{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QQTOU2CVOVRRFL5CAGKO5YOLE4","short_pith_number":"pith:QQTOU2CV","schema_version":"1.0","canonical_sha256":"8426ea6855756312afa20194eee1cb27062a79e132c888b7bfe5e24b2d03eb44","source":{"kind":"arxiv","id":"2506.21980","version":3},"attestation_state":"computed","paper":{"title":"R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Wang, Jiawei Ge, Wenwen Li","submitted_at":"2025-06-27T07:41:15Z","abstract_excerpt":"Visual single object tracking aims to continuously localize and estimate the scale of a target in subsequent video frames, given only its initial state in the first frame. This task has traditionally been framed as a template matching problem, evolving through major phases including correlation filters, two-stream networks, and one-stream networks with significant progress achieved. However, these methods typically require explicit classification and regression modeling, depend on supervised training with large-scale datasets, and are limited to the single task of tracking, lacking flexibility"},"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":"2506.21980","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T07:41:15Z","cross_cats_sorted":[],"title_canon_sha256":"e2c5c0d3e71bca10d4d6c9ead1f59898bd2d7ac36b362d8f33fd2d4b01813754","abstract_canon_sha256":"a01d3151f341e5cc7ab605deb06f6d99a4c41d2aacda27c835fa9f319438561b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:26.224003Z","signature_b64":"FdMLL3kolDS2ZHQCtuhIJppExZfqFuXdAdeMXmhONfK6Uq0ztsyeT/NatmNQ66C1fdxkbO8aLb0rjwYgcC/0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8426ea6855756312afa20194eee1cb27062a79e132c888b7bfe5e24b2d03eb44","last_reissued_at":"2026-07-05T11:41:26.223212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:26.223212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Wang, Jiawei Ge, Wenwen Li","submitted_at":"2025-06-27T07:41:15Z","abstract_excerpt":"Visual single object tracking aims to continuously localize and estimate the scale of a target in subsequent video frames, given only its initial state in the first frame. This task has traditionally been framed as a template matching problem, evolving through major phases including correlation filters, two-stream networks, and one-stream networks with significant progress achieved. However, these methods typically require explicit classification and regression modeling, depend on supervised training with large-scale datasets, and are limited to the single task of tracking, lacking flexibility"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21980","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/2506.21980/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":"2506.21980","created_at":"2026-07-05T11:41:26.223305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21980v3","created_at":"2026-07-05T11:41:26.223305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21980","created_at":"2026-07-05T11:41:26.223305+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQTOU2CVOVRR","created_at":"2026-07-05T11:41:26.223305+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQTOU2CVOVRRFL5C","created_at":"2026-07-05T11:41:26.223305+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQTOU2CV","created_at":"2026-07-05T11:41:26.223305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29357","citing_title":"Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20260","citing_title":"Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08014","citing_title":"Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17898","citing_title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18051","citing_title":"INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4","json":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4.json","graph_json":"https://pith.science/api/pith-number/QQTOU2CVOVRRFL5CAGKO5YOLE4/graph.json","events_json":"https://pith.science/api/pith-number/QQTOU2CVOVRRFL5CAGKO5YOLE4/events.json","paper":"https://pith.science/paper/QQTOU2CV"},"agent_actions":{"view_html":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4","download_json":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4.json","view_paper":"https://pith.science/paper/QQTOU2CV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21980&json=true","fetch_graph":"https://pith.science/api/pith-number/QQTOU2CVOVRRFL5CAGKO5YOLE4/graph.json","fetch_events":"https://pith.science/api/pith-number/QQTOU2CVOVRRFL5CAGKO5YOLE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4/action/storage_attestation","attest_author":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4/action/author_attestation","sign_citation":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4/action/citation_signature","submit_replication":"https://pith.science/pith/QQTOU2CVOVRRFL5CAGKO5YOLE4/action/replication_record"}},"created_at":"2026-07-05T11:41:26.223305+00:00","updated_at":"2026-07-05T11:41:26.223305+00:00"}