{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YIOD67ROOAQXMNNQMBXOIPVOXL","short_pith_number":"pith:YIOD67RO","canonical_record":{"source":{"id":"2410.01023","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:32:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f80e937fb8ce3b89515d79ad4d89e9d57575ee04a81285c9e657f44f9b33d01c","abstract_canon_sha256":"e35decefade3145cb2455824971893b39502ee22d0660de887217b3f630674ef"},"schema_version":"1.0"},"canonical_sha256":"c21c3f7e2e70217635b0606ee43eaebac5ddd709e0ef59522373962d9e7e181d","source":{"kind":"arxiv","id":"2410.01023","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01023","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01023v2","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01023","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"YIOD67ROOAQX","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"YIOD67ROOAQXMNNQ","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"YIOD67RO","created_at":"2026-07-05T09:24:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YIOD67ROOAQXMNNQMBXOIPVOXL","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01023","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:32:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f80e937fb8ce3b89515d79ad4d89e9d57575ee04a81285c9e657f44f9b33d01c","abstract_canon_sha256":"e35decefade3145cb2455824971893b39502ee22d0660de887217b3f630674ef"},"schema_version":"1.0"},"canonical_sha256":"c21c3f7e2e70217635b0606ee43eaebac5ddd709e0ef59522373962d9e7e181d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:18.406048Z","signature_b64":"OPt+WwmbVz/tApq8W6HxO+W9CbtEIWuSNSpHvY8ngo2P25fTo4OQtkwR4KlizxnKyoXUeqGBySRjf/m206wdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c21c3f7e2e70217635b0606ee43eaebac5ddd709e0ef59522373962d9e7e181d","last_reissued_at":"2026-07-05T09:24:18.405494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:18.405494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01023","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":"2026-07-05T09:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JBpOnkFwGlgSMPtTcTG18w1/ENc5kyx3ZEfk/w9VQI5jAUIDES40jAExrZSfHpI9z24AZq8/tnnMR251tFjoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:03:36.303311Z"},"content_sha256":"adf8b246f43e86d29c79f72f36635119e25ac8cfc562c227994987580d83f8a4","schema_version":"1.0","event_id":"sha256:adf8b246f43e86d29c79f72f36635119e25ac8cfc562c227994987580d83f8a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YIOD67ROOAQXMNNQMBXOIPVOXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can visual language models resolve textual ambiguity with visual cues? Let visual puns tell you!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jaehyun Jeon, Jiwan Chung, Seungbeen Lee, Seungwon Lim, Youngjae Yu","submitted_at":"2024-10-01T19:32:57Z","abstract_excerpt":"Humans possess multimodal literacy, allowing them to actively integrate information from various modalities to form reasoning. Faced with challenges like lexical ambiguity in text, we supplement this with other modalities, such as thumbnail images or textbook illustrations. Is it possible for machines to achieve a similar multimodal understanding capability? In response, we present Understanding Pun with Image Explanations (UNPIE), a novel benchmark designed to assess the impact of multimodal inputs in resolving lexical ambiguities. Puns serve as the ideal subject for this evaluation due to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01023","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/2410.01023/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":"2026-07-05T09:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MiFU/mXz32g/K2IIkdW9PBUZXQW1tcR+yXaObra/waCPOiIBeuSrsIVSCQNbidh3hndha4WEhXGk7dQI2apDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:03:36.304409Z"},"content_sha256":"5f1c03329c86642fe4a9549a306f99c605fe79d16d35829efd70418420a66b9c","schema_version":"1.0","event_id":"sha256:5f1c03329c86642fe4a9549a306f99c605fe79d16d35829efd70418420a66b9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIOD67ROOAQXMNNQMBXOIPVOXL/bundle.json","state_url":"https://pith.science/pith/YIOD67ROOAQXMNNQMBXOIPVOXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIOD67ROOAQXMNNQMBXOIPVOXL/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":"2026-08-16T15:03:36Z","links":{"resolver":"https://pith.science/pith/YIOD67ROOAQXMNNQMBXOIPVOXL","bundle":"https://pith.science/pith/YIOD67ROOAQXMNNQMBXOIPVOXL/bundle.json","state":"https://pith.science/pith/YIOD67ROOAQXMNNQMBXOIPVOXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIOD67ROOAQXMNNQMBXOIPVOXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YIOD67ROOAQXMNNQMBXOIPVOXL","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":"e35decefade3145cb2455824971893b39502ee22d0660de887217b3f630674ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:32:57Z","title_canon_sha256":"f80e937fb8ce3b89515d79ad4d89e9d57575ee04a81285c9e657f44f9b33d01c"},"schema_version":"1.0","source":{"id":"2410.01023","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01023","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01023v2","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01023","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"YIOD67ROOAQX","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"YIOD67ROOAQXMNNQ","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"YIOD67RO","created_at":"2026-07-05T09:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:5f1c03329c86642fe4a9549a306f99c605fe79d16d35829efd70418420a66b9c","target":"graph","created_at":"2026-07-05T09:24:18Z","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/2410.01023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans possess multimodal literacy, allowing them to actively integrate information from various modalities to form reasoning. Faced with challenges like lexical ambiguity in text, we supplement this with other modalities, such as thumbnail images or textbook illustrations. Is it possible for machines to achieve a similar multimodal understanding capability? In response, we present Understanding Pun with Image Explanations (UNPIE), a novel benchmark designed to assess the impact of multimodal inputs in resolving lexical ambiguities. Puns serve as the ideal subject for this evaluation due to th","authors_text":"Jaehyun Jeon, Jiwan Chung, Seungbeen Lee, Seungwon Lim, Youngjae Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:32:57Z","title":"Can visual language models resolve textual ambiguity with visual cues? Let visual puns tell you!"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01023","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:adf8b246f43e86d29c79f72f36635119e25ac8cfc562c227994987580d83f8a4","target":"record","created_at":"2026-07-05T09:24:18Z","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":"e35decefade3145cb2455824971893b39502ee22d0660de887217b3f630674ef","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:32:57Z","title_canon_sha256":"f80e937fb8ce3b89515d79ad4d89e9d57575ee04a81285c9e657f44f9b33d01c"},"schema_version":"1.0","source":{"id":"2410.01023","kind":"arxiv","version":2}},"canonical_sha256":"c21c3f7e2e70217635b0606ee43eaebac5ddd709e0ef59522373962d9e7e181d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c21c3f7e2e70217635b0606ee43eaebac5ddd709e0ef59522373962d9e7e181d","first_computed_at":"2026-07-05T09:24:18.405494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:18.405494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OPt+WwmbVz/tApq8W6HxO+W9CbtEIWuSNSpHvY8ngo2P25fTo4OQtkwR4KlizxnKyoXUeqGBySRjf/m206wdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:18.406048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01023","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adf8b246f43e86d29c79f72f36635119e25ac8cfc562c227994987580d83f8a4","sha256:5f1c03329c86642fe4a9549a306f99c605fe79d16d35829efd70418420a66b9c"],"state_sha256":"663479b0dd14440086d5fdfb0a12514c9d93fd191bf4c6de08ba0b7a99d1825d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YmeA/v2iS1d2NOAEOU0wpmIssftfOZE/Q5vPJ2vc6rr8ob4xDpZ1yovV35MrNQPHkQ+nwA2x0R5rBwXJNfHxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T15:03:36.311875Z","bundle_sha256":"b34d9860b2bc62355f2a7cc8f539186377e99955f424bab7acea6fcd40c28fdc"}}