{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EMLEHGJ57EWGXHWG5XL3JYFSAF","short_pith_number":"pith:EMLEHGJ5","canonical_record":{"source":{"id":"2503.23508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T16:41:12Z","cross_cats_sorted":[],"title_canon_sha256":"55642f29eeeeac8af2a6de8968288c76a248bc6c221feb0d8c13b224084c1418","abstract_canon_sha256":"953dc6acc72b668178997620ea5a06473a49323ba146e75ca7daa6c59aeb92a6"},"schema_version":"1.0"},"canonical_sha256":"231643993df92c6b9ec6edd7b4e0b2016668f696b10c1f5731d5edf206799fa1","source":{"kind":"arxiv","id":"2503.23508","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23508","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23508v1","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23508","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"pith_short_12","alias_value":"EMLEHGJ57EWG","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"pith_short_16","alias_value":"EMLEHGJ57EWGXHWG","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"pith_short_8","alias_value":"EMLEHGJ5","created_at":"2026-07-05T10:41:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EMLEHGJ57EWGXHWG5XL3JYFSAF","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T16:41:12Z","cross_cats_sorted":[],"title_canon_sha256":"55642f29eeeeac8af2a6de8968288c76a248bc6c221feb0d8c13b224084c1418","abstract_canon_sha256":"953dc6acc72b668178997620ea5a06473a49323ba146e75ca7daa6c59aeb92a6"},"schema_version":"1.0"},"canonical_sha256":"231643993df92c6b9ec6edd7b4e0b2016668f696b10c1f5731d5edf206799fa1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:37.639771Z","signature_b64":"xbILe1omg9pMW/6pV6iPE29o3lGMRyY9UWIkruqRmjv7mwxW8Hj2BA4OBowWOhsifJTxesaKhUZl2eXF9G2SAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"231643993df92c6b9ec6edd7b4e0b2016668f696b10c1f5731d5edf206799fa1","last_reissued_at":"2026-07-05T10:41:37.639270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:37.639270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23508","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":"2026-07-05T10:41:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/3Z3VspPuBRukfVRzC3GSe9mEwfVihqtFt50iSkm/l/85qJhAkroKsdjVvdyGtvrG1zCufTnYLmTdRNoFs3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:42:11.599598Z"},"content_sha256":"db1ff746b672ae2a80b74c3be561aee91e5da216085c8f88572177e2b6285f4c","schema_version":"1.0","event_id":"sha256:db1ff746b672ae2a80b74c3be561aee91e5da216085c8f88572177e2b6285f4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EMLEHGJ57EWGXHWG5XL3JYFSAF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Re-Aligning Language to Visual Objects with an Agentic Workflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhu, Haodong Zhang, Jiangyan Feng, Lijun Gong, Ming-Ming Cheng, Qibin Hou, Rui Zhao, Yibing Song, Yuming Chen","submitted_at":"2025-03-30T16:41:12Z","abstract_excerpt":"Language-based object detection (LOD) aims to align visual objects with language expressions. A large amount of paired data is utilized to improve LOD model generalizations. During the training process, recent studies leverage vision-language models (VLMs) to automatically generate human-like expressions for visual objects, facilitating training data scaling up. In this process, we observe that VLM hallucinations bring inaccurate object descriptions (e.g., object name, color, and shape) to deteriorate VL alignment quality. To reduce VLM hallucinations, we propose an agentic workflow controlled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23508","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/2503.23508/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":"2026-07-05T10:41:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8xsPymaBDEy+0QD+Fqe3PsYWLCjBpMFKhHEdQ6yDJWGL7JcRJW1V8Br9BVFpbw6pz925BF/Xk9c9h44TLv9HBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:42:11.599968Z"},"content_sha256":"1e77580e2c0af3ab63a3cca9afb644ba4a5faac6e9b4406e66fb31725faf04e0","schema_version":"1.0","event_id":"sha256:1e77580e2c0af3ab63a3cca9afb644ba4a5faac6e9b4406e66fb31725faf04e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EMLEHGJ57EWGXHWG5XL3JYFSAF/bundle.json","state_url":"https://pith.science/pith/EMLEHGJ57EWGXHWG5XL3JYFSAF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EMLEHGJ57EWGXHWG5XL3JYFSAF/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":"2026-07-07T08:42:11Z","links":{"resolver":"https://pith.science/pith/EMLEHGJ57EWGXHWG5XL3JYFSAF","bundle":"https://pith.science/pith/EMLEHGJ57EWGXHWG5XL3JYFSAF/bundle.json","state":"https://pith.science/pith/EMLEHGJ57EWGXHWG5XL3JYFSAF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EMLEHGJ57EWGXHWG5XL3JYFSAF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EMLEHGJ57EWGXHWG5XL3JYFSAF","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":"953dc6acc72b668178997620ea5a06473a49323ba146e75ca7daa6c59aeb92a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T16:41:12Z","title_canon_sha256":"55642f29eeeeac8af2a6de8968288c76a248bc6c221feb0d8c13b224084c1418"},"schema_version":"1.0","source":{"id":"2503.23508","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23508","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23508v1","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23508","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"pith_short_12","alias_value":"EMLEHGJ57EWG","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"pith_short_16","alias_value":"EMLEHGJ57EWGXHWG","created_at":"2026-07-05T10:41:37Z"},{"alias_kind":"pith_short_8","alias_value":"EMLEHGJ5","created_at":"2026-07-05T10:41:37Z"}],"graph_snapshots":[{"event_id":"sha256:1e77580e2c0af3ab63a3cca9afb644ba4a5faac6e9b4406e66fb31725faf04e0","target":"graph","created_at":"2026-07-05T10:41:37Z","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/2503.23508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-based object detection (LOD) aims to align visual objects with language expressions. A large amount of paired data is utilized to improve LOD model generalizations. During the training process, recent studies leverage vision-language models (VLMs) to automatically generate human-like expressions for visual objects, facilitating training data scaling up. In this process, we observe that VLM hallucinations bring inaccurate object descriptions (e.g., object name, color, and shape) to deteriorate VL alignment quality. To reduce VLM hallucinations, we propose an agentic workflow controlled","authors_text":"Feng Zhu, Haodong Zhang, Jiangyan Feng, Lijun Gong, Ming-Ming Cheng, Qibin Hou, Rui Zhao, Yibing Song, Yuming Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T16:41:12Z","title":"Re-Aligning Language to Visual Objects with an Agentic Workflow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23508","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:db1ff746b672ae2a80b74c3be561aee91e5da216085c8f88572177e2b6285f4c","target":"record","created_at":"2026-07-05T10:41:37Z","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":"953dc6acc72b668178997620ea5a06473a49323ba146e75ca7daa6c59aeb92a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-30T16:41:12Z","title_canon_sha256":"55642f29eeeeac8af2a6de8968288c76a248bc6c221feb0d8c13b224084c1418"},"schema_version":"1.0","source":{"id":"2503.23508","kind":"arxiv","version":1}},"canonical_sha256":"231643993df92c6b9ec6edd7b4e0b2016668f696b10c1f5731d5edf206799fa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"231643993df92c6b9ec6edd7b4e0b2016668f696b10c1f5731d5edf206799fa1","first_computed_at":"2026-07-05T10:41:37.639270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:37.639270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xbILe1omg9pMW/6pV6iPE29o3lGMRyY9UWIkruqRmjv7mwxW8Hj2BA4OBowWOhsifJTxesaKhUZl2eXF9G2SAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:37.639771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23508","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db1ff746b672ae2a80b74c3be561aee91e5da216085c8f88572177e2b6285f4c","sha256:1e77580e2c0af3ab63a3cca9afb644ba4a5faac6e9b4406e66fb31725faf04e0"],"state_sha256":"3d13f273ccdb6463114be86ad0e6e903553d4d853ff60d01e523abea961820b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1vB3w0dwFwauHqVeB4mhIvh2V8vvEVmFoL2O98gMcLN6uMR/yJ07WO6FkeNMNmszaO+eB78NsuCeX0CeoGzrBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:42:11.601972Z","bundle_sha256":"0e633cad9e2262e31f696c578eeaa68d9a0e38173d23504f4a772cf579aa471b"}}