{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OHGDPP3BSCG6RI6XYKARZXB37E","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":"c3e61c1ec19f3f25f6cf9bd91b2fd1713cedb3e1d96e65c1f48e336d2c24ff21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T12:18:12Z","title_canon_sha256":"da86b6f1137d22eba7a560d741886d8ab28c159b4f39d1ea5c8eb17688341b4f"},"schema_version":"1.0","source":{"id":"2601.06550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06550","created_at":"2026-07-07T03:18:52Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06550v3","created_at":"2026-07-07T03:18:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06550","created_at":"2026-07-07T03:18:52Z"},{"alias_kind":"pith_short_12","alias_value":"OHGDPP3BSCG6","created_at":"2026-07-07T03:18:52Z"},{"alias_kind":"pith_short_16","alias_value":"OHGDPP3BSCG6RI6X","created_at":"2026-07-07T03:18:52Z"},{"alias_kind":"pith_short_8","alias_value":"OHGDPP3B","created_at":"2026-07-07T03:18:52Z"}],"graph_snapshots":[{"event_id":"sha256:683787514af09773505db925e354fabc56e452f5839f392bac0c62d4b851ca57","target":"graph","created_at":"2026-07-07T03:18:52Z","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/2601.06550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic Multi-Object Tracking (SMOT) is evolving from purely geometric localization toward comprehensive video understanding. However, existing paradigms predominantly rely on closed-set interaction tags and fragmented perception pipelines, creating a bottleneck that prevents the full utilization of Multi-modal Large Language Models (MLLMs) for dynamic scenes. In this paper, we elevate SMOT from rigid classification to an open-ended generative reasoning task. To support this paradigm shift, we introduce Grand-SMOT, a large-scale benchmark featuring high-density, dual-stream narratives. This d","authors_text":"Dingwen Zhang, Di Wu, Feng Yang, Jinwen Yu, Pan Liao, Wang Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T12:18:12Z","title":"Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06550","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":"sha256:617108baa5c7f81df0f0bd915606ea3a23377395f68b5acb9d8dcb4c63b3435a","target":"record","created_at":"2026-07-07T03:18:52Z","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":"c3e61c1ec19f3f25f6cf9bd91b2fd1713cedb3e1d96e65c1f48e336d2c24ff21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T12:18:12Z","title_canon_sha256":"da86b6f1137d22eba7a560d741886d8ab28c159b4f39d1ea5c8eb17688341b4f"},"schema_version":"1.0","source":{"id":"2601.06550","kind":"arxiv","version":3}},"canonical_sha256":"71cc37bf61908de8a3d7c2811cdc3bf9283364748514d02bf47a28a7800981ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71cc37bf61908de8a3d7c2811cdc3bf9283364748514d02bf47a28a7800981ad","first_computed_at":"2026-07-07T03:18:52.275939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T03:18:52.275939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QXjBRQFs/mks/XaGGRX6+LY0Afw9BWEff5DQlMZ5+9aPv8fvN8VlNwHCpGkcne+eYs+eK1lPT33Xm6tGwkBTBw==","signature_status":"signed_v1","signed_at":"2026-07-07T03:18:52.276434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.06550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:617108baa5c7f81df0f0bd915606ea3a23377395f68b5acb9d8dcb4c63b3435a","sha256:683787514af09773505db925e354fabc56e452f5839f392bac0c62d4b851ca57"],"state_sha256":"e32fe203936ef095710c9dd3edad9f48428bf623dee2707bc27fa5546ca94c04"}