72c3bd9f799e885ff34a7823b9dabd82dce6037058cf9ea","first_computed_at":"2026-07-05T07:35:47.609837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:47.609837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xoj/neUT5QadeQ7wxGQO4I0jF5s4aclym31Kz3J518ATH4ptsP2DIOWt7QwTOF3bEhHWBoOxjrdQwoMuQ5GACA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:47.610214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0538df8d8a2c48827460800c7856144eb06d065e5c6d4cdb41356faee81a5346","sha256:c00fa21ddf2d9b58a727aa16ba801ae8b881dae9e7cad5a558cecad79aa1b537"],"state_sha256":"486af820d88731b14bc308d8078bdad8b4eb3ad73bb701de973c4aa4c73baa1f"}