{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2YATNMQJ23Q25BIFKMMTSJ7TIO","short_pith_number":"pith:2YATNMQJ","schema_version":"1.0","canonical_sha256":"d60136b209d6e1ae850553193927f343b37d99257ce8f0678e0ffba6c411e337","source":{"kind":"arxiv","id":"2509.00751","version":1},"attestation_state":"computed","paper":{"title":"EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dinh-Khoi Vo, Minh-Triet Tran, Trung-Nghia Le, Van-Loc Nguyen","submitted_at":"2025-08-31T09:03:25Z","abstract_excerpt":"Event-based image retrieval from free-form captions presents a significant challenge: models must understand not only visual features but also latent event semantics, context, and real-world knowledge. Conventional vision-language retrieval approaches often fall short when captions describe abstract events, implicit causality, temporal context, or contain long, complex narratives. To tackle these issues, we introduce a multi-stage retrieval framework combining dense article retrieval, event-aware language model reranking, and efficient image collection, followed by caption-guided semantic matc"},"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":"2509.00751","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T09:03:25Z","cross_cats_sorted":[],"title_canon_sha256":"e7a9dc8703af45c2508284ac33c36bb9d3af3bb768dff38f539dd806d593880c","abstract_canon_sha256":"63867d114194345993a095d50c895c08ee54a7979b24071e745d452758bcfe44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:22.204039Z","signature_b64":"Pk8z8Aw4Jn1RRZrHjFfuNEMLSp3o0TWXpwwz1NAHahx1kUx/KJOJiS7nlc99Tv1zlYjSjVneiHtTRoQMUQV0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d60136b209d6e1ae850553193927f343b37d99257ce8f0678e0ffba6c411e337","last_reissued_at":"2026-07-05T12:02:22.203552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:22.203552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dinh-Khoi Vo, Minh-Triet Tran, Trung-Nghia Le, Van-Loc Nguyen","submitted_at":"2025-08-31T09:03:25Z","abstract_excerpt":"Event-based image retrieval from free-form captions presents a significant challenge: models must understand not only visual features but also latent event semantics, context, and real-world knowledge. Conventional vision-language retrieval approaches often fall short when captions describe abstract events, implicit causality, temporal context, or contain long, complex narratives. To tackle these issues, we introduce a multi-stage retrieval framework combining dense article retrieval, event-aware language model reranking, and efficient image collection, followed by caption-guided semantic matc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00751","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/2509.00751/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":"2509.00751","created_at":"2026-07-05T12:02:22.203615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00751v1","created_at":"2026-07-05T12:02:22.203615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00751","created_at":"2026-07-05T12:02:22.203615+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YATNMQJ23Q2","created_at":"2026-07-05T12:02:22.203615+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YATNMQJ23Q25BIF","created_at":"2026-07-05T12:02:22.203615+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YATNMQJ","created_at":"2026-07-05T12:02:22.203615+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/2YATNMQJ23Q25BIFKMMTSJ7TIO","json":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO.json","graph_json":"https://pith.science/api/pith-number/2YATNMQJ23Q25BIFKMMTSJ7TIO/graph.json","events_json":"https://pith.science/api/pith-number/2YATNMQJ23Q25BIFKMMTSJ7TIO/events.json","paper":"https://pith.science/paper/2YATNMQJ"},"agent_actions":{"view_html":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO","download_json":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO.json","view_paper":"https://pith.science/paper/2YATNMQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00751&json=true","fetch_graph":"https://pith.science/api/pith-number/2YATNMQJ23Q25BIFKMMTSJ7TIO/graph.json","fetch_events":"https://pith.science/api/pith-number/2YATNMQJ23Q25BIFKMMTSJ7TIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO/action/storage_attestation","attest_author":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO/action/author_attestation","sign_citation":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO/action/citation_signature","submit_replication":"https://pith.science/pith/2YATNMQJ23Q25BIFKMMTSJ7TIO/action/replication_record"}},"created_at":"2026-07-05T12:02:22.203615+00:00","updated_at":"2026-07-05T12:02:22.203615+00:00"}