{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BXUVZYH5GFYBI47FCOEBYE3CEZ","short_pith_number":"pith:BXUVZYH5","canonical_record":{"source":{"id":"2307.09915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T11:35:21Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e3a68d061002499b4f0f4dccced2953f05dbfb0a8c20e7fa13f3b7027af32817","abstract_canon_sha256":"677c8cdf245232e20058edc3111c639d538737d8ce4002d7aeb93aa98e81664e"},"schema_version":"1.0"},"canonical_sha256":"0de95ce0fd31701473e513881c1362265a693d9d09dfe0375b177df65c126cb2","source":{"kind":"arxiv","id":"2307.09915","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09915","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09915v2","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09915","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"BXUVZYH5GFYB","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"BXUVZYH5GFYBI47F","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"BXUVZYH5","created_at":"2026-07-05T08:04:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BXUVZYH5GFYBI47FCOEBYE3CEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2307.09915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T11:35:21Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e3a68d061002499b4f0f4dccced2953f05dbfb0a8c20e7fa13f3b7027af32817","abstract_canon_sha256":"677c8cdf245232e20058edc3111c639d538737d8ce4002d7aeb93aa98e81664e"},"schema_version":"1.0"},"canonical_sha256":"0de95ce0fd31701473e513881c1362265a693d9d09dfe0375b177df65c126cb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:32.983944Z","signature_b64":"2IvfWXsrwggsNFVQCx+cObCQingbp4B1WzQSL4HxqNRpRVtEB/Jtzcm93mYCP1AzhJvu2BnHynJBMn+RlWjBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0de95ce0fd31701473e513881c1362265a693d9d09dfe0375b177df65c126cb2","last_reissued_at":"2026-07-05T08:04:32.983575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:32.983575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.09915","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":"2026-07-05T08:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0tWVRVrm7hDfm1vp7tcAco8qrPDadw4QJzzmgN55PHRxopQwDZ0hUd+jzi0El0PCY1VKCpTGhsojk7yuswvABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:15:24.776023Z"},"content_sha256":"58fd07421db614c1b908eb506945c94c41561f50460905108f5366f8abef8e01","schema_version":"1.0","event_id":"sha256:58fd07421db614c1b908eb506945c94c41561f50460905108f5366f8abef8e01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BXUVZYH5GFYBI47FCOEBYE3CEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Meng Wang, Richang Hong, Ye Zhao, Yuanen Zhou, Zhenzhen Hu, Zijie Song","submitted_at":"2023-07-19T11:35:21Z","abstract_excerpt":"Cross-lingual image captioning is a challenging task that requires addressing both cross-lingual and cross-modal obstacles in multimedia analysis. The crucial issue in this task is to model the global and the local matching between the image and different languages. Existing cross-modal embedding methods based on the transformer architecture oversee the local matching between the image region and monolingual words, especially when dealing with diverse languages. To overcome these limitations, we propose an Embedded Heterogeneous Attention Transformer (EHAT) to establish cross-domain relationsh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09915","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/2307.09915/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":"2026-07-05T08:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKe618RGGg7qCe1iMH3avteWyziiCbryWyCGzPrljKS9i2opZAT3XEv2VxP9sgD3UgHRnVB8tJB9DYL260YGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:15:24.776628Z"},"content_sha256":"bdb3880d70a8d87fea055e2461f5fd932629a6a4cf2b881f3f93de97768bdde7","schema_version":"1.0","event_id":"sha256:bdb3880d70a8d87fea055e2461f5fd932629a6a4cf2b881f3f93de97768bdde7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXUVZYH5GFYBI47FCOEBYE3CEZ/bundle.json","state_url":"https://pith.science/pith/BXUVZYH5GFYBI47FCOEBYE3CEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXUVZYH5GFYBI47FCOEBYE3CEZ/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":"2026-08-07T00:15:24Z","links":{"resolver":"https://pith.science/pith/BXUVZYH5GFYBI47FCOEBYE3CEZ","bundle":"https://pith.science/pith/BXUVZYH5GFYBI47FCOEBYE3CEZ/bundle.json","state":"https://pith.science/pith/BXUVZYH5GFYBI47FCOEBYE3CEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXUVZYH5GFYBI47FCOEBYE3CEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BXUVZYH5GFYBI47FCOEBYE3CEZ","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":"677c8cdf245232e20058edc3111c639d538737d8ce4002d7aeb93aa98e81664e","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T11:35:21Z","title_canon_sha256":"e3a68d061002499b4f0f4dccced2953f05dbfb0a8c20e7fa13f3b7027af32817"},"schema_version":"1.0","source":{"id":"2307.09915","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.09915","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2307.09915v2","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.09915","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"BXUVZYH5GFYB","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"BXUVZYH5GFYBI47F","created_at":"2026-07-05T08:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"BXUVZYH5","created_at":"2026-07-05T08:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:bdb3880d70a8d87fea055e2461f5fd932629a6a4cf2b881f3f93de97768bdde7","target":"graph","created_at":"2026-07-05T08:04:32Z","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/2307.09915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual image captioning is a challenging task that requires addressing both cross-lingual and cross-modal obstacles in multimedia analysis. The crucial issue in this task is to model the global and the local matching between the image and different languages. Existing cross-modal embedding methods based on the transformer architecture oversee the local matching between the image region and monolingual words, especially when dealing with diverse languages. To overcome these limitations, we propose an Embedded Heterogeneous Attention Transformer (EHAT) to establish cross-domain relationsh","authors_text":"Meng Wang, Richang Hong, Ye Zhao, Yuanen Zhou, Zhenzhen Hu, Zijie Song","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T11:35:21Z","title":"Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.09915","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":"sha256:58fd07421db614c1b908eb506945c94c41561f50460905108f5366f8abef8e01","target":"record","created_at":"2026-07-05T08:04:32Z","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":"677c8cdf245232e20058edc3111c639d538737d8ce4002d7aeb93aa98e81664e","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-19T11:35:21Z","title_canon_sha256":"e3a68d061002499b4f0f4dccced2953f05dbfb0a8c20e7fa13f3b7027af32817"},"schema_version":"1.0","source":{"id":"2307.09915","kind":"arxiv","version":2}},"canonical_sha256":"0de95ce0fd31701473e513881c1362265a693d9d09dfe0375b177df65c126cb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0de95ce0fd31701473e513881c1362265a693d9d09dfe0375b177df65c126cb2","first_computed_at":"2026-07-05T08:04:32.983575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:32.983575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2IvfWXsrwggsNFVQCx+cObCQingbp4B1WzQSL4HxqNRpRVtEB/Jtzcm93mYCP1AzhJvu2BnHynJBMn+RlWjBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:32.983944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.09915","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58fd07421db614c1b908eb506945c94c41561f50460905108f5366f8abef8e01","sha256:bdb3880d70a8d87fea055e2461f5fd932629a6a4cf2b881f3f93de97768bdde7"],"state_sha256":"ecfd5a92c839b316454664e454a8c5934113a2664874420db7d8e266a7b09865"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVw/RqT1rf4Rr7OhAWg43ixTYI5gzwyGHQe5Fhc7CbvGN+qsOupUM9+r3EApQSHcLuKxrtZ1Bgxq3g8bcTnJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:15:24.781378Z","bundle_sha256":"eecd930bbef458c44a46a8f2c2fb70f068532db5793eafd861e37b20d1f24849"}}