{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZXP62IQIFJDEO6STT7VKKRCVC3","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":"d0516aa62e73901908fe2481d7420eb4ea47012e96dfb6141f3226cd127991b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T03:54:22Z","title_canon_sha256":"e4622d1260831f93ecc246b676da5a95ee180f547a54143ffeb41e917f69c0c5"},"schema_version":"1.0","source":{"id":"2403.05021","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.05021","created_at":"2026-07-05T08:49:31Z"},{"alias_kind":"arxiv_version","alias_value":"2403.05021v4","created_at":"2026-07-05T08:49:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05021","created_at":"2026-07-05T08:49:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZXP62IQIFJDE","created_at":"2026-07-05T08:49:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZXP62IQIFJDEO6ST","created_at":"2026-07-05T08:49:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZXP62IQI","created_at":"2026-07-05T08:49:31Z"}],"graph_snapshots":[{"event_id":"sha256:d6964fba31eefa7aaf07eabb9f2a2ba9df7305211f417e83d4d16de474694791","target":"graph","created_at":"2026-07-05T08:49:31Z","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/2403.05021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current multi-object tracking (MOT) aims to predict trajectories of targets (i.e., ''where'') in videos. Yet, knowing merely ''where'' is insufficient in many crucial applications. In comparison, semantic understanding such as fine-grained behaviors, interactions, and overall summarized captions (i.e., ''what'') from videos, associated with ''where'', is highly-desired for comprehensive video analysis. Thus motivated, we introduce Semantic Multi-Object Tracking (SMOT), that aims to estimate object trajectories and meanwhile understand semantic details of associated trajectories including insta","authors_text":"Hao Wang, Heng Fan, Jiali Yao, Libo Zhang, Qin Li, Shaohua Dong, Xue Ma, Yunhao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T03:54:22Z","title":"Beyond MOT: Semantic Multi-Object Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05021","kind":"arxiv","version":4},"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":"sha256:08798c7a28fafb68d25b1f0acbd85cc1a195137d2e0671f12fc2ec9549261786","target":"record","created_at":"2026-07-05T08:49:31Z","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":"d0516aa62e73901908fe2481d7420eb4ea47012e96dfb6141f3226cd127991b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T03:54:22Z","title_canon_sha256":"e4622d1260831f93ecc246b676da5a95ee180f547a54143ffeb41e917f69c0c5"},"schema_version":"1.0","source":{"id":"2403.05021","kind":"arxiv","version":4}},"canonical_sha256":"cddfed22082a46477a539feaa5445516e4a3a30775f79beaa3c44c649bc2c0da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cddfed22082a46477a539feaa5445516e4a3a30775f79beaa3c44c649bc2c0da","first_computed_at":"2026-07-05T08:49:31.282571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:31.282571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dwj8rGzVUm96UYRt2o71qn0ZRxk3PMHGwapzq38PqyO2AyegRWLe1ZuRI4XEuOKR4DSoEdDFnoimVATt9w3EDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:31.283029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.05021","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08798c7a28fafb68d25b1f0acbd85cc1a195137d2e0671f12fc2ec9549261786","sha256:d6964fba31eefa7aaf07eabb9f2a2ba9df7305211f417e83d4d16de474694791"],"state_sha256":"eec45aa827ba094bc7f5886e39bd4d2b4b81afe0e53ee877d8fac241a1ad0b3d"}