{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YTJQQ2OJ2VJOZLZBF5XIX24EJR","short_pith_number":"pith:YTJQQ2OJ","canonical_record":{"source":{"id":"2506.23590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T07:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"a084df524712b75a7491de254f6aa2a173017c848acfe9fce01ba0e55227e7d2","abstract_canon_sha256":"aea7cf16069373dfed04c56939fdfd988e468577fe5baf326ead3e6cb68b9d9e"},"schema_version":"1.0"},"canonical_sha256":"c4d30869c9d552ecaf212f6e8beb844c4a566e6e82604288d0a3ba942ccbc9d2","source":{"kind":"arxiv","id":"2506.23590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23590","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23590v1","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23590","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_12","alias_value":"YTJQQ2OJ2VJO","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_16","alias_value":"YTJQQ2OJ2VJOZLZB","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_8","alias_value":"YTJQQ2OJ","created_at":"2026-07-05T11:29:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YTJQQ2OJ2VJOZLZBF5XIX24EJR","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T07:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"a084df524712b75a7491de254f6aa2a173017c848acfe9fce01ba0e55227e7d2","abstract_canon_sha256":"aea7cf16069373dfed04c56939fdfd988e468577fe5baf326ead3e6cb68b9d9e"},"schema_version":"1.0"},"canonical_sha256":"c4d30869c9d552ecaf212f6e8beb844c4a566e6e82604288d0a3ba942ccbc9d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:24.495300Z","signature_b64":"tnEmQHMcKpK2T3SoKJdZu8ltqu7T9Qs3+GJ8eFqM/UcoHqSM1wCS+Kt+Jj566pqfYhBh5TkK8UY2qtGYwYaQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d30869c9d552ecaf212f6e8beb844c4a566e6e82604288d0a3ba942ccbc9d2","last_reissued_at":"2026-07-05T11:29:24.494748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:24.494748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23590","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":"2026-07-05T11:29:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/mHqZopYDJt+XaQwRJOmJWyz4L1Ql3UrJn+ZLawytlckWiaUz/6lLviKIaqXaki5yE/l7BJEYyn8GANZ2WDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:23:03.302672Z"},"content_sha256":"bb4ac089d77749b143db01abfe2153a35f369804cab1495d774ed2f28516db28","schema_version":"1.0","event_id":"sha256:bb4ac089d77749b143db01abfe2153a35f369804cab1495d774ed2f28516db28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YTJQQ2OJ2VJOZLZBF5XIX24EJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baohang Li, Bing Qin, Kui Jiang, Libo Qin, Qiming Li, Ruihan Chen, Ting Liu, Weihong Zhong, Xiaocheng Feng, Yaowei Wang, Zekai Ye","submitted_at":"2025-06-30T07:52:36Z","abstract_excerpt":"Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual information, leading to object hallucination. To tackle this, recent works mostly depend on expensive manual annotations and training cost, or significantly increase inference time. In this work, we observe that LVLMs' attention to visual information is significantly stronger when answering caption queries compared to non-caption queries. Inspired by this phenomenon, we propose Caption-sensitive Attention Interventio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23590","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/2506.23590/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":"2026-07-05T11:29:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9QQKuOEevYb9rJUW1COT3jx/+m+AwxikxerVdelLFOibEvrSY6KgYPmpNWLVc/cpkyODOKURHDd0z5pvz1XBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:23:03.303639Z"},"content_sha256":"d27b09318fa16cfd5c71aa7c32834024ebbd937b74993e7fd227336c6d73978a","schema_version":"1.0","event_id":"sha256:d27b09318fa16cfd5c71aa7c32834024ebbd937b74993e7fd227336c6d73978a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YTJQQ2OJ2VJOZLZBF5XIX24EJR/bundle.json","state_url":"https://pith.science/pith/YTJQQ2OJ2VJOZLZBF5XIX24EJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YTJQQ2OJ2VJOZLZBF5XIX24EJR/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":"2026-08-07T06:23:03Z","links":{"resolver":"https://pith.science/pith/YTJQQ2OJ2VJOZLZBF5XIX24EJR","bundle":"https://pith.science/pith/YTJQQ2OJ2VJOZLZBF5XIX24EJR/bundle.json","state":"https://pith.science/pith/YTJQQ2OJ2VJOZLZBF5XIX24EJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YTJQQ2OJ2VJOZLZBF5XIX24EJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YTJQQ2OJ2VJOZLZBF5XIX24EJR","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":"aea7cf16069373dfed04c56939fdfd988e468577fe5baf326ead3e6cb68b9d9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T07:52:36Z","title_canon_sha256":"a084df524712b75a7491de254f6aa2a173017c848acfe9fce01ba0e55227e7d2"},"schema_version":"1.0","source":{"id":"2506.23590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23590","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23590v1","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23590","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_12","alias_value":"YTJQQ2OJ2VJO","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_16","alias_value":"YTJQQ2OJ2VJOZLZB","created_at":"2026-07-05T11:29:24Z"},{"alias_kind":"pith_short_8","alias_value":"YTJQQ2OJ","created_at":"2026-07-05T11:29:24Z"}],"graph_snapshots":[{"event_id":"sha256:d27b09318fa16cfd5c71aa7c32834024ebbd937b74993e7fd227336c6d73978a","target":"graph","created_at":"2026-07-05T11:29:24Z","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/2506.23590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Large Vision-Language Models (LVLMs) have demonstrated powerful capabilities in interpreting visual information, they frequently produce content that deviates from visual information, leading to object hallucination. To tackle this, recent works mostly depend on expensive manual annotations and training cost, or significantly increase inference time. In this work, we observe that LVLMs' attention to visual information is significantly stronger when answering caption queries compared to non-caption queries. Inspired by this phenomenon, we propose Caption-sensitive Attention Interventio","authors_text":"Baohang Li, Bing Qin, Kui Jiang, Libo Qin, Qiming Li, Ruihan Chen, Ting Liu, Weihong Zhong, Xiaocheng Feng, Yaowei Wang, Zekai Ye","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T07:52:36Z","title":"CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23590","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:bb4ac089d77749b143db01abfe2153a35f369804cab1495d774ed2f28516db28","target":"record","created_at":"2026-07-05T11:29:24Z","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":"aea7cf16069373dfed04c56939fdfd988e468577fe5baf326ead3e6cb68b9d9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T07:52:36Z","title_canon_sha256":"a084df524712b75a7491de254f6aa2a173017c848acfe9fce01ba0e55227e7d2"},"schema_version":"1.0","source":{"id":"2506.23590","kind":"arxiv","version":1}},"canonical_sha256":"c4d30869c9d552ecaf212f6e8beb844c4a566e6e82604288d0a3ba942ccbc9d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4d30869c9d552ecaf212f6e8beb844c4a566e6e82604288d0a3ba942ccbc9d2","first_computed_at":"2026-07-05T11:29:24.494748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:24.494748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tnEmQHMcKpK2T3SoKJdZu8ltqu7T9Qs3+GJ8eFqM/UcoHqSM1wCS+Kt+Jj566pqfYhBh5TkK8UY2qtGYwYaQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:24.495300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb4ac089d77749b143db01abfe2153a35f369804cab1495d774ed2f28516db28","sha256:d27b09318fa16cfd5c71aa7c32834024ebbd937b74993e7fd227336c6d73978a"],"state_sha256":"3b7b4be39245f4e3600c037e205c64f8a92591a097d93aac0d7b3fc61fa7edc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5t4vr4Z0wIVaIFWPiJrDA3OqyhbctsqQXFIyTD4R4AwPzU0YMhBSBJzIU1kQCvTuYzyr3NsDLDGJ8x1I6hr8CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:23:03.310603Z","bundle_sha256":"dcbf9a004e1435bceaa266184b6899b4a6e4a6ffbb3f5d983b29febccad44810"}}