{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZDO2YRAKJRGEXUYDY3WTHOX73T","short_pith_number":"pith:ZDO2YRAK","schema_version":"1.0","canonical_sha256":"c8ddac440a4c4c4bd303c6ed33baffdcd994b953f0866196cf0fa01786830916","source":{"kind":"arxiv","id":"2311.13614","version":2},"attestation_state":"computed","paper":{"title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bosheng Qin, Juncheng Li, Liang Pang, Longhui Wei, Qifan Yu, Qi Tian, Siliang Tang, Wentao Ye, Yueting Zhuang","submitted_at":"2023-11-22T04:52:58Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks. However, the hallucinations inherent in machine-generated data, which could lead to hallucinatory outputs in MLLMs, remain under-explored. This work aims to investigate various hallucinations (i.e., object, relation, attribute hallucinations) and mitigate those hallucinatory toxicities in large-scale machine-generated visual instruction datasets. Drawing on the human ability to identify factual errors"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.13614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T04:52:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59669edf640551c7abbd0dfbef785dc145e26e7c97923fcd5a43d79426f8a9f2","abstract_canon_sha256":"8c96ece983c30e1d396ef53607bc410f58fb28b9b3db178e2ba2761ae19daf0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:57.731881Z","signature_b64":"VU8a71699JhAiJh1t8jZBZMhvVWPIBlILpLQCyEyK/sMJlwHOTNRetk6Gy7/0tEtdW0JwD+Qayczn/mXyi+pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8ddac440a4c4c4bd303c6ed33baffdcd994b953f0866196cf0fa01786830916","last_reissued_at":"2026-07-05T07:59:57.731391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:57.731391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bosheng Qin, Juncheng Li, Liang Pang, Longhui Wei, Qifan Yu, Qi Tian, Siliang Tang, Wentao Ye, Yueting Zhuang","submitted_at":"2023-11-22T04:52:58Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks. However, the hallucinations inherent in machine-generated data, which could lead to hallucinatory outputs in MLLMs, remain under-explored. This work aims to investigate various hallucinations (i.e., object, relation, attribute hallucinations) and mitigate those hallucinatory toxicities in large-scale machine-generated visual instruction datasets. Drawing on the human ability to identify factual errors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13614","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/2311.13614/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.13614","created_at":"2026-07-05T07:59:57.731451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13614v2","created_at":"2026-07-05T07:59:57.731451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13614","created_at":"2026-07-05T07:59:57.731451+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDO2YRAKJRGE","created_at":"2026-07-05T07:59:57.731451+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDO2YRAKJRGEXUYD","created_at":"2026-07-05T07:59:57.731451+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDO2YRAK","created_at":"2026-07-05T07:59:57.731451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13156","citing_title":"Dual-Pathway Circuits of Object Hallucination in Vision-Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":196,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T","json":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T.json","graph_json":"https://pith.science/api/pith-number/ZDO2YRAKJRGEXUYDY3WTHOX73T/graph.json","events_json":"https://pith.science/api/pith-number/ZDO2YRAKJRGEXUYDY3WTHOX73T/events.json","paper":"https://pith.science/paper/ZDO2YRAK"},"agent_actions":{"view_html":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T","download_json":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T.json","view_paper":"https://pith.science/paper/ZDO2YRAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13614&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDO2YRAKJRGEXUYDY3WTHOX73T/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDO2YRAKJRGEXUYDY3WTHOX73T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T/action/storage_attestation","attest_author":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T/action/author_attestation","sign_citation":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T/action/citation_signature","submit_replication":"https://pith.science/pith/ZDO2YRAKJRGEXUYDY3WTHOX73T/action/replication_record"}},"created_at":"2026-07-05T07:59:57.731451+00:00","updated_at":"2026-07-05T07:59:57.731451+00:00"}