{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ER4LK3QH7JW7JBIDO6ZRAPN2VN","short_pith_number":"pith:ER4LK3QH","schema_version":"1.0","canonical_sha256":"2478b56e07fa6df4850377b3103dbaab7ee63ab887e5c790acc2f118d4c39cd7","source":{"kind":"arxiv","id":"2408.01355","version":2},"attestation_state":"computed","paper":{"title":"Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Ma, Jiajun Chen, Jingyu Wu, Jun Kuang, Peng Ding, Shi Chen, Shujian Huang, Xuezhi Cao, Xunliang Cai","submitted_at":"2024-08-02T16:07:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on various visual-language understanding and generation tasks. However, MLLMs occasionally generate content inconsistent with the given images, which is known as \"hallucination\". Prior works primarily center on evaluating hallucination using standard, unperturbed benchmarks, which overlook the prevalent occurrence of perturbed inputs in real-world scenarios-such as image cropping or blurring-that are critical for a comprehensive assessment of MLLMs' hallucination. In this paper, to bridge this gap, we propose Ha"},"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":"2408.01355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-02T16:07:15Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"67a2232beac4cf18a63f151155d593eb32ac4269358a526f1b84dd1c9119ab04","abstract_canon_sha256":"ab27ed9dad406f44fd460d28b592547e13dddf2cd05f8daf9b6bb66e4d70020d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:57.572016Z","signature_b64":"ngw30ufoccD3/BW0OpyLm2Jkpf2mr2hf47q5nSMqMMpn78tulfWKhClylWjJs1vtMsRFvx4UMHjEjm0aEai5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2478b56e07fa6df4850377b3103dbaab7ee63ab887e5c790acc2f118d4c39cd7","last_reissued_at":"2026-07-05T08:51:57.571611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:57.571611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Ma, Jiajun Chen, Jingyu Wu, Jun Kuang, Peng Ding, Shi Chen, Shujian Huang, Xuezhi Cao, Xunliang Cai","submitted_at":"2024-08-02T16:07:15Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on various visual-language understanding and generation tasks. However, MLLMs occasionally generate content inconsistent with the given images, which is known as \"hallucination\". Prior works primarily center on evaluating hallucination using standard, unperturbed benchmarks, which overlook the prevalent occurrence of perturbed inputs in real-world scenarios-such as image cropping or blurring-that are critical for a comprehensive assessment of MLLMs' hallucination. In this paper, to bridge this gap, we propose Ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01355","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/2408.01355/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":"2408.01355","created_at":"2026-07-05T08:51:57.571658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01355v2","created_at":"2026-07-05T08:51:57.571658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01355","created_at":"2026-07-05T08:51:57.571658+00:00"},{"alias_kind":"pith_short_12","alias_value":"ER4LK3QH7JW7","created_at":"2026-07-05T08:51:57.571658+00:00"},{"alias_kind":"pith_short_16","alias_value":"ER4LK3QH7JW7JBID","created_at":"2026-07-05T08:51:57.571658+00:00"},{"alias_kind":"pith_short_8","alias_value":"ER4LK3QH","created_at":"2026-07-05T08:51:57.571658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN","json":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN.json","graph_json":"https://pith.science/api/pith-number/ER4LK3QH7JW7JBIDO6ZRAPN2VN/graph.json","events_json":"https://pith.science/api/pith-number/ER4LK3QH7JW7JBIDO6ZRAPN2VN/events.json","paper":"https://pith.science/paper/ER4LK3QH"},"agent_actions":{"view_html":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN","download_json":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN.json","view_paper":"https://pith.science/paper/ER4LK3QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01355&json=true","fetch_graph":"https://pith.science/api/pith-number/ER4LK3QH7JW7JBIDO6ZRAPN2VN/graph.json","fetch_events":"https://pith.science/api/pith-number/ER4LK3QH7JW7JBIDO6ZRAPN2VN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN/action/storage_attestation","attest_author":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN/action/author_attestation","sign_citation":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN/action/citation_signature","submit_replication":"https://pith.science/pith/ER4LK3QH7JW7JBIDO6ZRAPN2VN/action/replication_record"}},"created_at":"2026-07-05T08:51:57.571658+00:00","updated_at":"2026-07-05T08:51:57.571658+00:00"}