{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2YATNMQJ23Q25BIFKMMTSJ7TIO","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":"63867d114194345993a095d50c895c08ee54a7979b24071e745d452758bcfe44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T09:03:25Z","title_canon_sha256":"e7a9dc8703af45c2508284ac33c36bb9d3af3bb768dff38f539dd806d593880c"},"schema_version":"1.0","source":{"id":"2509.00751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00751","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00751v1","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00751","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"2YATNMQJ23Q2","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"2YATNMQJ23Q25BIF","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"2YATNMQJ","created_at":"2026-07-05T12:02:22Z"}],"graph_snapshots":[{"event_id":"sha256:7ff788feb0f8b16355bf8feefd06b06c0975395c5bd130fe91742ef68653e5d2","target":"graph","created_at":"2026-07-05T12:02:22Z","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/2509.00751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dinh-Khoi Vo, Minh-Triet Tran, Trung-Nghia Le, Van-Loc Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T09:03:25Z","title":"EVENT-Retriever: Event-Aware Multimodal Image Retrieval for Realistic Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00751","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:cbbef9f532b6482b06145cdc4cbbda91e00d8891d706fc52019caba06b3def0f","target":"record","created_at":"2026-07-05T12:02:22Z","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":"63867d114194345993a095d50c895c08ee54a7979b24071e745d452758bcfe44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T09:03:25Z","title_canon_sha256":"e7a9dc8703af45c2508284ac33c36bb9d3af3bb768dff38f539dd806d593880c"},"schema_version":"1.0","source":{"id":"2509.00751","kind":"arxiv","version":1}},"canonical_sha256":"d60136b209d6e1ae850553193927f343b37d99257ce8f0678e0ffba6c411e337","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d60136b209d6e1ae850553193927f343b37d99257ce8f0678e0ffba6c411e337","first_computed_at":"2026-07-05T12:02:22.203552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:22.203552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pk8z8Aw4Jn1RRZrHjFfuNEMLSp3o0TWXpwwz1NAHahx1kUx/KJOJiS7nlc99Tv1zlYjSjVneiHtTRoQMUQV0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:22.204039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbbef9f532b6482b06145cdc4cbbda91e00d8891d706fc52019caba06b3def0f","sha256:7ff788feb0f8b16355bf8feefd06b06c0975395c5bd130fe91742ef68653e5d2"],"state_sha256":"35db13bd2bcf2674d20409984ead5ec0af4553963d0d6f64eb4673c06b7b0cc3"}