{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZF5K747CEV662QBA3NYSUPXRWM","short_pith_number":"pith:ZF5K747C","canonical_record":{"source":{"id":"2507.19875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T09:05:12Z","cross_cats_sorted":[],"title_canon_sha256":"e93c100d2c2aeea0d25f766010e59ba7cd97eeafb9675c3af8bb0df41bd40d31","abstract_canon_sha256":"d8aa97b666b64273750b0a3d0a4c62b9b85f0fa42e512c349ee2b56f3753bc58"},"schema_version":"1.0"},"canonical_sha256":"c97aaff3e2257ded4020db712a3ef1b33dbe7798eb6c7cfaf5745839d5481374","source":{"kind":"arxiv","id":"2507.19875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19875","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19875v1","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19875","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZF5K747CEV66","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZF5K747CEV662QBA","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZF5K747C","created_at":"2026-07-05T11:43:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZF5K747CEV662QBA3NYSUPXRWM","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T09:05:12Z","cross_cats_sorted":[],"title_canon_sha256":"e93c100d2c2aeea0d25f766010e59ba7cd97eeafb9675c3af8bb0df41bd40d31","abstract_canon_sha256":"d8aa97b666b64273750b0a3d0a4c62b9b85f0fa42e512c349ee2b56f3753bc58"},"schema_version":"1.0"},"canonical_sha256":"c97aaff3e2257ded4020db712a3ef1b33dbe7798eb6c7cfaf5745839d5481374","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:44.139051Z","signature_b64":"ZX522CFkqvAd5xbo7FdNDoLeYBREUP02QFEhX60ZDyOzx64QmC5f5RPy0vRkwssVGJRtRabGNym5BWXry1zaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c97aaff3e2257ded4020db712a3ef1b33dbe7798eb6c7cfaf5745839d5481374","last_reissued_at":"2026-07-05T11:43:44.138492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:44.138492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19875","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ClFR2fpXSL1x471BipWiUCXAe6r21d5OmRgzFjaSL9xPoZciTs0z4n0Oq/bwBB2CS98s2Ui6+Zk4aIZb1PIQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:53:14.056635Z"},"content_sha256":"b865a2ad8bc702acd47533e72f866bca850abdcb240e709c799de61b82c52b9e","schema_version":"1.0","event_id":"sha256:b865a2ad8bc702acd47533e72f866bca850abdcb240e709c799de61b82c52b9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZF5K747CEV662QBA3NYSUPXRWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"D. Zhang, J. Zhang, K. Huang, M. Wu, S. Hu, X. Chen, X. Feng, X. Li","submitted_at":"2025-07-26T09:05:12Z","abstract_excerpt":"Vision-language tracking aims to locate the target object in the video sequence using a template patch and a language description provided in the initial frame. To achieve robust tracking, especially in complex long-term scenarios that reflect real-world conditions as recently highlighted by MGIT, it is essential not only to characterize the target features but also to utilize the context features related to the target. However, the visual and textual target-context cues derived from the initial prompts generally align only with the initial target state. Due to their dynamic nature, target sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19875","kind":"arxiv","version":1},"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/2507.19875/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":"2026-07-05T11:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGnzXkE8s61UaV04JAEF33aJK3KbB+iUXj7D1j91F3czckh+p735cEZaZ07QWnO/Bw2RUhUc9CoC46aMcOfzCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:53:14.057149Z"},"content_sha256":"92b1c6e009f1f3fce47c1aefcae12ff54d3614b6227c5a00706f4be651e00c19","schema_version":"1.0","event_id":"sha256:92b1c6e009f1f3fce47c1aefcae12ff54d3614b6227c5a00706f4be651e00c19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZF5K747CEV662QBA3NYSUPXRWM/bundle.json","state_url":"https://pith.science/pith/ZF5K747CEV662QBA3NYSUPXRWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZF5K747CEV662QBA3NYSUPXRWM/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":"2026-08-05T09:53:14Z","links":{"resolver":"https://pith.science/pith/ZF5K747CEV662QBA3NYSUPXRWM","bundle":"https://pith.science/pith/ZF5K747CEV662QBA3NYSUPXRWM/bundle.json","state":"https://pith.science/pith/ZF5K747CEV662QBA3NYSUPXRWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZF5K747CEV662QBA3NYSUPXRWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZF5K747CEV662QBA3NYSUPXRWM","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":"d8aa97b666b64273750b0a3d0a4c62b9b85f0fa42e512c349ee2b56f3753bc58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T09:05:12Z","title_canon_sha256":"e93c100d2c2aeea0d25f766010e59ba7cd97eeafb9675c3af8bb0df41bd40d31"},"schema_version":"1.0","source":{"id":"2507.19875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19875","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19875v1","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19875","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZF5K747CEV66","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZF5K747CEV662QBA","created_at":"2026-07-05T11:43:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZF5K747C","created_at":"2026-07-05T11:43:44Z"}],"graph_snapshots":[{"event_id":"sha256:92b1c6e009f1f3fce47c1aefcae12ff54d3614b6227c5a00706f4be651e00c19","target":"graph","created_at":"2026-07-05T11:43:44Z","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/2507.19875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language tracking aims to locate the target object in the video sequence using a template patch and a language description provided in the initial frame. To achieve robust tracking, especially in complex long-term scenarios that reflect real-world conditions as recently highlighted by MGIT, it is essential not only to characterize the target features but also to utilize the context features related to the target. However, the visual and textual target-context cues derived from the initial prompts generally align only with the initial target state. Due to their dynamic nature, target sta","authors_text":"D. Zhang, J. Zhang, K. Huang, M. Wu, S. Hu, X. Chen, X. Feng, X. Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T09:05:12Z","title":"ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19875","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:b865a2ad8bc702acd47533e72f866bca850abdcb240e709c799de61b82c52b9e","target":"record","created_at":"2026-07-05T11:43:44Z","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":"d8aa97b666b64273750b0a3d0a4c62b9b85f0fa42e512c349ee2b56f3753bc58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T09:05:12Z","title_canon_sha256":"e93c100d2c2aeea0d25f766010e59ba7cd97eeafb9675c3af8bb0df41bd40d31"},"schema_version":"1.0","source":{"id":"2507.19875","kind":"arxiv","version":1}},"canonical_sha256":"c97aaff3e2257ded4020db712a3ef1b33dbe7798eb6c7cfaf5745839d5481374","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c97aaff3e2257ded4020db712a3ef1b33dbe7798eb6c7cfaf5745839d5481374","first_computed_at":"2026-07-05T11:43:44.138492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:44.138492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZX522CFkqvAd5xbo7FdNDoLeYBREUP02QFEhX60ZDyOzx64QmC5f5RPy0vRkwssVGJRtRabGNym5BWXry1zaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:44.139051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b865a2ad8bc702acd47533e72f866bca850abdcb240e709c799de61b82c52b9e","sha256:92b1c6e009f1f3fce47c1aefcae12ff54d3614b6227c5a00706f4be651e00c19"],"state_sha256":"26fa9070f21403ffb3567fea33835f230e9d9105432d6ca45ba38d6ed893d011"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9vAZkn6Qksm/0ku3qdhc5wtoD588dDpWgN4OMAzMl8Gai2UZdNoqYtMyDtyT7aoIXZWSJM6NRHI6Y46O85N0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:53:14.064027Z","bundle_sha256":"7e6d579b7884bc2721043e45e3d23b0bccff16ff8506d47021ded77fcfe6d5d9"}}