{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:STKJ6KZDPLF7GU6VQSB3MGR4XR","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":"e69f0c8afafce2d042bda8c27d7bba5e866ea4d2b7187a45e2a46b43803012b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:56:29Z","title_canon_sha256":"7c4560c3977b99f49fa56a1881dc0ce17d5c49537a654af2ea6faa61b08a6ef6"},"schema_version":"1.0","source":{"id":"2304.14394","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14394","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14394v3","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14394","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"STKJ6KZDPLF7","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"STKJ6KZDPLF7GU6V","created_at":"2026-07-05T08:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"STKJ6KZD","created_at":"2026-07-05T08:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:b51606d3e731012ec5c961a91c2d5bf24d93952599cc1f2677598772e5877e3a","target":"graph","created_at":"2026-07-05T08:00:59Z","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/2304.14394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generation task, forecasting object bounding boxes in an autoregressive manner. This differs from previous trackers, which depend on the design of intricate head networks, such as classification and regression heads. SeqTrack employs a basic encoder-decoder transformer architecture. The encoder utilizes a bidirectional transformer for feature extraction, while the decoder generates boun","authors_text":"Ben Kang, Dong Wang, Houwen Peng, Huchuan Lu, Jiawen Zhu, Xin Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:56:29Z","title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14394","kind":"arxiv","version":3},"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:ff09f9923b849fdd09b04b4716445f00c8d842122e119f977e924c7b8b6c9f11","target":"record","created_at":"2026-07-05T08:00:59Z","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":"e69f0c8afafce2d042bda8c27d7bba5e866ea4d2b7187a45e2a46b43803012b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:56:29Z","title_canon_sha256":"7c4560c3977b99f49fa56a1881dc0ce17d5c49537a654af2ea6faa61b08a6ef6"},"schema_version":"1.0","source":{"id":"2304.14394","kind":"arxiv","version":3}},"canonical_sha256":"94d49f2b237acbf353d58483b61a3cbc61147c13b17c4995e358fd8fd0e5c26f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94d49f2b237acbf353d58483b61a3cbc61147c13b17c4995e358fd8fd0e5c26f","first_computed_at":"2026-07-05T08:00:59.236486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:59.236486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3POBrpfO9fjbDxtal9Nh11j3mfRnlxRy1GpwDV9sy19Fj7XAR0EDEQiHU53KiE2VEwfveJZtp5kVdoAsDHRjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:59.236954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14394","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff09f9923b849fdd09b04b4716445f00c8d842122e119f977e924c7b8b6c9f11","sha256:b51606d3e731012ec5c961a91c2d5bf24d93952599cc1f2677598772e5877e3a"],"state_sha256":"2671f9e5410ea1d6f6e9ec816a8a4e624fdf64cf2e8ff7c8ea1defac9c13e986"}