{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MFJDG6UJQQCV3TZX6M6GXKOD4I","short_pith_number":"pith:MFJDG6UJ","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"},"canonical_sha256":"6152337a8984055dcf37f33c6ba9c3e23a2da90b82136d0d8ea8d4236be8d2d5","source":{"kind":"arxiv","id":"2505.20718","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20718","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20718v2","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20718","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"MFJDG6UJQQCV","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"MFJDG6UJQQCV3TZX","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"MFJDG6UJ","created_at":"2026-07-05T11:11:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MFJDG6UJQQCV3TZX6M6GXKOD4I","target":"record","payload":{"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"},"canonical_sha256":"6152337a8984055dcf37f33c6ba9c3e23a2da90b82136d0d8ea8d4236be8d2d5","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"},"source_kind":"arxiv","source_id":"2505.20718","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/fQbPIzNXde9rxhE496rzKWaINiRTlG+w4k9vOko0BN5L1iQ5PZciE2a9aMrn2hP8jxTFSE8UM1w1D6gwh8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:57:05.555175Z"},"content_sha256":"2f4b33d70bbdc8d1d682e5da2f2d51153444a467a93021b46e2b9f6cb7458342","schema_version":"1.0","event_id":"sha256:2f4b33d70bbdc8d1d682e5da2f2d51153444a467a93021b46e2b9f6cb7458342"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MFJDG6UJQQCV3TZX6M6GXKOD4I","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9LKnaTrzHKCrL0yDQImR78tGGnItUb/CL3QmXVFZ2R1pgEpg8arwoJob8QYFdOSVrKV+3dTflx38BL3ChcmJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:57:05.555836Z"},"content_sha256":"ae59fd4f6f5309044635929cb8b0b919459f70663e610da2693b26815a808ec2","schema_version":"1.0","event_id":"sha256:ae59fd4f6f5309044635929cb8b0b919459f70663e610da2693b26815a808ec2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/bundle.json","state_url":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:57:05Z","links":{"resolver":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I","bundle":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/bundle.json","state":"https://pith.science/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFJDG6UJQQCV3TZX6M6GXKOD4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MFJDG6UJQQCV3TZX6M6GXKOD4I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"912b54b07afa81db968f50fd5bf86e99862db247c1216f7c76a16f652a15b4f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:53:50Z","title_canon_sha256":"4833b64c0826d9d1c406f918e37f219c58d592eb4825c44751ba221262c9361e"},"schema_version":"1.0","source":{"id":"2505.20718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20718","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20718v2","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20718","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"MFJDG6UJQQCV","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"MFJDG6UJQQCV3TZX","created_at":"2026-07-05T11:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"MFJDG6UJ","created_at":"2026-07-05T11:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:ae59fd4f6f5309044635929cb8b0b919459f70663e610da2693b26815a808ec2","target":"graph","created_at":"2026-07-05T11:11:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.20718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Churan Wang, Fangwei Zhong, Hao Chen, Kui Wu, ShuHang Xu, Yizhou Wang, Zhoujun Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:53:50Z","title":"VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20718","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2f4b33d70bbdc8d1d682e5da2f2d51153444a467a93021b46e2b9f6cb7458342","target":"record","created_at":"2026-07-05T11:11:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"912b54b07afa81db968f50fd5bf86e99862db247c1216f7c76a16f652a15b4f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:53:50Z","title_canon_sha256":"4833b64c0826d9d1c406f918e37f219c58d592eb4825c44751ba221262c9361e"},"schema_version":"1.0","source":{"id":"2505.20718","kind":"arxiv","version":2}},"canonical_sha256":"6152337a8984055dcf37f33c6ba9c3e23a2da90b82136d0d8ea8d4236be8d2d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6152337a8984055dcf37f33c6ba9c3e23a2da90b82136d0d8ea8d4236be8d2d5","first_computed_at":"2026-07-05T11:11:23.023900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:23.023900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yrA176hHz5dV+1Jq6VxEQpG8u/6s10tZBIlhHFjMcAQSwJ/a2FAVEnRTJB60t14BVNZTTJufIaYfnaBUW1+RBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:23.024403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f4b33d70bbdc8d1d682e5da2f2d51153444a467a93021b46e2b9f6cb7458342","sha256:ae59fd4f6f5309044635929cb8b0b919459f70663e610da2693b26815a808ec2"],"state_sha256":"6187de41180eea26422f5474872cdae2b5be5f00e3e03f0d1542dcb54a9bd220"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qZBCXjmKv/Ay4DU0iy0d4u9awCQrBKmemuIc+q7q/zYH305HDVls6tPKX38456EUr861wt/L/4ijVssTvuf3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:57:05.560057Z","bundle_sha256":"40913b5ad8135b1d9a6f93925051fa8cb0f42050e5ceabfa93aef5b237a636d1"}}