{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AQEHB7PHKTRQ6LN3WOFYKYXQTI","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":"cab370cd73d0305b7d5a4ead28562cf33476f5ac9b132f9772ce37ee9afbe548","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:56:08Z","title_canon_sha256":"e7d25d9d90ca28785b621281b6c83a6733ec74d19da5c89ea86fb8b2c7be3615"},"schema_version":"1.0","source":{"id":"2312.12273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12273","created_at":"2026-07-05T07:26:01Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12273v1","created_at":"2026-07-05T07:26:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12273","created_at":"2026-07-05T07:26:01Z"},{"alias_kind":"pith_short_12","alias_value":"AQEHB7PHKTRQ","created_at":"2026-07-05T07:26:01Z"},{"alias_kind":"pith_short_16","alias_value":"AQEHB7PHKTRQ6LN3","created_at":"2026-07-05T07:26:01Z"},{"alias_kind":"pith_short_8","alias_value":"AQEHB7PH","created_at":"2026-07-05T07:26:01Z"}],"graph_snapshots":[{"event_id":"sha256:22ff878abf7ef8b2f878098682250903f86a4d528381b9bd4a94fa965d10bed7","target":"graph","created_at":"2026-07-05T07:26:01Z","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/2312.12273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Albeit progress has been made in Composed Image Retrieval (CIR), we empirically find that a certain percentage of failure retrieval results are not consistent with their relative captions. To address this issue, this work provides a Visual Question Answering (VQA) perspective to boost the performance of CIR. The resulting VQA4CIR is a post-processing approach and can be directly plugged into existing CIR methods. Given the top-C retrieved images by a CIR method, VQA4CIR aims to decrease the adverse effect of the failure retrieval results being inconsistent with the relative caption. To find th","authors_text":"Chun-Mei Feng, Rick Siow Mong Goh, Salman Khan, Tao Luo, Wangmeng Zuo, Xinxing Xu, Yang Bai, Yong Liu, Zhen Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:56:08Z","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12273","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":"sha256:3201e48fa31c8d5a225cc315adfb4e64f0ae7b898d794e0cf64d036ad80deae3","target":"record","created_at":"2026-07-05T07:26:01Z","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":"cab370cd73d0305b7d5a4ead28562cf33476f5ac9b132f9772ce37ee9afbe548","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:56:08Z","title_canon_sha256":"e7d25d9d90ca28785b621281b6c83a6733ec74d19da5c89ea86fb8b2c7be3615"},"schema_version":"1.0","source":{"id":"2312.12273","kind":"arxiv","version":1}},"canonical_sha256":"040870fde754e30f2dbbb38b8562f09a324a348b965ec7e9fe123de83eb1789d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"040870fde754e30f2dbbb38b8562f09a324a348b965ec7e9fe123de83eb1789d","first_computed_at":"2026-07-05T07:26:01.344088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:01.344088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kYOZSVQV7bSqWAWoZ9LGBFoZZjxFxpvbBTBURIeeUxuDnkpTgI+MS6aygTnJE39omlyVNPaU2235+gQgIDMADw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:01.344632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3201e48fa31c8d5a225cc315adfb4e64f0ae7b898d794e0cf64d036ad80deae3","sha256:22ff878abf7ef8b2f878098682250903f86a4d528381b9bd4a94fa965d10bed7"],"state_sha256":"22920aa3608f2a79b14f0ab9c877050b1226d0be8175bd009842e42b6adc6c6b"}