{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MSM7YQ4JOCH4KQD4WPTK2NWA5W","short_pith_number":"pith:MSM7YQ4J","schema_version":"1.0","canonical_sha256":"6499fc4389708fc5407cb3e6ad36c0edba9a775719741bc21d63a11494e478cc","source":{"kind":"arxiv","id":"2411.15459","version":1},"attestation_state":"computed","paper":{"title":"MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianqiu Chen, Li Zhou, Xinqi Liu, Zhenyu He, Zikun Zhou","submitted_at":"2024-11-23T05:31:58Z","abstract_excerpt":"The vision-language tracking task aims to perform object tracking based on various modality references. Existing Transformer-based vision-language tracking methods have made remarkable progress by leveraging the global modeling ability of self-attention. However, current approaches still face challenges in effectively exploiting the temporal information and dynamically updating reference features during tracking. Recently, the State Space Model (SSM), known as Mamba, has shown astonishing ability in efficient long-sequence modeling. Particularly, its state space evolving process demonstrates p"},"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":"2411.15459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T05:31:58Z","cross_cats_sorted":[],"title_canon_sha256":"6c246e41a62739977f6fb186637aa7a4687c3a1e4682438719d60a2e988a1ef7","abstract_canon_sha256":"2142d518b2c88e8990b7dffd1fc938a0eb72d92ff3dcd9403d6bd970766f9789"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:35.188554Z","signature_b64":"+3VuYgS1uzT5ra37Apo0E6Xhm6nmUtYQBA8fbHtYIDLKh+d3m0/ZFN9aNXSKOG8rmWBWKKcsM84ve5Sw2DYVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6499fc4389708fc5407cb3e6ad36c0edba9a775719741bc21d63a11494e478cc","last_reissued_at":"2026-07-05T09:39:35.188093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:35.188093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MambaVLT: Time-Evolving Multimodal State Space Model for Vision-Language Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianqiu Chen, Li Zhou, Xinqi Liu, Zhenyu He, Zikun Zhou","submitted_at":"2024-11-23T05:31:58Z","abstract_excerpt":"The vision-language tracking task aims to perform object tracking based on various modality references. Existing Transformer-based vision-language tracking methods have made remarkable progress by leveraging the global modeling ability of self-attention. However, current approaches still face challenges in effectively exploiting the temporal information and dynamically updating reference features during tracking. Recently, the State Space Model (SSM), known as Mamba, has shown astonishing ability in efficient long-sequence modeling. Particularly, its state space evolving process demonstrates p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15459","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/2411.15459/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":"2411.15459","created_at":"2026-07-05T09:39:35.188145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15459v1","created_at":"2026-07-05T09:39:35.188145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15459","created_at":"2026-07-05T09:39:35.188145+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSM7YQ4JOCH4","created_at":"2026-07-05T09:39:35.188145+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSM7YQ4JOCH4KQD4","created_at":"2026-07-05T09:39:35.188145+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSM7YQ4J","created_at":"2026-07-05T09:39:35.188145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W","json":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W.json","graph_json":"https://pith.science/api/pith-number/MSM7YQ4JOCH4KQD4WPTK2NWA5W/graph.json","events_json":"https://pith.science/api/pith-number/MSM7YQ4JOCH4KQD4WPTK2NWA5W/events.json","paper":"https://pith.science/paper/MSM7YQ4J"},"agent_actions":{"view_html":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W","download_json":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W.json","view_paper":"https://pith.science/paper/MSM7YQ4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15459&json=true","fetch_graph":"https://pith.science/api/pith-number/MSM7YQ4JOCH4KQD4WPTK2NWA5W/graph.json","fetch_events":"https://pith.science/api/pith-number/MSM7YQ4JOCH4KQD4WPTK2NWA5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W/action/storage_attestation","attest_author":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W/action/author_attestation","sign_citation":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W/action/citation_signature","submit_replication":"https://pith.science/pith/MSM7YQ4JOCH4KQD4WPTK2NWA5W/action/replication_record"}},"created_at":"2026-07-05T09:39:35.188145+00:00","updated_at":"2026-07-05T09:39:35.188145+00:00"}