{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MFJDG6UJQQCV3TZX6M6GXKOD4I","short_pith_number":"pith:MFJDG6UJ","schema_version":"1.0","canonical_sha256":"6152337a8984055dcf37f33c6ba9c3e23a2da90b82136d0d8ea8d4236be8d2d5","source":{"kind":"arxiv","id":"2505.20718","version":2},"attestation_state":"computed","paper":{"title":"VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Churan Wang, Fangwei Zhong, Hao Chen, Kui Wu, ShuHang Xu, Yizhou Wang, Zhoujun Li","submitted_at":"2025-05-27T04:53:50Z","abstract_excerpt":"We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our approach combines the off-the-shelf active tracking methods with VLMs' reasoning capabilities, deploying a fast visual policy for normal tracking and activating VLM reasoning only upon failure detection. The framework features a memory-augmented self-reflection mechanism that enables the VLM to progressively improve by learning from past experiences, effectively"},"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":"2505.20718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:53:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4833b64c0826d9d1c406f918e37f219c58d592eb4825c44751ba221262c9361e","abstract_canon_sha256":"912b54b07afa81db968f50fd5bf86e99862db247c1216f7c76a16f652a15b4f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:23.024403Z","signature_b64":"yrA176hHz5dV+1Jq6VxEQpG8u/6s10tZBIlhHFjMcAQSwJ/a2FAVEnRTJB60t14BVNZTTJufIaYfnaBUW1+RBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6152337a8984055dcf37f33c6ba9c3e23a2da90b82136d0d8ea8d4236be8d2d5","last_reissued_at":"2026-07-05T11:11:23.023900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:23.023900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Churan Wang, Fangwei Zhong, Hao Chen, Kui Wu, ShuHang Xu, Yizhou Wang, Zhoujun Li","submitted_at":"2025-05-27T04:53:50Z","abstract_excerpt":"We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our approach combines the off-the-shelf active tracking methods with VLMs' reasoning capabilities, deploying a fast visual policy for normal tracking and activating VLM reasoning only upon failure detection. The framework features a memory-augmented self-reflection mechanism that enables the VLM to progressively improve by learning from past experiences, effectively"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20718","kind":"arxiv","version":2},"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/2505.20718/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":"2505.20718","created_at":"2026-07-05T11:11:23.023960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20718v2","created_at":"2026-07-05T11:11:23.023960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20718","created_at":"2026-07-05T11:11:23.023960+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFJDG6UJQQCV","created_at":"2026-07-05T11:11:23.023960+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFJDG6UJQQCV3TZX","created_at":"2026-07-05T11:11:23.023960+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFJDG6UJ","created_at":"2026-07-05T11:11:23.023960+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/MFJDG6UJQQCV3TZX6M6GXKOD4I","json":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I.json","graph_json":"https://pith.science/api/pith-number/MFJDG6UJQQCV3TZX6M6GXKOD4I/graph.json","events_json":"https://pith.science/api/pith-number/MFJDG6UJQQCV3TZX6M6GXKOD4I/events.json","paper":"https://pith.science/paper/MFJDG6UJ"},"agent_actions":{"view_html":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I","download_json":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I.json","view_paper":"https://pith.science/paper/MFJDG6UJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20718&json=true","fetch_graph":"https://pith.science/api/pith-number/MFJDG6UJQQCV3TZX6M6GXKOD4I/graph.json","fetch_events":"https://pith.science/api/pith-number/MFJDG6UJQQCV3TZX6M6GXKOD4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/action/storage_attestation","attest_author":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/action/author_attestation","sign_citation":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/action/citation_signature","submit_replication":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/action/replication_record"}},"created_at":"2026-07-05T11:11:23.023960+00:00","updated_at":"2026-07-05T11:11:23.023960+00:00"}