{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JJDIMEDH5NSVYHPXTT7Q5LYFS2","short_pith_number":"pith:JJDIMEDH","canonical_record":{"source":{"id":"2606.18553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T00:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"c87a2e982b83ed8f0e25e1e079154ce6fe3610824dbcd3f75f910867aa91dc56","abstract_canon_sha256":"b2ca65a5307117e23767b096b6c6724ffb366ba1073a2ccc1fe2fe0637a26f65"},"schema_version":"1.0"},"canonical_sha256":"4a46861067eb655c1df79cff0eaf0596961050bc0dd6111d0fff56d997161efd","source":{"kind":"arxiv","id":"2606.18553","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18553","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18553v1","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18553","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"JJDIMEDH5NSV","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"JJDIMEDH5NSVYHPX","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"JJDIMEDH","created_at":"2026-06-19T16:11:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JJDIMEDH5NSVYHPXTT7Q5LYFS2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.18553","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T00:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"c87a2e982b83ed8f0e25e1e079154ce6fe3610824dbcd3f75f910867aa91dc56","abstract_canon_sha256":"b2ca65a5307117e23767b096b6c6724ffb366ba1073a2ccc1fe2fe0637a26f65"},"schema_version":"1.0"},"canonical_sha256":"4a46861067eb655c1df79cff0eaf0596961050bc0dd6111d0fff56d997161efd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:40.742072Z","signature_b64":"w/mgUiyuXyLrXpyZMoRZ08MG/QbgQr/K3gODFr8VzevLik57cyrftqbla6ECJEiHlEnfOuOniSvP+fzOgSchCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a46861067eb655c1df79cff0eaf0596961050bc0dd6111d0fff56d997161efd","last_reissued_at":"2026-06-19T16:11:40.741636Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:40.741636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.18553","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Qalz4iU6w5yhXUf6ST4681qrzkGDEznGo456egRVFteRc+fKpker9iuyYanTrEXqHd5r1ZMjCkGpuaEcbo/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T11:05:32.067378Z"},"content_sha256":"45851d48db19e81130227fcb64496462ae677a3855b4d9aed935a1a9d79c4ce4","schema_version":"1.0","event_id":"sha256:45851d48db19e81130227fcb64496462ae677a3855b4d9aed935a1a9d79c4ce4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JJDIMEDH5NSVYHPXTT7Q5LYFS2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hoang-Bach Ngo, Long-Bao Nguyen, Minh-Loi Nguyen, Trung-Nghia Le, Xuan-Vu Le","submitted_at":"2026-06-17T00:08:17Z","abstract_excerpt":"Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptions, especially for details not directly observable from visual cues. To overcome this, we propose a novel retrieval-augmented image captioning framework that generates captions with deeper insights, such as object attributes, event context, and underlying significance, by leveraging external knowledge. Our approach features a hierarchical multi-modal article retrieval mechanism that moves beyond monolithic text entities. This retrieval considers article structure-aware features, including weig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18553","kind":"arxiv","version":1},"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/2606.18553/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":"2026-06-19T16:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u2Afj0sjNDHVIdt883w4ZTKJwhde0s2xcw0TcpOvzxrtQdkrpvFciyg2JEtR7h1Uv5LkYN4bxoDefxhOgEmFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T11:05:32.068020Z"},"content_sha256":"47782cd840356dee78f70a8b46b0d92db3c57232e8c7289154d059753b95033e","schema_version":"1.0","event_id":"sha256:47782cd840356dee78f70a8b46b0d92db3c57232e8c7289154d059753b95033e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/bundle.json","state_url":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/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":"2026-07-01T11:05:32Z","links":{"resolver":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2","bundle":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/bundle.json","state":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JJDIMEDH5NSVYHPXTT7Q5LYFS2","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":"b2ca65a5307117e23767b096b6c6724ffb366ba1073a2ccc1fe2fe0637a26f65","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T00:08:17Z","title_canon_sha256":"c87a2e982b83ed8f0e25e1e079154ce6fe3610824dbcd3f75f910867aa91dc56"},"schema_version":"1.0","source":{"id":"2606.18553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18553","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18553v1","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18553","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"JJDIMEDH5NSV","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"JJDIMEDH5NSVYHPX","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"JJDIMEDH","created_at":"2026-06-19T16:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:47782cd840356dee78f70a8b46b0d92db3c57232e8c7289154d059753b95033e","target":"graph","created_at":"2026-06-19T16:11:40Z","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/2606.18553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptions, especially for details not directly observable from visual cues. To overcome this, we propose a novel retrieval-augmented image captioning framework that generates captions with deeper insights, such as object attributes, event context, and underlying significance, by leveraging external knowledge. Our approach features a hierarchical multi-modal article retrieval mechanism that moves beyond monolithic text entities. This retrieval considers article structure-aware features, including weig","authors_text":"Hoang-Bach Ngo, Long-Bao Nguyen, Minh-Loi Nguyen, Trung-Nghia Le, Xuan-Vu Le","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T00:08:17Z","title":"Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18553","kind":"arxiv","version":1},"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":"sha256:45851d48db19e81130227fcb64496462ae677a3855b4d9aed935a1a9d79c4ce4","target":"record","created_at":"2026-06-19T16:11:40Z","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":"b2ca65a5307117e23767b096b6c6724ffb366ba1073a2ccc1fe2fe0637a26f65","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T00:08:17Z","title_canon_sha256":"c87a2e982b83ed8f0e25e1e079154ce6fe3610824dbcd3f75f910867aa91dc56"},"schema_version":"1.0","source":{"id":"2606.18553","kind":"arxiv","version":1}},"canonical_sha256":"4a46861067eb655c1df79cff0eaf0596961050bc0dd6111d0fff56d997161efd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a46861067eb655c1df79cff0eaf0596961050bc0dd6111d0fff56d997161efd","first_computed_at":"2026-06-19T16:11:40.741636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:40.741636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w/mgUiyuXyLrXpyZMoRZ08MG/QbgQr/K3gODFr8VzevLik57cyrftqbla6ECJEiHlEnfOuOniSvP+fzOgSchCQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:40.742072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45851d48db19e81130227fcb64496462ae677a3855b4d9aed935a1a9d79c4ce4","sha256:47782cd840356dee78f70a8b46b0d92db3c57232e8c7289154d059753b95033e"],"state_sha256":"27274a0ffa96f32b5dce87aa06c8ea6d863d0c764426698d370abf4ace8852a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/GNu7aAXx5rqO2cvXbxYX0zppRWu0RzbV8QcvKp7Si+ixV7NDB+UQoiERtKyzcoWiogxq0xhMMtex/2I/KdCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T11:05:32.070845Z","bundle_sha256":"f6363e25163b3394b8ccbcad7b63945153395bb530b368941900f19e9045ce69"}}