{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SFUIQTKHFGIXZRLZYR3R3OKVBP","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":"965d7f384e65e0f0b960dbf72d725a90e7d1b7efaf320c06cfda0895aa24740c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T14:54:37Z","title_canon_sha256":"5a6a25f89f892dcf17aed9323e9830a8e85895a39dd9136bbcd737a04eabaa7f"},"schema_version":"1.0","source":{"id":"2409.08887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08887","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08887v1","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08887","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_12","alias_value":"SFUIQTKHFGIX","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_16","alias_value":"SFUIQTKHFGIXZRLZ","created_at":"2026-07-05T09:06:49Z"},{"alias_kind":"pith_short_8","alias_value":"SFUIQTKH","created_at":"2026-07-05T09:06:49Z"}],"graph_snapshots":[{"event_id":"sha256:54a99162c47cc797caf640d71370174351eaf4e21825fbacfca7aadb9c9dfa28","target":"graph","created_at":"2026-07-05T09:06:49Z","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/2409.08887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Language Tracking (VLT) enhances tracking by mitigating the limitations of relying solely on the visual modality, utilizing high-level semantic information through language. This integration of the language enables more advanced human-machine interaction. The essence of interaction is cognitive alignment, which typically requires multiple information exchanges, especially in the sequential decision-making process of VLT. However, current VLT benchmarks do not account for multi-round interactions during tracking. They provide only an initial text and bounding box (bbox) in the first fram","authors_text":"Dailing Zhang, Jing Zhang, Kaiqi Huang, Meiqi Wu, Shiyu Hu, Xiaokun Feng, Xuchen Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T14:54:37Z","title":"Visual Language Tracking with Multi-modal Interaction: A Robust Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08887","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":"sha256:43393506b304150fe908b87af5197aa3f3153c5aafb8c8e786f8ec94206b7d87","target":"record","created_at":"2026-07-05T09:06:49Z","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":"965d7f384e65e0f0b960dbf72d725a90e7d1b7efaf320c06cfda0895aa24740c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T14:54:37Z","title_canon_sha256":"5a6a25f89f892dcf17aed9323e9830a8e85895a39dd9136bbcd737a04eabaa7f"},"schema_version":"1.0","source":{"id":"2409.08887","kind":"arxiv","version":1}},"canonical_sha256":"9168884d4729917cc579c4771db9550bf75427e3d95ed36995c66c620dd42465","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9168884d4729917cc579c4771db9550bf75427e3d95ed36995c66c620dd42465","first_computed_at":"2026-07-05T09:06:49.311703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:49.311703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Swnwf5jMqg5BtykWPnfnzkjmEgO+uWdtNHe4Vo5Iunux1WvTcwczyb/fF4S5EPOIvRMW7HNFVrwlQzOUOr3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:49.312151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43393506b304150fe908b87af5197aa3f3153c5aafb8c8e786f8ec94206b7d87","sha256:54a99162c47cc797caf640d71370174351eaf4e21825fbacfca7aadb9c9dfa28"],"state_sha256":"c2c51717f97c6c228dd47e46ae8fb678f8d88ac76264b681c908e367aba2f122"}