{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RBJJNCEDGBP3UGU3M4XOBLGUVV","short_pith_number":"pith:RBJJNCED","canonical_record":{"source":{"id":"2410.12787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"f7563f0c78f8b31092442bcaa902cfabf7207b5bae3729eb9a8f42aa3661af08","abstract_canon_sha256":"5bbe88fa22a2610e60e168ee1c34017278914771038f57d61d73049872f6ca2c"},"schema_version":"1.0"},"canonical_sha256":"8852968883305fba1a9b672ee0acd4ad7e650c61894ae29513d3dd3f934cae82","source":{"kind":"arxiv","id":"2410.12787","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12787","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12787v1","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12787","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"RBJJNCEDGBP3","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"pith_short_16","alias_value":"RBJJNCEDGBP3UGU3","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"pith_short_8","alias_value":"RBJJNCED","created_at":"2026-07-05T09:21:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RBJJNCEDGBP3UGU3M4XOBLGUVV","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"f7563f0c78f8b31092442bcaa902cfabf7207b5bae3729eb9a8f42aa3661af08","abstract_canon_sha256":"5bbe88fa22a2610e60e168ee1c34017278914771038f57d61d73049872f6ca2c"},"schema_version":"1.0"},"canonical_sha256":"8852968883305fba1a9b672ee0acd4ad7e650c61894ae29513d3dd3f934cae82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:33.972817Z","signature_b64":"LImGsQhm0o3LfG4hYHLoGQ4UweE5RrY5UOK10EqNB1Txfp1LFhitGvNOR7kdz5WVyjiuXLXTDgOoXn6P+/L8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8852968883305fba1a9b672ee0acd4ad7e650c61894ae29513d3dd3f934cae82","last_reissued_at":"2026-07-05T09:21:33.972333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:33.972333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12787","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":"2026-07-05T09:21:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lN5MKuSPYpVspOUOoHIZb4EWkQaj7o2n9mQ4sTEG1SA4BKeuPOXWpndzkQ2W0hyQ4I9QqErOmOZ+z/QAKe4XBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:05:34.306348Z"},"content_sha256":"132d8f7b33f9a9fefbf16dbe0cce8cca80f1397a8c00fc70edc9aefd0047a9fb","schema_version":"1.0","event_id":"sha256:132d8f7b33f9a9fefbf16dbe0cce8cca80f1397a8c00fc70edc9aefd0047a9fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RBJJNCEDGBP3UGU3M4XOBLGUVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyan Miao, Deli Zhao, Hang Zhang, Lidong Bing, Shijian Lu, Sicong Leng, Xin Li, Yang Zhou, Yun Xing, Zesen Cheng","submitted_at":"2024-10-16T17:59:02Z","abstract_excerpt":"Recent advancements in large multimodal models (LMMs) have significantly enhanced performance across diverse tasks, with ongoing efforts to further integrate additional modalities such as video and audio. However, most existing LMMs remain vulnerable to hallucinations, the discrepancy between the factual multimodal input and the generated textual output, which has limited their applicability in various real-world scenarios. This paper presents the first systematic investigation of hallucinations in LMMs involving the three most common modalities: language, visual, and audio. Our study reveals "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12787","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/2410.12787/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":"2026-07-05T09:21:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uimtdbf6WMfX34Qp0UM7jsX1yuuGX9AnzSQAzrifPaNi6gTI1O6uqkWUhUUb8vS6ERjXWM6p0vn9YSks5akLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:05:34.306685Z"},"content_sha256":"76f74286efe37537345ff525bdb9b545e4bae8f31333590adcfdd0d3c5db67a2","schema_version":"1.0","event_id":"sha256:76f74286efe37537345ff525bdb9b545e4bae8f31333590adcfdd0d3c5db67a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RBJJNCEDGBP3UGU3M4XOBLGUVV/bundle.json","state_url":"https://pith.science/pith/RBJJNCEDGBP3UGU3M4XOBLGUVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RBJJNCEDGBP3UGU3M4XOBLGUVV/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":"2026-08-20T17:05:34Z","links":{"resolver":"https://pith.science/pith/RBJJNCEDGBP3UGU3M4XOBLGUVV","bundle":"https://pith.science/pith/RBJJNCEDGBP3UGU3M4XOBLGUVV/bundle.json","state":"https://pith.science/pith/RBJJNCEDGBP3UGU3M4XOBLGUVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RBJJNCEDGBP3UGU3M4XOBLGUVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RBJJNCEDGBP3UGU3M4XOBLGUVV","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":"5bbe88fa22a2610e60e168ee1c34017278914771038f57d61d73049872f6ca2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T17:59:02Z","title_canon_sha256":"f7563f0c78f8b31092442bcaa902cfabf7207b5bae3729eb9a8f42aa3661af08"},"schema_version":"1.0","source":{"id":"2410.12787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12787","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12787v1","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12787","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"RBJJNCEDGBP3","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"pith_short_16","alias_value":"RBJJNCEDGBP3UGU3","created_at":"2026-07-05T09:21:33Z"},{"alias_kind":"pith_short_8","alias_value":"RBJJNCED","created_at":"2026-07-05T09:21:33Z"}],"graph_snapshots":[{"event_id":"sha256:76f74286efe37537345ff525bdb9b545e4bae8f31333590adcfdd0d3c5db67a2","target":"graph","created_at":"2026-07-05T09:21:33Z","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/2410.12787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large multimodal models (LMMs) have significantly enhanced performance across diverse tasks, with ongoing efforts to further integrate additional modalities such as video and audio. However, most existing LMMs remain vulnerable to hallucinations, the discrepancy between the factual multimodal input and the generated textual output, which has limited their applicability in various real-world scenarios. This paper presents the first systematic investigation of hallucinations in LMMs involving the three most common modalities: language, visual, and audio. Our study reveals ","authors_text":"Chunyan Miao, Deli Zhao, Hang Zhang, Lidong Bing, Shijian Lu, Sicong Leng, Xin Li, Yang Zhou, Yun Xing, Zesen Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T17:59:02Z","title":"The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12787","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":"sha256:132d8f7b33f9a9fefbf16dbe0cce8cca80f1397a8c00fc70edc9aefd0047a9fb","target":"record","created_at":"2026-07-05T09:21:33Z","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":"5bbe88fa22a2610e60e168ee1c34017278914771038f57d61d73049872f6ca2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-16T17:59:02Z","title_canon_sha256":"f7563f0c78f8b31092442bcaa902cfabf7207b5bae3729eb9a8f42aa3661af08"},"schema_version":"1.0","source":{"id":"2410.12787","kind":"arxiv","version":1}},"canonical_sha256":"8852968883305fba1a9b672ee0acd4ad7e650c61894ae29513d3dd3f934cae82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8852968883305fba1a9b672ee0acd4ad7e650c61894ae29513d3dd3f934cae82","first_computed_at":"2026-07-05T09:21:33.972333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:33.972333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LImGsQhm0o3LfG4hYHLoGQ4UweE5RrY5UOK10EqNB1Txfp1LFhitGvNOR7kdz5WVyjiuXLXTDgOoXn6P+/L8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:33.972817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:132d8f7b33f9a9fefbf16dbe0cce8cca80f1397a8c00fc70edc9aefd0047a9fb","sha256:76f74286efe37537345ff525bdb9b545e4bae8f31333590adcfdd0d3c5db67a2"],"state_sha256":"5c228d51324f9b51ffd976c79f04df39eb21704f64dd80eeaa70f19ea7668036"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knY37NrkefC+M4OGTk59+1aRdY05bEvvM81p+USF/NDiPpqoQ0mJy9XmdN0UIv76zHHg7PPo90bqfptS7b4wAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:05:34.310078Z","bundle_sha256":"c29af8abdce4a04608dc7955132675a9deb75c985de8ad7b63188302959cce24"}}