{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5CYV2VECFS42IKYNKUMNQRGHRL","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":"bc3caa59e22b7baf851e97373ca069030517c28eab76b8023f922a2fe32b8669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-03-28T13:00:01Z","title_canon_sha256":"2dd139c159539f94f9d6f9a4d0bf5b4004fc73dae3def202cd7bb61b00d66a36"},"schema_version":"1.0","source":{"id":"2203.14713","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.14713","created_at":"2026-07-05T05:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"2203.14713v3","created_at":"2026-07-05T05:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14713","created_at":"2026-07-05T05:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"5CYV2VECFS42","created_at":"2026-07-05T05:17:10Z"},{"alias_kind":"pith_short_16","alias_value":"5CYV2VECFS42IKYN","created_at":"2026-07-05T05:17:10Z"},{"alias_kind":"pith_short_8","alias_value":"5CYV2VEC","created_at":"2026-07-05T05:17:10Z"}],"graph_snapshots":[{"event_id":"sha256:35f323c31762fd9a8c7e93485ba37c7099bef8b5b881883fb5c35231dff05dd2","target":"graph","created_at":"2026-07-05T05:17:10Z","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/2203.14713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the past few years, cross-modal image-text retrieval (ITR) has experienced increased interest in the research community due to its excellent research value and broad real-world application. It is designed for the scenarios where the queries are from one modality and the retrieval galleries from another modality. This paper presents a comprehensive and up-to-date survey on the ITR approaches from four perspectives. By dissecting an ITR system into two processes: feature extraction and feature alignment, we summarize the recent advance of the ITR approaches from these two perspectives. On top","authors_text":"Juntao Li, Liqiang Nie, Min Cao, Min Zhang, Shiping Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-03-28T13:00:01Z","title":"Image-text Retrieval: A Survey on Recent Research and Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14713","kind":"arxiv","version":3},"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:ced065abd8b4ebb196b1794384ad279815bbed30b156859edd4e79856bbf7e17","target":"record","created_at":"2026-07-05T05:17:10Z","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":"bc3caa59e22b7baf851e97373ca069030517c28eab76b8023f922a2fe32b8669","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-03-28T13:00:01Z","title_canon_sha256":"2dd139c159539f94f9d6f9a4d0bf5b4004fc73dae3def202cd7bb61b00d66a36"},"schema_version":"1.0","source":{"id":"2203.14713","kind":"arxiv","version":3}},"canonical_sha256":"e8b15d54822cb9a42b0d5518d844c78adede766ac56ce2c96aa14acf8a39d61e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8b15d54822cb9a42b0d5518d844c78adede766ac56ce2c96aa14acf8a39d61e","first_computed_at":"2026-07-05T05:17:10.059894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:10.059894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pLigmESgUl1u6Wf5jh/rqh6ggVT/U9k9szDNYwXWXkVdxvVU+GLABoLTxjlPRRh4b3KPTlk9ynFaeW9dDwiQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:10.060340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.14713","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ced065abd8b4ebb196b1794384ad279815bbed30b156859edd4e79856bbf7e17","sha256:35f323c31762fd9a8c7e93485ba37c7099bef8b5b881883fb5c35231dff05dd2"],"state_sha256":"32e9960869733a0f7d05e9c395abf77a74889d816cdfa5f0e26b9335ca424324"}