{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TZBTAI3XNBMJATVYNQEM46DBTU","short_pith_number":"pith:TZBTAI3X","schema_version":"1.0","canonical_sha256":"9e433023776858904eb86c08ce78619d106eb1b03d591c27c3a3bbaac535ad8d","source":{"kind":"arxiv","id":"2305.06558","version":1},"attestation_state":"computed","paper":{"title":"Segment and Track Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liulei Li, Wenguan Wang, Xiaodi Li, Yangming Cheng, Yi Yang, Yuanyou Xu, Zongxin Yang","submitted_at":"2023-05-11T04:33:08Z","abstract_excerpt":"This report presents a framework called Segment And Track Anything (SAMTrack) that allows users to precisely and effectively segment and track any object in a video. Additionally, SAM-Track employs multimodal interaction methods that enable users to select multiple objects in videos for tracking, corresponding to their specific requirements. These interaction methods comprise click, stroke, and text, each possessing unique benefits and capable of being employed in combination. As a result, SAM-Track can be used across an array of fields, ranging from drone technology, autonomous driving, medic"},"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":"2305.06558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T04:33:08Z","cross_cats_sorted":[],"title_canon_sha256":"8c16b9158e255915a7db2d2ebd262b7a5b882ba67b022950c52db9721629b82e","abstract_canon_sha256":"4e11935edf8f5bbe2be77a86f112c40df87b82ab17d2155aaebada72394fc7e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:14.024299Z","signature_b64":"SDwMe/GRWvo5Y7zxImQ0ELP0/NgfH7mNEfw56G40qc530+K4jhnWBRR8Ij6km3hAwlFLM9y5T5TsXnw4vzkhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e433023776858904eb86c08ce78619d106eb1b03d591c27c3a3bbaac535ad8d","last_reissued_at":"2026-07-05T06:09:14.023840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:14.023840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment and Track Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liulei Li, Wenguan Wang, Xiaodi Li, Yangming Cheng, Yi Yang, Yuanyou Xu, Zongxin Yang","submitted_at":"2023-05-11T04:33:08Z","abstract_excerpt":"This report presents a framework called Segment And Track Anything (SAMTrack) that allows users to precisely and effectively segment and track any object in a video. Additionally, SAM-Track employs multimodal interaction methods that enable users to select multiple objects in videos for tracking, corresponding to their specific requirements. These interaction methods comprise click, stroke, and text, each possessing unique benefits and capable of being employed in combination. As a result, SAM-Track can be used across an array of fields, ranging from drone technology, autonomous driving, medic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06558","kind":"arxiv","version":1},"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/2305.06558/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":"2305.06558","created_at":"2026-07-05T06:09:14.023899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06558v1","created_at":"2026-07-05T06:09:14.023899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06558","created_at":"2026-07-05T06:09:14.023899+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZBTAI3XNBMJ","created_at":"2026-07-05T06:09:14.023899+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZBTAI3XNBMJATVY","created_at":"2026-07-05T06:09:14.023899+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZBTAI3X","created_at":"2026-07-05T06:09:14.023899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27655","citing_title":"Temporal-Emerged Prompting for Segment Anything in Multiframe Infrared Small Target Detection","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04960","citing_title":"On Efficient Variants of Segment Anything Model: A Survey","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15115","citing_title":"Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14244","citing_title":"Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17445","citing_title":"LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23173","citing_title":"One Identity, Many Roles: Multimodal Entity Coreference for Enhanced Video Situation Recognition","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08546","citing_title":"When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2408.00714","citing_title":"SAM 2: Segment Anything in Images and Videos","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20305","citing_title":"AdaTracker: Learning Adaptive In-Context Policy for Cross-Embodiment Active Visual Tracking","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU","json":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU.json","graph_json":"https://pith.science/api/pith-number/TZBTAI3XNBMJATVYNQEM46DBTU/graph.json","events_json":"https://pith.science/api/pith-number/TZBTAI3XNBMJATVYNQEM46DBTU/events.json","paper":"https://pith.science/paper/TZBTAI3X"},"agent_actions":{"view_html":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU","download_json":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU.json","view_paper":"https://pith.science/paper/TZBTAI3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06558&json=true","fetch_graph":"https://pith.science/api/pith-number/TZBTAI3XNBMJATVYNQEM46DBTU/graph.json","fetch_events":"https://pith.science/api/pith-number/TZBTAI3XNBMJATVYNQEM46DBTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU/action/storage_attestation","attest_author":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU/action/author_attestation","sign_citation":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU/action/citation_signature","submit_replication":"https://pith.science/pith/TZBTAI3XNBMJATVYNQEM46DBTU/action/replication_record"}},"created_at":"2026-07-05T06:09:14.023899+00:00","updated_at":"2026-07-05T06:09:14.023899+00:00"}