{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:STKJ6KZDPLF7GU6VQSB3MGR4XR","short_pith_number":"pith:STKJ6KZD","canonical_record":{"source":{"id":"2304.14394","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"7c4560c3977b99f49fa56a1881dc0ce17d5c49537a654af2ea6faa61b08a6ef6","abstract_canon_sha256":"e69f0c8afafce2d042bda8c27d7bba5e866ea4d2b7187a45e2a46b43803012b9"},"schema_version":"1.0"},"canonical_sha256":"94d49f2b237acbf353d58483b61a3cbc61147c13b17c4995e358fd8fd0e5c26f","source":{"kind":"arxiv","id":"2304.14394","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:STKJ6KZDPLF7GU6VQSB3MGR4XR","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14394","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T17:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"7c4560c3977b99f49fa56a1881dc0ce17d5c49537a654af2ea6faa61b08a6ef6","abstract_canon_sha256":"e69f0c8afafce2d042bda8c27d7bba5e866ea4d2b7187a45e2a46b43803012b9"},"schema_version":"1.0"},"canonical_sha256":"94d49f2b237acbf353d58483b61a3cbc61147c13b17c4995e358fd8fd0e5c26f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:59.236954Z","signature_b64":"3POBrpfO9fjbDxtal9Nh11j3mfRnlxRy1GpwDV9sy19Fj7XAR0EDEQiHU53KiE2VEwfveJZtp5kVdoAsDHRjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94d49f2b237acbf353d58483b61a3cbc61147c13b17c4995e358fd8fd0e5c26f","last_reissued_at":"2026-07-05T08:00:59.236486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:59.236486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14394","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FWaz++goMtH3tkRBUKxtJw76q39ter3bA72QtHcfnGFPR9owXcXJD0zNkt1EIEVUb4pbIyKs1tc+unDemgeyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:08:53.164202Z"},"content_sha256":"ff09f9923b849fdd09b04b4716445f00c8d842122e119f977e924c7b8b6c9f11","schema_version":"1.0","event_id":"sha256:ff09f9923b849fdd09b04b4716445f00c8d842122e119f977e924c7b8b6c9f11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:STKJ6KZDPLF7GU6VQSB3MGR4XR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Kang, Dong Wang, Houwen Peng, Huchuan Lu, Jiawen Zhu, Xin Chen","submitted_at":"2023-04-27T17:56:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14394","kind":"arxiv","version":3},"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/2304.14394/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":"2026-07-05T08:00:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAUqgupo8wI4JHHGNZTUf9e5FqKlKSpBKXyujR0GkJdfzm6jEdfCtc+IC8OitjMuKnTpjpA/ZJCIhh0kMzBGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:08:53.165127Z"},"content_sha256":"b51606d3e731012ec5c961a91c2d5bf24d93952599cc1f2677598772e5877e3a","schema_version":"1.0","event_id":"sha256:b51606d3e731012ec5c961a91c2d5bf24d93952599cc1f2677598772e5877e3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/STKJ6KZDPLF7GU6VQSB3MGR4XR/bundle.json","state_url":"https://pith.science/pith/STKJ6KZDPLF7GU6VQSB3MGR4XR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/STKJ6KZDPLF7GU6VQSB3MGR4XR/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":"2026-08-07T00:08:53Z","links":{"resolver":"https://pith.science/pith/STKJ6KZDPLF7GU6VQSB3MGR4XR","bundle":"https://pith.science/pith/STKJ6KZDPLF7GU6VQSB3MGR4XR/bundle.json","state":"https://pith.science/pith/STKJ6KZDPLF7GU6VQSB3MGR4XR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/STKJ6KZDPLF7GU6VQSB3MGR4XR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h0helcwFoxC9AeT50Q7r7RtilpRKF+Xe6HsskaO6eDg++ux9Shf8MlqaODRI9BRg/wmtYIlT8Dno1l3bvgjxBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:08:53.242121Z","bundle_sha256":"8f4eea6c36c4f6f19bf571ea890c08049cef52ffeda7420d8a80d9ad2c8de77f"}}