{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UBEL7N3ZIJFXDF252QW2ORYISU","short_pith_number":"pith:UBEL7N3Z","canonical_record":{"source":{"id":"2402.14683","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T16:40:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"778ac379079ebf21c1bdfc4b1d636ab237623f72e73ab3503aeb4b62b92d2acf","abstract_canon_sha256":"92c8f901cbcc96a5f79d853186ad8a30a735039f465ff98054b1738e1dae45c1"},"schema_version":"1.0"},"canonical_sha256":"a048bfb779424b71975dd42da74708952c3d4f04d07879c203a2e3a75ff66e42","source":{"kind":"arxiv","id":"2402.14683","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14683","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14683v2","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14683","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"UBEL7N3ZIJFX","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"UBEL7N3ZIJFXDF25","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"UBEL7N3Z","created_at":"2026-07-05T08:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UBEL7N3ZIJFXDF252QW2ORYISU","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14683","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T16:40:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"778ac379079ebf21c1bdfc4b1d636ab237623f72e73ab3503aeb4b62b92d2acf","abstract_canon_sha256":"92c8f901cbcc96a5f79d853186ad8a30a735039f465ff98054b1738e1dae45c1"},"schema_version":"1.0"},"canonical_sha256":"a048bfb779424b71975dd42da74708952c3d4f04d07879c203a2e3a75ff66e42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:37.475086Z","signature_b64":"LZtjdq3P2Osh0SlNGkqYkICTOKx2LBwxerbqFf7254JNeY9F4dreEyXHyj35bR1JpsNAe7bTA18DnnEg2yT+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a048bfb779424b71975dd42da74708952c3d4f04d07879c203a2e3a75ff66e42","last_reissued_at":"2026-07-05T08:32:37.474602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:37.474602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14683","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":"2026-07-05T08:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rOgd+cL7XLhLqWPiw/FtLqULndc+q+oeUk8pAnALtkhfjgbSDMl2z2ddicMIGU2BICmZ0rOQMg7deDc1Y7DBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:54:57.559636Z"},"content_sha256":"bee780dd9a5bba9f380a17976f6cb03aeacae03374bad027e704c3b769223994","schema_version":"1.0","event_id":"sha256:bee780dd9a5bba9f380a17976f6cb03aeacae03374bad027e704c3b769223994"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UBEL7N3ZIJFXDF252QW2ORYISU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Hallucinations of Multi-modal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hongbin Liu, Minxin Guo, Neil Zhenqiang Gong, Wen Huang","submitted_at":"2024-02-22T16:40:33Z","abstract_excerpt":"Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines incorrect details about an image in visual question answering. Existing studies find VH instances only in existing image datasets, which results in biased understanding of MLLMs' performance under VH due to limited diversity of such VH instances. In this work, we propose a tool called VHTest to generate a diverse set of VH instances. Specifically, VHTest finds some initial VH instances in existing image datasets (e.g., COCO), generates a text description for each VH mode, and uses a text-to-image generative model (e.g., DAL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14683","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/2402.14683/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":"2026-07-05T08:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DyB070YG/4ICZRXUeQI2P/2dagOplTwVn4AEXxpJjU5ojPZyXqX5JbbQyUYJtrFMjUQGE4xlyKnUZKcarJpIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:54:57.561017Z"},"content_sha256":"f7e14c1c34c242a43066002940dda7e79bd74413e8f86c235f120c1ff9f1767c","schema_version":"1.0","event_id":"sha256:f7e14c1c34c242a43066002940dda7e79bd74413e8f86c235f120c1ff9f1767c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBEL7N3ZIJFXDF252QW2ORYISU/bundle.json","state_url":"https://pith.science/pith/UBEL7N3ZIJFXDF252QW2ORYISU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBEL7N3ZIJFXDF252QW2ORYISU/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":"2026-08-05T04:54:57Z","links":{"resolver":"https://pith.science/pith/UBEL7N3ZIJFXDF252QW2ORYISU","bundle":"https://pith.science/pith/UBEL7N3ZIJFXDF252QW2ORYISU/bundle.json","state":"https://pith.science/pith/UBEL7N3ZIJFXDF252QW2ORYISU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBEL7N3ZIJFXDF252QW2ORYISU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UBEL7N3ZIJFXDF252QW2ORYISU","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":"92c8f901cbcc96a5f79d853186ad8a30a735039f465ff98054b1738e1dae45c1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T16:40:33Z","title_canon_sha256":"778ac379079ebf21c1bdfc4b1d636ab237623f72e73ab3503aeb4b62b92d2acf"},"schema_version":"1.0","source":{"id":"2402.14683","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14683","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14683v2","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14683","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"UBEL7N3ZIJFX","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"UBEL7N3ZIJFXDF25","created_at":"2026-07-05T08:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"UBEL7N3Z","created_at":"2026-07-05T08:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:f7e14c1c34c242a43066002940dda7e79bd74413e8f86c235f120c1ff9f1767c","target":"graph","created_at":"2026-07-05T08:32:37Z","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/2402.14683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines incorrect details about an image in visual question answering. Existing studies find VH instances only in existing image datasets, which results in biased understanding of MLLMs' performance under VH due to limited diversity of such VH instances. In this work, we propose a tool called VHTest to generate a diverse set of VH instances. Specifically, VHTest finds some initial VH instances in existing image datasets (e.g., COCO), generates a text description for each VH mode, and uses a text-to-image generative model (e.g., DAL","authors_text":"Hongbin Liu, Minxin Guo, Neil Zhenqiang Gong, Wen Huang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T16:40:33Z","title":"Visual Hallucinations of Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14683","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:bee780dd9a5bba9f380a17976f6cb03aeacae03374bad027e704c3b769223994","target":"record","created_at":"2026-07-05T08:32:37Z","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":"92c8f901cbcc96a5f79d853186ad8a30a735039f465ff98054b1738e1dae45c1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-22T16:40:33Z","title_canon_sha256":"778ac379079ebf21c1bdfc4b1d636ab237623f72e73ab3503aeb4b62b92d2acf"},"schema_version":"1.0","source":{"id":"2402.14683","kind":"arxiv","version":2}},"canonical_sha256":"a048bfb779424b71975dd42da74708952c3d4f04d07879c203a2e3a75ff66e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a048bfb779424b71975dd42da74708952c3d4f04d07879c203a2e3a75ff66e42","first_computed_at":"2026-07-05T08:32:37.474602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:37.474602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LZtjdq3P2Osh0SlNGkqYkICTOKx2LBwxerbqFf7254JNeY9F4dreEyXHyj35bR1JpsNAe7bTA18DnnEg2yT+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:37.475086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14683","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bee780dd9a5bba9f380a17976f6cb03aeacae03374bad027e704c3b769223994","sha256:f7e14c1c34c242a43066002940dda7e79bd74413e8f86c235f120c1ff9f1767c"],"state_sha256":"24e0b9946aa7b92874828f0661c609e493040ab357a0ffe935f48644933b3166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kp3qk8TfJkgcXIaxb2wPf41Y4fRn5WyyvKBPZuZIfBdRTanA7rM/jNWrkv0g5948sQmYE3+pPFgretDQa/RZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:54:57.566629Z","bundle_sha256":"1475f8d36e38ac7bcbf75c7a36b8ebb45c13a23148f22e0fc6020138a72e0823"}}