{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DLECZMHE7PMVUXYSUSE23LNGWN","short_pith_number":"pith:DLECZMHE","canonical_record":{"source":{"id":"2406.12663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T14:33:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a340daf42ce8ee3363e62c82c440dc2126bb22075b46d11d4229ab7a9e798e6c","abstract_canon_sha256":"69d7de98b5cca8b70c351c71363e48159b45d6023207f529d4a0e12f58bea065"},"schema_version":"1.0"},"canonical_sha256":"1ac82cb0e4fbd95a5f12a489adada6b34c226096791420fa566b548a69901f01","source":{"kind":"arxiv","id":"2406.12663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12663","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12663v1","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12663","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"pith_short_12","alias_value":"DLECZMHE7PMV","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"pith_short_16","alias_value":"DLECZMHE7PMVUXYS","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"pith_short_8","alias_value":"DLECZMHE","created_at":"2026-07-05T08:33:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DLECZMHE7PMVUXYSUSE23LNGWN","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T14:33:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a340daf42ce8ee3363e62c82c440dc2126bb22075b46d11d4229ab7a9e798e6c","abstract_canon_sha256":"69d7de98b5cca8b70c351c71363e48159b45d6023207f529d4a0e12f58bea065"},"schema_version":"1.0"},"canonical_sha256":"1ac82cb0e4fbd95a5f12a489adada6b34c226096791420fa566b548a69901f01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:49.246603Z","signature_b64":"NJJCRmv/s+klZmJH2JmvgeYQSYM6vTX2K29AvgWu0POaa1/GVkMzRHGDK+ya1cyzVVDydbkX5tSMjI/aUuFLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ac82cb0e4fbd95a5f12a489adada6b34c226096791420fa566b548a69901f01","last_reissued_at":"2026-07-05T08:33:49.246140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:49.246140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12663","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":"2026-07-05T08:33:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uF8JNHrLMj6pJf65E6xUe3wW+lpEBQww+R7Ud31Rye/C/xcZl50V9Ox2lVjQklRzTUpZkkB1L0IIogFVcy8TAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T06:53:27.208151Z"},"content_sha256":"bf8ea66e18d8348040771ffe554274f8001225db26daf13fa6541906c74588b7","schema_version":"1.0","event_id":"sha256:bf8ea66e18d8348040771ffe554274f8001225db26daf13fa6541906c74588b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DLECZMHE7PMVUXYSUSE23LNGWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Mingqian Feng, Yunlong Tang, Zeliang Zhang","submitted_at":"2024-06-18T14:33:56Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) excel in integrating visual and linguistic contexts to produce detailed content, facilitating applications such as image captioning. However, using LVLMs to generate descriptions often faces the challenge of object hallucination (OH), where the output text misrepresents actual objects in the input image. While previous studies attribute the occurrence of OH to the inclusion of more details, our study finds technical flaws in existing metrics, leading to unreliable evaluations of models and conclusions about OH. This has sparked a debate on the question: Do "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12663","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/2406.12663/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":"2026-07-05T08:33:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8WwGAxpz/LxEkgOMuSX267VHP2q32vALC+2AZ03C+7KotSfIu1Gq4fxq8xnC7B7AuUjl4KPcT5qM9FO4Z6YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T06:53:27.208543Z"},"content_sha256":"a5ef74cb91da14f6147fe4644bb248fd603f2aac838028e3321de2d291e32aff","schema_version":"1.0","event_id":"sha256:a5ef74cb91da14f6147fe4644bb248fd603f2aac838028e3321de2d291e32aff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DLECZMHE7PMVUXYSUSE23LNGWN/bundle.json","state_url":"https://pith.science/pith/DLECZMHE7PMVUXYSUSE23LNGWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DLECZMHE7PMVUXYSUSE23LNGWN/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":"2026-07-20T06:53:27Z","links":{"resolver":"https://pith.science/pith/DLECZMHE7PMVUXYSUSE23LNGWN","bundle":"https://pith.science/pith/DLECZMHE7PMVUXYSUSE23LNGWN/bundle.json","state":"https://pith.science/pith/DLECZMHE7PMVUXYSUSE23LNGWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DLECZMHE7PMVUXYSUSE23LNGWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DLECZMHE7PMVUXYSUSE23LNGWN","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":"69d7de98b5cca8b70c351c71363e48159b45d6023207f529d4a0e12f58bea065","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T14:33:56Z","title_canon_sha256":"a340daf42ce8ee3363e62c82c440dc2126bb22075b46d11d4229ab7a9e798e6c"},"schema_version":"1.0","source":{"id":"2406.12663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12663","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12663v1","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12663","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"pith_short_12","alias_value":"DLECZMHE7PMV","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"pith_short_16","alias_value":"DLECZMHE7PMVUXYS","created_at":"2026-07-05T08:33:49Z"},{"alias_kind":"pith_short_8","alias_value":"DLECZMHE","created_at":"2026-07-05T08:33:49Z"}],"graph_snapshots":[{"event_id":"sha256:a5ef74cb91da14f6147fe4644bb248fd603f2aac838028e3321de2d291e32aff","target":"graph","created_at":"2026-07-05T08:33:49Z","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/2406.12663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) excel in integrating visual and linguistic contexts to produce detailed content, facilitating applications such as image captioning. However, using LVLMs to generate descriptions often faces the challenge of object hallucination (OH), where the output text misrepresents actual objects in the input image. While previous studies attribute the occurrence of OH to the inclusion of more details, our study finds technical flaws in existing metrics, leading to unreliable evaluations of models and conclusions about OH. This has sparked a debate on the question: Do ","authors_text":"Chenliang Xu, Mingqian Feng, Yunlong Tang, Zeliang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T14:33:56Z","title":"Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12663","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:bf8ea66e18d8348040771ffe554274f8001225db26daf13fa6541906c74588b7","target":"record","created_at":"2026-07-05T08:33:49Z","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":"69d7de98b5cca8b70c351c71363e48159b45d6023207f529d4a0e12f58bea065","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-18T14:33:56Z","title_canon_sha256":"a340daf42ce8ee3363e62c82c440dc2126bb22075b46d11d4229ab7a9e798e6c"},"schema_version":"1.0","source":{"id":"2406.12663","kind":"arxiv","version":1}},"canonical_sha256":"1ac82cb0e4fbd95a5f12a489adada6b34c226096791420fa566b548a69901f01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ac82cb0e4fbd95a5f12a489adada6b34c226096791420fa566b548a69901f01","first_computed_at":"2026-07-05T08:33:49.246140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:49.246140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NJJCRmv/s+klZmJH2JmvgeYQSYM6vTX2K29AvgWu0POaa1/GVkMzRHGDK+ya1cyzVVDydbkX5tSMjI/aUuFLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:49.246603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf8ea66e18d8348040771ffe554274f8001225db26daf13fa6541906c74588b7","sha256:a5ef74cb91da14f6147fe4644bb248fd603f2aac838028e3321de2d291e32aff"],"state_sha256":"33faf79489939eab26359c17200f30e9e3af0954462dda44e37c3b452de31914"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxNrcF9lzv05ziKos/1l3PIsHlgzHoUowmeXHoLFNh3lHIBMn8kVI6FXcgR6SYgLJLIZktuebAnvvTOHW7m2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T06:53:27.210771Z","bundle_sha256":"210cd473ce46f444c9d890f3a3c171feebe46cf7a88572f0a291da945472ee25"}}