{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJDIMEDH5NSVYHPXTT7Q5LYFS2","short_pith_number":"pith:JJDIMEDH","schema_version":"1.0","canonical_sha256":"4a46861067eb655c1df79cff0eaf0596961050bc0dd6111d0fff56d997161efd","source":{"kind":"arxiv","id":"2606.18553","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.18553","created_at":"2026-06-19T16:11:40.741692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18553v1","created_at":"2026-06-19T16:11:40.741692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18553","created_at":"2026-06-19T16:11:40.741692+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJDIMEDH5NSV","created_at":"2026-06-19T16:11:40.741692+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJDIMEDH5NSVYHPX","created_at":"2026-06-19T16:11:40.741692+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJDIMEDH","created_at":"2026-06-19T16:11:40.741692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2","json":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2.json","graph_json":"https://pith.science/api/pith-number/JJDIMEDH5NSVYHPXTT7Q5LYFS2/graph.json","events_json":"https://pith.science/api/pith-number/JJDIMEDH5NSVYHPXTT7Q5LYFS2/events.json","paper":"https://pith.science/paper/JJDIMEDH"},"agent_actions":{"view_html":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2","download_json":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2.json","view_paper":"https://pith.science/paper/JJDIMEDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18553&json=true","fetch_graph":"https://pith.science/api/pith-number/JJDIMEDH5NSVYHPXTT7Q5LYFS2/graph.json","fetch_events":"https://pith.science/api/pith-number/JJDIMEDH5NSVYHPXTT7Q5LYFS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/action/storage_attestation","attest_author":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/action/author_attestation","sign_citation":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/action/citation_signature","submit_replication":"https://pith.science/pith/JJDIMEDH5NSVYHPXTT7Q5LYFS2/action/replication_record"}},"created_at":"2026-06-19T16:11:40.741692+00:00","updated_at":"2026-06-19T16:11:40.741692+00:00"}