{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FIEY5VINW5OIZXZ4JVUL3L5GLS","short_pith_number":"pith:FIEY5VIN","canonical_record":{"source":{"id":"2402.05374","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T03:12:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bf433bf5d65b3035e451a5ee43ec233faad0693093e9c0d34ab10620527ee0c6","abstract_canon_sha256":"f33e013995ae46c9c0f1c1a4c4e131608cb62bfd6e62d81e1541a9eac19287a5"},"schema_version":"1.0"},"canonical_sha256":"2a098ed50db75c8cdf3c4d68bdafa65c9769990336cf66b55e60b7bb85fc24aa","source":{"kind":"arxiv","id":"2402.05374","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05374","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05374v5","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05374","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"FIEY5VINW5OI","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"FIEY5VINW5OIZXZ4","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"FIEY5VIN","created_at":"2026-07-05T10:18:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FIEY5VINW5OIZXZ4JVUL3L5GLS","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05374","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T03:12:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bf433bf5d65b3035e451a5ee43ec233faad0693093e9c0d34ab10620527ee0c6","abstract_canon_sha256":"f33e013995ae46c9c0f1c1a4c4e131608cb62bfd6e62d81e1541a9eac19287a5"},"schema_version":"1.0"},"canonical_sha256":"2a098ed50db75c8cdf3c4d68bdafa65c9769990336cf66b55e60b7bb85fc24aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:34.869780Z","signature_b64":"ipCp/D/DarNQ/2zSEXC4Z6eSeZh33ORBiGtbNJ65qx16ShOeD0XZn2l99v0Kw4zz8iSod2pdm02yxVrdLzP1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a098ed50db75c8cdf3c4d68bdafa65c9769990336cf66b55e60b7bb85fc24aa","last_reissued_at":"2026-07-05T10:18:34.869303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:34.869303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05374","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rC5wGpxxjXKquVUn7vRhdiT1vyLAAk5RzavDfJVobBpvI0Q4i8a0ig4UmKx60ie8u68uIag/WXY2ChpQf+zlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:41:51.631007Z"},"content_sha256":"d9d84b8e1f8ddc0768bc2dbf46bd896cdd8874149324ed97457b58adb40b39b4","schema_version":"1.0","event_id":"sha256:d9d84b8e1f8ddc0768bc2dbf46bd896cdd8874149324ed97457b58adb40b39b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FIEY5VINW5OIZXZ4JVUL3L5GLS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CIC: A Framework for Culturally-Aware Image Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jihie Kim, Youngsik Yun","submitted_at":"2024-02-08T03:12:25Z","abstract_excerpt":"Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the cultural elements depicted in the images, such as the traditional clothing worn by people from Asian cultural groups. In this paper, we propose a new framework, Culturally-aware Image Captioning (CIC), that generates captions and describes cultural elements extracted from cultural visual elements in images representing cultures. Inspired by methods combining vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05374","kind":"arxiv","version":5},"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/2402.05374/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":"2026-07-05T10:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fC2ut8CirtmsNl6xq+cAZ3ce0VLLbmxQTFmGyAOiJLA4ml4WO6Zn76pk6ENcrdQ0T6I5ra5G7ogFHJqO9gx7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:41:51.631385Z"},"content_sha256":"510e2cde399edc1ca08f4a425898bbcc11023ed9e30132669651efafc964f193","schema_version":"1.0","event_id":"sha256:510e2cde399edc1ca08f4a425898bbcc11023ed9e30132669651efafc964f193"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIEY5VINW5OIZXZ4JVUL3L5GLS/bundle.json","state_url":"https://pith.science/pith/FIEY5VINW5OIZXZ4JVUL3L5GLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIEY5VINW5OIZXZ4JVUL3L5GLS/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":"2026-08-21T10:41:51Z","links":{"resolver":"https://pith.science/pith/FIEY5VINW5OIZXZ4JVUL3L5GLS","bundle":"https://pith.science/pith/FIEY5VINW5OIZXZ4JVUL3L5GLS/bundle.json","state":"https://pith.science/pith/FIEY5VINW5OIZXZ4JVUL3L5GLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIEY5VINW5OIZXZ4JVUL3L5GLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FIEY5VINW5OIZXZ4JVUL3L5GLS","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":"f33e013995ae46c9c0f1c1a4c4e131608cb62bfd6e62d81e1541a9eac19287a5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T03:12:25Z","title_canon_sha256":"bf433bf5d65b3035e451a5ee43ec233faad0693093e9c0d34ab10620527ee0c6"},"schema_version":"1.0","source":{"id":"2402.05374","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05374","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05374v5","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05374","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"FIEY5VINW5OI","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"FIEY5VINW5OIZXZ4","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"FIEY5VIN","created_at":"2026-07-05T10:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:510e2cde399edc1ca08f4a425898bbcc11023ed9e30132669651efafc964f193","target":"graph","created_at":"2026-07-05T10:18:34Z","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/2402.05374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the cultural elements depicted in the images, such as the traditional clothing worn by people from Asian cultural groups. In this paper, we propose a new framework, Culturally-aware Image Captioning (CIC), that generates captions and describes cultural elements extracted from cultural visual elements in images representing cultures. Inspired by methods combining vi","authors_text":"Jihie Kim, Youngsik Yun","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T03:12:25Z","title":"CIC: A Framework for Culturally-Aware Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05374","kind":"arxiv","version":5},"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:d9d84b8e1f8ddc0768bc2dbf46bd896cdd8874149324ed97457b58adb40b39b4","target":"record","created_at":"2026-07-05T10:18:34Z","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":"f33e013995ae46c9c0f1c1a4c4e131608cb62bfd6e62d81e1541a9eac19287a5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T03:12:25Z","title_canon_sha256":"bf433bf5d65b3035e451a5ee43ec233faad0693093e9c0d34ab10620527ee0c6"},"schema_version":"1.0","source":{"id":"2402.05374","kind":"arxiv","version":5}},"canonical_sha256":"2a098ed50db75c8cdf3c4d68bdafa65c9769990336cf66b55e60b7bb85fc24aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a098ed50db75c8cdf3c4d68bdafa65c9769990336cf66b55e60b7bb85fc24aa","first_computed_at":"2026-07-05T10:18:34.869303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:34.869303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ipCp/D/DarNQ/2zSEXC4Z6eSeZh33ORBiGtbNJ65qx16ShOeD0XZn2l99v0Kw4zz8iSod2pdm02yxVrdLzP1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:34.869780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05374","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9d84b8e1f8ddc0768bc2dbf46bd896cdd8874149324ed97457b58adb40b39b4","sha256:510e2cde399edc1ca08f4a425898bbcc11023ed9e30132669651efafc964f193"],"state_sha256":"54e099d92e4f3104a27b6b73d4da5790b4adedf39c352d4b1f62800add0d5d60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jp4JRrY+0RVzB8174hT/bk5KATOS49LshncPgqrJ2eInyuLgUx0z+7JQRjKDvv+p/SEFFhxLEvYijXTmnUDJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:41:51.634582Z","bundle_sha256":"ca1b27a9d4944245ba04359bb2e3f5c6fb8d3a0072bbc05de8cd10411e8c9e3e"}}