{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TIAYBQAODM6JH2DPGWLPG2QRAT","short_pith_number":"pith:TIAYBQAO","schema_version":"1.0","canonical_sha256":"9a0180c00e1b3c93e86f3596f36a1104ce4fb149f7927578e2ede38c49fd128a","source":{"kind":"arxiv","id":"2608.01488","version":1},"attestation_state":"computed","paper":{"title":"Towards Compact Unified Multimodal Tracking: Synergizing Knowledge Distillation with Structural Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanguang Yang, Huiran Duan, Shiping Wen, Tingwen Huang, Weilun Feng, Yingli Tian, Yuedong Tan, Yuqi Li, Zhulin An, Zongwei Wu","submitted_at":"2026-08-02T20:41:33Z","abstract_excerpt":"Unified multimodal object tracking has achieved remarkable robustness by leveraging complementary sensor data (e.g., RGB, Thermal, Depth), yet the heavy computational burden of state-of-the-art models hinders their deployment on resource-constrained edge devices. In this work, we identify the prediction head as a critical but often overlooked efficiency bottleneck. By strategically streamlining the decoder architecture, we unlock the potential for real-time inference but simultaneously introduce a capacity gap between the lightweight student and the heavy teacher. To resolve this, we conduct a"},"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":"2608.01488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-02T20:41:33Z","cross_cats_sorted":[],"title_canon_sha256":"e2e12113c0ca35625e2cc6fc60e7c6e321fc12d45254b3a5f1e33afa54806ba1","abstract_canon_sha256":"85a5670926882e6e85d60c659db54369552e9a6a3b8ca75b32622c96e43a90bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:05:30.736784Z","signature_b64":"8wt6fK4yYNlXUrf3eJq+m2opcLeN4/TBOFSQKkso2qoMnvDp8KVPh0BKC8uFk/V9uYqPrwMiLdrXvVZ5brynCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a0180c00e1b3c93e86f3596f36a1104ce4fb149f7927578e2ede38c49fd128a","last_reissued_at":"2026-08-04T02:05:30.735322Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:05:30.735322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Compact Unified Multimodal Tracking: Synergizing Knowledge Distillation with Structural Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanguang Yang, Huiran Duan, Shiping Wen, Tingwen Huang, Weilun Feng, Yingli Tian, Yuedong Tan, Yuqi Li, Zhulin An, Zongwei Wu","submitted_at":"2026-08-02T20:41:33Z","abstract_excerpt":"Unified multimodal object tracking has achieved remarkable robustness by leveraging complementary sensor data (e.g., RGB, Thermal, Depth), yet the heavy computational burden of state-of-the-art models hinders their deployment on resource-constrained edge devices. In this work, we identify the prediction head as a critical but often overlooked efficiency bottleneck. By strategically streamlining the decoder architecture, we unlock the potential for real-time inference but simultaneously introduce a capacity gap between the lightweight student and the heavy teacher. To resolve this, we conduct a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01488","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/2608.01488/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":"2608.01488","created_at":"2026-08-04T02:05:30.736733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01488v1","created_at":"2026-08-04T02:05:30.736733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01488","created_at":"2026-08-04T02:05:30.736733+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIAYBQAODM6J","created_at":"2026-08-04T02:05:30.736733+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIAYBQAODM6JH2DP","created_at":"2026-08-04T02:05:30.736733+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIAYBQAO","created_at":"2026-08-04T02:05:30.736733+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/TIAYBQAODM6JH2DPGWLPG2QRAT","json":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT.json","graph_json":"https://pith.science/api/pith-number/TIAYBQAODM6JH2DPGWLPG2QRAT/graph.json","events_json":"https://pith.science/api/pith-number/TIAYBQAODM6JH2DPGWLPG2QRAT/events.json","paper":"https://pith.science/paper/TIAYBQAO"},"agent_actions":{"view_html":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT","download_json":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT.json","view_paper":"https://pith.science/paper/TIAYBQAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01488&json=true","fetch_graph":"https://pith.science/api/pith-number/TIAYBQAODM6JH2DPGWLPG2QRAT/graph.json","fetch_events":"https://pith.science/api/pith-number/TIAYBQAODM6JH2DPGWLPG2QRAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT/action/storage_attestation","attest_author":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT/action/author_attestation","sign_citation":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT/action/citation_signature","submit_replication":"https://pith.science/pith/TIAYBQAODM6JH2DPGWLPG2QRAT/action/replication_record"}},"created_at":"2026-08-04T02:05:30.736733+00:00","updated_at":"2026-08-04T02:05:30.736733+00:00"}