{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OHGDPP3BSCG6RI6XYKARZXB37E","short_pith_number":"pith:OHGDPP3B","schema_version":"1.0","canonical_sha256":"71cc37bf61908de8a3d7c2811cdc3bf9283364748514d02bf47a28a7800981ad","source":{"kind":"arxiv","id":"2601.06550","version":3},"attestation_state":"computed","paper":{"title":"Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dingwen Zhang, Di Wu, Feng Yang, Jinwen Yu, Pan Liao, Wang Zhao","submitted_at":"2026-01-10T12:18:12Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.06550","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-10T12:18:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da86b6f1137d22eba7a560d741886d8ab28c159b4f39d1ea5c8eb17688341b4f","abstract_canon_sha256":"c3e61c1ec19f3f25f6cf9bd91b2fd1713cedb3e1d96e65c1f48e336d2c24ff21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:18:52.276434Z","signature_b64":"QXjBRQFs/mks/XaGGRX6+LY0Afw9BWEff5DQlMZ5+9aPv8fvN8VlNwHCpGkcne+eYs+eK1lPT33Xm6tGwkBTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71cc37bf61908de8a3d7c2811cdc3bf9283364748514d02bf47a28a7800981ad","last_reissued_at":"2026-07-07T03:18:52.275939Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:18:52.275939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Semantic Multi-Object Tracking: A Large-Scale Benchmark and an MLLM-Driven Reasoning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dingwen Zhang, Di Wu, Feng Yang, Jinwen Yu, Pan Liao, Wang Zhao","submitted_at":"2026-01-10T12:18:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06550","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/2601.06550/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.06550","created_at":"2026-07-07T03:18:52.275996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.06550v3","created_at":"2026-07-07T03:18:52.275996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06550","created_at":"2026-07-07T03:18:52.275996+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHGDPP3BSCG6","created_at":"2026-07-07T03:18:52.275996+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHGDPP3BSCG6RI6X","created_at":"2026-07-07T03:18:52.275996+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHGDPP3B","created_at":"2026-07-07T03:18:52.275996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.29357","citing_title":"Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E","json":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E.json","graph_json":"https://pith.science/api/pith-number/OHGDPP3BSCG6RI6XYKARZXB37E/graph.json","events_json":"https://pith.science/api/pith-number/OHGDPP3BSCG6RI6XYKARZXB37E/events.json","paper":"https://pith.science/paper/OHGDPP3B"},"agent_actions":{"view_html":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E","download_json":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E.json","view_paper":"https://pith.science/paper/OHGDPP3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.06550&json=true","fetch_graph":"https://pith.science/api/pith-number/OHGDPP3BSCG6RI6XYKARZXB37E/graph.json","fetch_events":"https://pith.science/api/pith-number/OHGDPP3BSCG6RI6XYKARZXB37E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E/action/storage_attestation","attest_author":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E/action/author_attestation","sign_citation":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E/action/citation_signature","submit_replication":"https://pith.science/pith/OHGDPP3BSCG6RI6XYKARZXB37E/action/replication_record"}},"created_at":"2026-07-07T03:18:52.275996+00:00","updated_at":"2026-07-07T03:18:52.275996+00:00"}