{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3MS36KGQH6SZLSOSHMAAMVTXQN","short_pith_number":"pith:3MS36KGQ","schema_version":"1.0","canonical_sha256":"db25bf28d03fa595c9d23b00065677834cc11743f50a8e48154e73bff139278f","source":{"kind":"arxiv","id":"2606.17430","version":1},"attestation_state":"computed","paper":{"title":"CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Trinh Thi Thu Hien, Trung-Nghia Le","submitted_at":"2026-06-16T02:24:08Z","abstract_excerpt":"Event-enriched image captioning describes not only visible content but also the broader context of events, including timing, location, and participants, capabilities missing in most pixel-bound models. We propose the Contextual Image-Article Narrator (CIAN), a multi-stage framework that enriches captions with external narratives. CIAN retrieves relevant articles using SigLIP, summarizes them to guide a Narrative Generation stage with a LoRA-fine-tuned Qwen model, and applies N-Gram-based Refinement for fluency and coherence. On the OpenEvents-V1 benchmark, CIAN achieves high retrieval performa"},"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":"2606.17430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T02:24:08Z","cross_cats_sorted":[],"title_canon_sha256":"c1a4c0aa93ca6c2d75493b719b4227e47fbdd62bff0664060eff1f10c9676362","abstract_canon_sha256":"f90bb17db9a10fee4301f62b704c74d57a4cf5d717ba9cb996712da3dd11ce43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:12.595485Z","signature_b64":"u6M6AAG4fcXijy/1X3fkq8lhsr2Zm95utsxgKDO+8yopNCQo0D3FKhqVm2uNm7b+/fT14Q7bXCk8aIsO5zgZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db25bf28d03fa595c9d23b00065677834cc11743f50a8e48154e73bff139278f","last_reissued_at":"2026-06-19T16:10:12.595121Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:12.595121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Trinh Thi Thu Hien, Trung-Nghia Le","submitted_at":"2026-06-16T02:24:08Z","abstract_excerpt":"Event-enriched image captioning describes not only visible content but also the broader context of events, including timing, location, and participants, capabilities missing in most pixel-bound models. We propose the Contextual Image-Article Narrator (CIAN), a multi-stage framework that enriches captions with external narratives. CIAN retrieves relevant articles using SigLIP, summarizes them to guide a Narrative Generation stage with a LoRA-fine-tuned Qwen model, and applies N-Gram-based Refinement for fluency and coherence. On the OpenEvents-V1 benchmark, CIAN achieves high retrieval performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17430","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/2606.17430/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":"2606.17430","created_at":"2026-06-19T16:10:12.595182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17430v1","created_at":"2026-06-19T16:10:12.595182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17430","created_at":"2026-06-19T16:10:12.595182+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MS36KGQH6SZ","created_at":"2026-06-19T16:10:12.595182+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MS36KGQH6SZLSOS","created_at":"2026-06-19T16:10:12.595182+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MS36KGQ","created_at":"2026-06-19T16:10:12.595182+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/3MS36KGQH6SZLSOSHMAAMVTXQN","json":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN.json","graph_json":"https://pith.science/api/pith-number/3MS36KGQH6SZLSOSHMAAMVTXQN/graph.json","events_json":"https://pith.science/api/pith-number/3MS36KGQH6SZLSOSHMAAMVTXQN/events.json","paper":"https://pith.science/paper/3MS36KGQ"},"agent_actions":{"view_html":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN","download_json":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN.json","view_paper":"https://pith.science/paper/3MS36KGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17430&json=true","fetch_graph":"https://pith.science/api/pith-number/3MS36KGQH6SZLSOSHMAAMVTXQN/graph.json","fetch_events":"https://pith.science/api/pith-number/3MS36KGQH6SZLSOSHMAAMVTXQN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN/action/storage_attestation","attest_author":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN/action/author_attestation","sign_citation":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN/action/citation_signature","submit_replication":"https://pith.science/pith/3MS36KGQH6SZLSOSHMAAMVTXQN/action/replication_record"}},"created_at":"2026-06-19T16:10:12.595182+00:00","updated_at":"2026-06-19T16:10:12.595182+00:00"}