{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YU4EOBSBB4ZZDQJI2IV5TEVJWY","short_pith_number":"pith:YU4EOBSB","canonical_record":{"source":{"id":"2410.02492","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T13:57:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dd40b09617b25270f5be179c4db25b42c4ff95e21ce610248eec3372d5326511","abstract_canon_sha256":"98199596ec9c9b420d0b5d8a42e83591bf934a3b3b49e4cf378afbfdde29208e"},"schema_version":"1.0"},"canonical_sha256":"c5384706410f3391c128d22bd992a9b607f21b2e05f01fb318626b19b464308f","source":{"kind":"arxiv","id":"2410.02492","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02492","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02492v2","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02492","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"YU4EOBSBB4ZZ","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"YU4EOBSBB4ZZDQJI","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"YU4EOBSB","created_at":"2026-07-05T09:17:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YU4EOBSBB4ZZDQJI2IV5TEVJWY","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02492","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T13:57:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dd40b09617b25270f5be179c4db25b42c4ff95e21ce610248eec3372d5326511","abstract_canon_sha256":"98199596ec9c9b420d0b5d8a42e83591bf934a3b3b49e4cf378afbfdde29208e"},"schema_version":"1.0"},"canonical_sha256":"c5384706410f3391c128d22bd992a9b607f21b2e05f01fb318626b19b464308f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:50.601146Z","signature_b64":"5188L6sxvm1EprZt4JfpZ5wmlEqTncLVaIMXwu4x7KDsdqEyIvDZm1MJtqhNFxZgFwagE1QmHPjJQwKYk9YrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5384706410f3391c128d22bd992a9b607f21b2e05f01fb318626b19b464308f","last_reissued_at":"2026-07-05T09:17:50.600671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:50.600671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02492","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"moNnhov9yNbRJC23dCB9YFWnTJ0fINrNnJP9zx7nTa8tqVS3H6ukcIPUToVfQzbSOpkP6cgALIS+6uc45Ql2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:35:00.855929Z"},"content_sha256":"a7442071244ed3bc4bf78affc8b2791994c5e09c3854dd62882c95d62134b821","schema_version":"1.0","event_id":"sha256:a7442071244ed3bc4bf78affc8b2791994c5e09c3854dd62882c95d62134b821"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YU4EOBSBB4ZZDQJI2IV5TEVJWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dailing Zhang, Jing Zhang, Kaiqi Huang, Meiqi Wu, Shiyu Hu, Xiaokun Feng, Xuchen Li","submitted_at":"2024-10-03T13:57:07Z","abstract_excerpt":"Visual language tracking (VLT) has emerged as a cutting-edge research area, harnessing linguistic data to enhance algorithms with multi-modal inputs and broadening the scope of traditional single object tracking (SOT) to encompass video understanding applications. Despite this, most VLT benchmarks still depend on succinct, human-annotated text descriptions for each video. These descriptions often fall short in capturing the nuances of video content dynamics and lack stylistic variety in language, constrained by their uniform level of detail and a fixed annotation frequency. As a result, algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02492","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.02492/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7TNXXrqaxAyGqJ2cLF1xVlVNJQa+dnFIpkcRrZPgZ0+jz+dVBFj0bfHcppynX35JwIsCE5IjLxAF847szX4PCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:35:00.856460Z"},"content_sha256":"544e233b1f0a2074f0c2463094ab88cc5456f28982bb4d6199b286b877a290a5","schema_version":"1.0","event_id":"sha256:544e233b1f0a2074f0c2463094ab88cc5456f28982bb4d6199b286b877a290a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YU4EOBSBB4ZZDQJI2IV5TEVJWY/bundle.json","state_url":"https://pith.science/pith/YU4EOBSBB4ZZDQJI2IV5TEVJWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YU4EOBSBB4ZZDQJI2IV5TEVJWY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T20:35:00Z","links":{"resolver":"https://pith.science/pith/YU4EOBSBB4ZZDQJI2IV5TEVJWY","bundle":"https://pith.science/pith/YU4EOBSBB4ZZDQJI2IV5TEVJWY/bundle.json","state":"https://pith.science/pith/YU4EOBSBB4ZZDQJI2IV5TEVJWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YU4EOBSBB4ZZDQJI2IV5TEVJWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YU4EOBSBB4ZZDQJI2IV5TEVJWY","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":"98199596ec9c9b420d0b5d8a42e83591bf934a3b3b49e4cf378afbfdde29208e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T13:57:07Z","title_canon_sha256":"dd40b09617b25270f5be179c4db25b42c4ff95e21ce610248eec3372d5326511"},"schema_version":"1.0","source":{"id":"2410.02492","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02492","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02492v2","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02492","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"YU4EOBSBB4ZZ","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"YU4EOBSBB4ZZDQJI","created_at":"2026-07-05T09:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"YU4EOBSB","created_at":"2026-07-05T09:17:50Z"}],"graph_snapshots":[{"event_id":"sha256:544e233b1f0a2074f0c2463094ab88cc5456f28982bb4d6199b286b877a290a5","target":"graph","created_at":"2026-07-05T09:17:50Z","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/2410.02492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual language tracking (VLT) has emerged as a cutting-edge research area, harnessing linguistic data to enhance algorithms with multi-modal inputs and broadening the scope of traditional single object tracking (SOT) to encompass video understanding applications. Despite this, most VLT benchmarks still depend on succinct, human-annotated text descriptions for each video. These descriptions often fall short in capturing the nuances of video content dynamics and lack stylistic variety in language, constrained by their uniform level of detail and a fixed annotation frequency. As a result, algori","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":"2024-10-03T13:57:07Z","title":"DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02492","kind":"arxiv","version":2},"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:a7442071244ed3bc4bf78affc8b2791994c5e09c3854dd62882c95d62134b821","target":"record","created_at":"2026-07-05T09:17:50Z","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":"98199596ec9c9b420d0b5d8a42e83591bf934a3b3b49e4cf378afbfdde29208e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T13:57:07Z","title_canon_sha256":"dd40b09617b25270f5be179c4db25b42c4ff95e21ce610248eec3372d5326511"},"schema_version":"1.0","source":{"id":"2410.02492","kind":"arxiv","version":2}},"canonical_sha256":"c5384706410f3391c128d22bd992a9b607f21b2e05f01fb318626b19b464308f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5384706410f3391c128d22bd992a9b607f21b2e05f01fb318626b19b464308f","first_computed_at":"2026-07-05T09:17:50.600671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:50.600671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5188L6sxvm1EprZt4JfpZ5wmlEqTncLVaIMXwu4x7KDsdqEyIvDZm1MJtqhNFxZgFwagE1QmHPjJQwKYk9YrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:50.601146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02492","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7442071244ed3bc4bf78affc8b2791994c5e09c3854dd62882c95d62134b821","sha256:544e233b1f0a2074f0c2463094ab88cc5456f28982bb4d6199b286b877a290a5"],"state_sha256":"695f388264e45601750987664810f210d95102f7a72d725ee91899d187ea8d68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jLtVgMFrlTBt+go3QqHgCsiSo8lDyYCsgyPyaK/0RIRCGsFzVQ9Rk/XJjpfT1BqBH8USOlcBnASvg8ANlUF2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:35:00.867747Z","bundle_sha256":"933df9417ceb014c674fae3b06990043d1fe174e5cc71484fb400983e2348a88"}}