{"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"}