{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KPFREK3BAEG6QB3O5GSUUBWQBN","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bb5dcce14b1d6176e83e7561ececb2c5510055a4416c1f08ccfc56bc78e2176f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T19:58:09Z","title_canon_sha256":"9cdac8a3a9696c4890306ad3981c22314e35ebed980308c24d245143ed2e7bf2"},"schema_version":"1.0","source":{"id":"2608.00847","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00847","created_at":"2026-08-04T01:55:15Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00847v1","created_at":"2026-08-04T01:55:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00847","created_at":"2026-08-04T01:55:15Z"},{"alias_kind":"pith_short_12","alias_value":"KPFREK3BAEG6","created_at":"2026-08-04T01:55:15Z"},{"alias_kind":"pith_short_16","alias_value":"KPFREK3BAEG6QB3O","created_at":"2026-08-04T01:55:15Z"},{"alias_kind":"pith_short_8","alias_value":"KPFREK3B","created_at":"2026-08-04T01:55:15Z"}],"graph_snapshots":[{"event_id":"sha256:7dfd5e300fe9c3b8b1b9f3e044aacc90cd080dd092f1c5c44f5e900abc50f587","target":"graph","created_at":"2026-08-04T01:55:15Z","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/2608.00847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most current visual trackers adopt a matching-based architecture trained exclusively on tracking datasets, whose performance gains depend heavily on the length of the input context, and have now reached a bottleneck. While high-performance tracking increasingly relies on foundation models, existing methods use them monolithically, adapting a foundation model into a tracker or modify a segmentation foundation model into a tracking pipeline, which fails to exploit complementary strengths. Matching-based trackers excel at instance-level correspondence but lack semantic discrimination and fine-gra","authors_text":"Qingjie Liu, Wenrui Cai, Yunhong Wang, Yuzhe Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T19:58:09Z","title":"Models as Tools: An Agentic Coordination Framework for Unified Multimodal Visual Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00847","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":"sha256:4f8d9ad1912c14ec2b89cf82c6d78ac201cbca53f2f868529bdad950428606ee","target":"record","created_at":"2026-08-04T01:55:15Z","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":"bb5dcce14b1d6176e83e7561ececb2c5510055a4416c1f08ccfc56bc78e2176f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T19:58:09Z","title_canon_sha256":"9cdac8a3a9696c4890306ad3981c22314e35ebed980308c24d245143ed2e7bf2"},"schema_version":"1.0","source":{"id":"2608.00847","kind":"arxiv","version":1}},"canonical_sha256":"53cb122b61010de8076ee9a54a06d00b5c3a075a9361a3e9d10b0e4783260ded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53cb122b61010de8076ee9a54a06d00b5c3a075a9361a3e9d10b0e4783260ded","first_computed_at":"2026-08-04T01:55:15.329397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:55:15.329397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i2mMdx58wjTUOMjdFP7fQtr45y1Ysom8yh4aEVkaSpz90/oWGL788SYm8qvE+ek1cBlZrRwo14INGnMw5mWWCw==","signature_status":"signed_v1","signed_at":"2026-08-04T01:55:15.330892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00847","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f8d9ad1912c14ec2b89cf82c6d78ac201cbca53f2f868529bdad950428606ee","sha256:7dfd5e300fe9c3b8b1b9f3e044aacc90cd080dd092f1c5c44f5e900abc50f587","sha256:b09d51c5435826d097dd563b39c8f700083267ad4fba08bbd590c342fd5274b7"],"state_sha256":"a6b859a2b30df098da45047d1943b4ff5df02bfd755f128e27a4418e1042f8a4"}