{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M5IZUQHXYVL6HITFK5BZNIOYAA","short_pith_number":"pith:M5IZUQHX","canonical_record":{"source":{"id":"2410.06795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T11:46:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2fd0739ea53ce4f766140e51ac14787bce61fb2f536b94620eb94df01e1a6cf5","abstract_canon_sha256":"5e33e32909408e7926ee3210a06495c0cf863e0fdfd109a0be061c1083dd00c9"},"schema_version":"1.0"},"canonical_sha256":"67519a40f7c557e3a265574396a1d8002e171f4ca848d0e094643ecb66510fe6","source":{"kind":"arxiv","id":"2410.06795","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06795","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06795v2","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06795","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"M5IZUQHXYVL6","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"M5IZUQHXYVL6HITF","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"M5IZUQHX","created_at":"2026-07-05T11:52:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M5IZUQHXYVL6HITFK5BZNIOYAA","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T11:46:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2fd0739ea53ce4f766140e51ac14787bce61fb2f536b94620eb94df01e1a6cf5","abstract_canon_sha256":"5e33e32909408e7926ee3210a06495c0cf863e0fdfd109a0be061c1083dd00c9"},"schema_version":"1.0"},"canonical_sha256":"67519a40f7c557e3a265574396a1d8002e171f4ca848d0e094643ecb66510fe6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:15.186587Z","signature_b64":"5sQLkR/UNtJeRT3xARFlFyX6IutqBsvXt3uAvPiVb36ZSK+IdgzZd83raP13az4jVb+87r2OQPTXYkHo5vb5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67519a40f7c557e3a265574396a1d8002e171f4ca848d0e094643ecb66510fe6","last_reissued_at":"2026-07-05T11:52:15.186136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:15.186136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06795","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":"2026-07-05T11:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+1mLKevCLboBump0+ERX/f9Uyv+0kwIKtgyqOlmojSVW0g+7g9voCMLJQ4E77DMwootXbH+v59p9kEua/TRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:24.046256Z"},"content_sha256":"e7285edf2c70db339d3d0bebf778510b95877d9f76e5dd986d0ceebe9ab5a6a9","schema_version":"1.0","event_id":"sha256:e7285edf2c70db339d3d0bebf778510b95877d9f76e5dd986d0ceebe9ab5a6a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M5IZUQHXYVL6HITFK5BZNIOYAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jiawei Chen, Jingyuan Zhang, Xiao Yang, Xinyi Zeng, Yutao Zhu, Yu Tian, Yuying Shang, Zhengwei Fang, Zinan Liu","submitted_at":"2024-10-09T11:46:32Z","abstract_excerpt":"Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to effectively extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06795","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/2410.06795/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":"2026-07-05T11:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McOsE8sRTmIEboPvDkOS5JFpmwE5dXGqZlFnsoSTWBJNDUx8TJXuEHyxIFswMM4KQaQBB5iyxV9/AgMhcZ1/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:24.046754Z"},"content_sha256":"b62cd9a1d46c03a680bf89ecb0ccc534523365c11602225be33b79ee8c35c276","schema_version":"1.0","event_id":"sha256:b62cd9a1d46c03a680bf89ecb0ccc534523365c11602225be33b79ee8c35c276"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5IZUQHXYVL6HITFK5BZNIOYAA/bundle.json","state_url":"https://pith.science/pith/M5IZUQHXYVL6HITFK5BZNIOYAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5IZUQHXYVL6HITFK5BZNIOYAA/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":"2026-08-08T19:21:24Z","links":{"resolver":"https://pith.science/pith/M5IZUQHXYVL6HITFK5BZNIOYAA","bundle":"https://pith.science/pith/M5IZUQHXYVL6HITFK5BZNIOYAA/bundle.json","state":"https://pith.science/pith/M5IZUQHXYVL6HITFK5BZNIOYAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5IZUQHXYVL6HITFK5BZNIOYAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M5IZUQHXYVL6HITFK5BZNIOYAA","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":"5e33e32909408e7926ee3210a06495c0cf863e0fdfd109a0be061c1083dd00c9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T11:46:32Z","title_canon_sha256":"2fd0739ea53ce4f766140e51ac14787bce61fb2f536b94620eb94df01e1a6cf5"},"schema_version":"1.0","source":{"id":"2410.06795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06795","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06795v2","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06795","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"M5IZUQHXYVL6","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"M5IZUQHXYVL6HITF","created_at":"2026-07-05T11:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"M5IZUQHX","created_at":"2026-07-05T11:52:15Z"}],"graph_snapshots":[{"event_id":"sha256:b62cd9a1d46c03a680bf89ecb0ccc534523365c11602225be33b79ee8c35c276","target":"graph","created_at":"2026-07-05T11:52:15Z","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/2410.06795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to effectively extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (featu","authors_text":"Jiawei Chen, Jingyuan Zhang, Xiao Yang, Xinyi Zeng, Yutao Zhu, Yu Tian, Yuying Shang, Zhengwei Fang, Zinan Liu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T11:46:32Z","title":"From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06795","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:e7285edf2c70db339d3d0bebf778510b95877d9f76e5dd986d0ceebe9ab5a6a9","target":"record","created_at":"2026-07-05T11:52:15Z","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":"5e33e32909408e7926ee3210a06495c0cf863e0fdfd109a0be061c1083dd00c9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T11:46:32Z","title_canon_sha256":"2fd0739ea53ce4f766140e51ac14787bce61fb2f536b94620eb94df01e1a6cf5"},"schema_version":"1.0","source":{"id":"2410.06795","kind":"arxiv","version":2}},"canonical_sha256":"67519a40f7c557e3a265574396a1d8002e171f4ca848d0e094643ecb66510fe6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67519a40f7c557e3a265574396a1d8002e171f4ca848d0e094643ecb66510fe6","first_computed_at":"2026-07-05T11:52:15.186136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:15.186136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5sQLkR/UNtJeRT3xARFlFyX6IutqBsvXt3uAvPiVb36ZSK+IdgzZd83raP13az4jVb+87r2OQPTXYkHo5vb5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:15.186587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7285edf2c70db339d3d0bebf778510b95877d9f76e5dd986d0ceebe9ab5a6a9","sha256:b62cd9a1d46c03a680bf89ecb0ccc534523365c11602225be33b79ee8c35c276"],"state_sha256":"9cdab429d798decf6211bb55602b075e72705b0debf7ec8c09314d097f7c407f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuxdBB9e+yvz6ZUTcqbhBOS62oZmks8IbmXe1DlWOu0yjaQ2r2UasuFJBhPNPaIjVh2tUBYFtb6NeJUFxowPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:21:24.050351Z","bundle_sha256":"9085aeb8ac87bfe49bf7c3c640e07b2a8e87c85d9d245edd9d7661f8f61d0208"}}