{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TDHKBUWAF6HA6X7YQORJUMRVW3","short_pith_number":"pith:TDHKBUWA","canonical_record":{"source":{"id":"2409.01584","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T03:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"0136dedd6da18293bd47efd4c781c5cd15f92a156553b8f725d84eda872452c4","abstract_canon_sha256":"0b0ccd3af6ba23dc0af2125b0b702437dfa099d24f9a801f39e4b5249e12043f"},"schema_version":"1.0"},"canonical_sha256":"98cea0d2c02f8e0f5ff883a29a3235b6f02babd0faafb81022d4add7c9e67965","source":{"kind":"arxiv","id":"2409.01584","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01584","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01584v2","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01584","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"TDHKBUWAF6HA","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"TDHKBUWAF6HA6X7Y","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"TDHKBUWA","created_at":"2026-07-05T10:14:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TDHKBUWAF6HA6X7YQORJUMRVW3","target":"record","payload":{"canonical_record":{"source":{"id":"2409.01584","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T03:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"0136dedd6da18293bd47efd4c781c5cd15f92a156553b8f725d84eda872452c4","abstract_canon_sha256":"0b0ccd3af6ba23dc0af2125b0b702437dfa099d24f9a801f39e4b5249e12043f"},"schema_version":"1.0"},"canonical_sha256":"98cea0d2c02f8e0f5ff883a29a3235b6f02babd0faafb81022d4add7c9e67965","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:04.994506Z","signature_b64":"FgH9/y6oOP3+HyE/xGHINgyH03lwVrOUY5v9XaHmTbMRSjNa5yfNbCeD8gzOkpYlgXgPDZuYNuSJ2PBlwwVFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98cea0d2c02f8e0f5ff883a29a3235b6f02babd0faafb81022d4add7c9e67965","last_reissued_at":"2026-07-05T10:14:04.993715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:04.993715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.01584","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":"2026-07-05T10:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5sptI2dgUgI4usVtSE8yBsPvLDn2EFRPJR0oc6BY8eke1EgLvHueIdEAuUaObMPq1dYWHeE+2ZZFulEm6ZYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:18:21.701000Z"},"content_sha256":"98726aad56cd4f5d4331f9af16fc05852f6019ca87f91d3f91197b32cbabcaa2","schema_version":"1.0","event_id":"sha256:98726aad56cd4f5d4331f9af16fc05852f6019ca87f91d3f91197b32cbabcaa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TDHKBUWAF6HA6X7YQORJUMRVW3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hidetaka Kamigaito, Katsuhiko Hayashi, Kazuki Hayashi, Shintaro Ozaki, Taro Watanabe, Yusuke Sakai","submitted_at":"2024-09-03T03:42:56Z","abstract_excerpt":"As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the demand for explanations generated by LVLMs will grow. However, pre-training of Vision Encoder and the integrated training of LLMs with Vision Encoder are mainly conducted using English training data, leaving it uncertain whether LVLMs can completely handle their potential when generating explanations in languages other than English. In addition, multilingual QA benchmarks that create datasets using machine translation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01584","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/2409.01584/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":"2026-07-05T10:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4L+dJH/jZlLeHaTHYNM71LWyRpN6RTXP9GQ3eOaSwefs5qwrItojsBt8lVOhCujCcrQ5kylD81gGZPQHD8xBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:18:21.701648Z"},"content_sha256":"cf8c220da72daa874983ac2d3ee68077d69539f6d1b7b016f1d4b61c7faad442","schema_version":"1.0","event_id":"sha256:cf8c220da72daa874983ac2d3ee68077d69539f6d1b7b016f1d4b61c7faad442"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDHKBUWAF6HA6X7YQORJUMRVW3/bundle.json","state_url":"https://pith.science/pith/TDHKBUWAF6HA6X7YQORJUMRVW3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDHKBUWAF6HA6X7YQORJUMRVW3/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":"2026-08-09T21:18:21Z","links":{"resolver":"https://pith.science/pith/TDHKBUWAF6HA6X7YQORJUMRVW3","bundle":"https://pith.science/pith/TDHKBUWAF6HA6X7YQORJUMRVW3/bundle.json","state":"https://pith.science/pith/TDHKBUWAF6HA6X7YQORJUMRVW3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDHKBUWAF6HA6X7YQORJUMRVW3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TDHKBUWAF6HA6X7YQORJUMRVW3","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":"0b0ccd3af6ba23dc0af2125b0b702437dfa099d24f9a801f39e4b5249e12043f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T03:42:56Z","title_canon_sha256":"0136dedd6da18293bd47efd4c781c5cd15f92a156553b8f725d84eda872452c4"},"schema_version":"1.0","source":{"id":"2409.01584","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01584","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01584v2","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01584","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"TDHKBUWAF6HA","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"TDHKBUWAF6HA6X7Y","created_at":"2026-07-05T10:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"TDHKBUWA","created_at":"2026-07-05T10:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:cf8c220da72daa874983ac2d3ee68077d69539f6d1b7b016f1d4b61c7faad442","target":"graph","created_at":"2026-07-05T10:14:04Z","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/2409.01584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the demand for explanations generated by LVLMs will grow. However, pre-training of Vision Encoder and the integrated training of LLMs with Vision Encoder are mainly conducted using English training data, leaving it uncertain whether LVLMs can completely handle their potential when generating explanations in languages other than English. In addition, multilingual QA benchmarks that create datasets using machine translation","authors_text":"Hidetaka Kamigaito, Katsuhiko Hayashi, Kazuki Hayashi, Shintaro Ozaki, Taro Watanabe, Yusuke Sakai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T03:42:56Z","title":"Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01584","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":"sha256:98726aad56cd4f5d4331f9af16fc05852f6019ca87f91d3f91197b32cbabcaa2","target":"record","created_at":"2026-07-05T10:14:04Z","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":"0b0ccd3af6ba23dc0af2125b0b702437dfa099d24f9a801f39e4b5249e12043f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T03:42:56Z","title_canon_sha256":"0136dedd6da18293bd47efd4c781c5cd15f92a156553b8f725d84eda872452c4"},"schema_version":"1.0","source":{"id":"2409.01584","kind":"arxiv","version":2}},"canonical_sha256":"98cea0d2c02f8e0f5ff883a29a3235b6f02babd0faafb81022d4add7c9e67965","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98cea0d2c02f8e0f5ff883a29a3235b6f02babd0faafb81022d4add7c9e67965","first_computed_at":"2026-07-05T10:14:04.993715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:04.993715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FgH9/y6oOP3+HyE/xGHINgyH03lwVrOUY5v9XaHmTbMRSjNa5yfNbCeD8gzOkpYlgXgPDZuYNuSJ2PBlwwVFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:04.994506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01584","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98726aad56cd4f5d4331f9af16fc05852f6019ca87f91d3f91197b32cbabcaa2","sha256:cf8c220da72daa874983ac2d3ee68077d69539f6d1b7b016f1d4b61c7faad442"],"state_sha256":"9ccaed5d97f7fee557d7a6ff32ea35afc606848da5ed3307cb51f1de96e1c90c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4MDUIWvA8Sv6EBxpaLE+Gb+VQKfTdFk1lpTME/xFJi8pXUJehia9mOCVaLRRYx+Hr4oxNeLJXATnTxOAu7NAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:18:21.706156Z","bundle_sha256":"9018ed0d33f0edd40d79d61c980f7938f8f2a828b9dada25dbb52e2274337cd2"}}