{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZRHJYSTFZRELVEAQLAMUA5KSU3","short_pith_number":"pith:ZRHJYSTF","canonical_record":{"source":{"id":"2505.20710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:36:26Z","cross_cats_sorted":[],"title_canon_sha256":"faee42300ccc153d6053c9404fef8e53d17b03a49b9e8a68e421e430b964a045","abstract_canon_sha256":"8b19a75d67cc33c5d37be5cfab5c6d817117c3f05757d94da71b13df5a4f470c"},"schema_version":"1.0"},"canonical_sha256":"cc4e9c4a65cc48ba90105819407552a6f8b7c039d81acb0e91724c2fb11535cf","source":{"kind":"arxiv","id":"2505.20710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20710","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20710v1","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20710","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZRHJYSTFZREL","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZRHJYSTFZRELVEAQ","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZRHJYSTF","created_at":"2026-07-05T11:10:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZRHJYSTFZRELVEAQLAMUA5KSU3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:36:26Z","cross_cats_sorted":[],"title_canon_sha256":"faee42300ccc153d6053c9404fef8e53d17b03a49b9e8a68e421e430b964a045","abstract_canon_sha256":"8b19a75d67cc33c5d37be5cfab5c6d817117c3f05757d94da71b13df5a4f470c"},"schema_version":"1.0"},"canonical_sha256":"cc4e9c4a65cc48ba90105819407552a6f8b7c039d81acb0e91724c2fb11535cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:17.335240Z","signature_b64":"yB8sw5FWaPvcoTg3zkTvANjTfsKXuN58JWUY7ShGNUpU7tKkTFnMPWm5e1MSQbzZ7fKyazZNpHaP63gjZXYADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc4e9c4a65cc48ba90105819407552a6f8b7c039d81acb0e91724c2fb11535cf","last_reissued_at":"2026-07-05T11:10:17.334706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:17.334706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20710","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"reaFMsX07Q4VHjFl1cuHxx6UgIvTpf4du2FKxcegrro2jO9scXKRYh7ckD6VYufSIoMBPLbs49HvIX+kru4fAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:29:06.380529Z"},"content_sha256":"3f78f985bb90883ce8448131e16481000e803c6a81f27557c7a89260cd3906aa","schema_version":"1.0","event_id":"sha256:3f78f985bb90883ce8448131e16481000e803c6a81f27557c7a89260cd3906aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZRHJYSTFZRELVEAQLAMUA5KSU3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Instruction-aware Embodied Visual Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Churan Wang, Fakhri Karray, Fangwei Zhong, Hao Chen, Kui Wu, Yizhou Wang, Zhoujun Li","submitted_at":"2025-05-27T04:36:26Z","abstract_excerpt":"User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions and low-level agent actions. While recent advancements in language models (e.g., LLMs, VLMs, VLAs) have improved instruction comprehension, these models face critical limitations in either inference speed (LLMs, VLMs) or generalizability (VLAs) for UC-EVT tasks. To address these challenges, we propose \\textbf{Hierarchical Instruction-aware Embodied Visual Tracking (HIEVT)} agent, which bridges instruction comprehension"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20710","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/2505.20710/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":"2026-07-05T11:10:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EM+paY6gyE3UuXrHWsMSmNZizmEqb0c9dFDHPzBqUD6qMZbac77Hw1suJGJIgJ3ezSy62Ec92VulhNuYc00XBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:29:06.381071Z"},"content_sha256":"dec734c739a2b2747d37fb2be9a12c800eb4144122d1c7683a087ea4785c7d19","schema_version":"1.0","event_id":"sha256:dec734c739a2b2747d37fb2be9a12c800eb4144122d1c7683a087ea4785c7d19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZRHJYSTFZRELVEAQLAMUA5KSU3/bundle.json","state_url":"https://pith.science/pith/ZRHJYSTFZRELVEAQLAMUA5KSU3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZRHJYSTFZRELVEAQLAMUA5KSU3/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":"2026-08-10T00:29:06Z","links":{"resolver":"https://pith.science/pith/ZRHJYSTFZRELVEAQLAMUA5KSU3","bundle":"https://pith.science/pith/ZRHJYSTFZRELVEAQLAMUA5KSU3/bundle.json","state":"https://pith.science/pith/ZRHJYSTFZRELVEAQLAMUA5KSU3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZRHJYSTFZRELVEAQLAMUA5KSU3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZRHJYSTFZRELVEAQLAMUA5KSU3","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":"8b19a75d67cc33c5d37be5cfab5c6d817117c3f05757d94da71b13df5a4f470c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:36:26Z","title_canon_sha256":"faee42300ccc153d6053c9404fef8e53d17b03a49b9e8a68e421e430b964a045"},"schema_version":"1.0","source":{"id":"2505.20710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20710","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20710v1","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20710","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZRHJYSTFZREL","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZRHJYSTFZRELVEAQ","created_at":"2026-07-05T11:10:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZRHJYSTF","created_at":"2026-07-05T11:10:17Z"}],"graph_snapshots":[{"event_id":"sha256:dec734c739a2b2747d37fb2be9a12c800eb4144122d1c7683a087ea4785c7d19","target":"graph","created_at":"2026-07-05T11:10:17Z","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/2505.20710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions and low-level agent actions. While recent advancements in language models (e.g., LLMs, VLMs, VLAs) have improved instruction comprehension, these models face critical limitations in either inference speed (LLMs, VLMs) or generalizability (VLAs) for UC-EVT tasks. To address these challenges, we propose \\textbf{Hierarchical Instruction-aware Embodied Visual Tracking (HIEVT)} agent, which bridges instruction comprehension","authors_text":"Churan Wang, Fakhri Karray, Fangwei Zhong, Hao Chen, Kui Wu, Yizhou Wang, Zhoujun Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:36:26Z","title":"Hierarchical Instruction-aware Embodied Visual Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20710","kind":"arxiv","version":1},"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":"sha256:3f78f985bb90883ce8448131e16481000e803c6a81f27557c7a89260cd3906aa","target":"record","created_at":"2026-07-05T11:10:17Z","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":"8b19a75d67cc33c5d37be5cfab5c6d817117c3f05757d94da71b13df5a4f470c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T04:36:26Z","title_canon_sha256":"faee42300ccc153d6053c9404fef8e53d17b03a49b9e8a68e421e430b964a045"},"schema_version":"1.0","source":{"id":"2505.20710","kind":"arxiv","version":1}},"canonical_sha256":"cc4e9c4a65cc48ba90105819407552a6f8b7c039d81acb0e91724c2fb11535cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc4e9c4a65cc48ba90105819407552a6f8b7c039d81acb0e91724c2fb11535cf","first_computed_at":"2026-07-05T11:10:17.334706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:17.334706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yB8sw5FWaPvcoTg3zkTvANjTfsKXuN58JWUY7ShGNUpU7tKkTFnMPWm5e1MSQbzZ7fKyazZNpHaP63gjZXYADA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:17.335240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f78f985bb90883ce8448131e16481000e803c6a81f27557c7a89260cd3906aa","sha256:dec734c739a2b2747d37fb2be9a12c800eb4144122d1c7683a087ea4785c7d19"],"state_sha256":"1931b4275f9b52d6814160ec3bd092c771c2b6bfdd0fe5f82e8ad61808e1b4cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3oMXvjhQqeSUewzr/vT5LADOGryHD0//zY6klDVumPd9NT9SXT/GRwbSLv2VJ45JavTQdFLyPMS/Rso2jG+FBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:29:06.384707Z","bundle_sha256":"04dc20f1cd3e0920c337d2d424664c4b6654926c13f855ca48ea81d1209fc0fb"}}