{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YJXLO2LDM3KQE5NUHCBHDJSTIK","short_pith_number":"pith:YJXLO2LD","schema_version":"1.0","canonical_sha256":"c26eb7696366d50275b4388271a65342849678d4b8cc7ec64f9e2c159918d3ae","source":{"kind":"arxiv","id":"2208.10126","version":2},"attestation_state":"computed","paper":{"title":"Revising Image-Text Retrieval via Multi-Modal Entailment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunhui Ai, Guohong Fu, Min Cao, Sujian Li, Wenjie Li, Xu Yan, Ziqiang Cao","submitted_at":"2022-08-22T07:58:54Z","abstract_excerpt":"An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from fitting other images. We observe that such a many-to-many matching phenomenon is quite common in the widely-used retrieval datasets, where one caption can describe up to 178 images. These large matching-lost data not only confuse the model in training but also weaken the evaluation accuracy. Inspired by visual and textual entailment tasks, we propose a multi-mod"},"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":"2208.10126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-22T07:58:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"af8d10fc85b5bf5ea7947ff97940b539efb52cbca97c587ddbcdc1a6592b4866","abstract_canon_sha256":"560dcf5ebcca33c3266ba28d0fb17e341b125f7877a7bb4602b9d0c1cfc8271a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:44.042239Z","signature_b64":"K9I6wsQT1aKnBK5ZWtwZRsm48tsk//aQgOoRPpZhbMzdpvzWAG51WWk5arXBGsY9YSy2OFBEe2OBrSe30FSRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c26eb7696366d50275b4388271a65342849678d4b8cc7ec64f9e2c159918d3ae","last_reissued_at":"2026-07-05T04:53:44.041752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:44.041752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revising Image-Text Retrieval via Multi-Modal Entailment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chunhui Ai, Guohong Fu, Min Cao, Sujian Li, Wenjie Li, Xu Yan, Ziqiang Cao","submitted_at":"2022-08-22T07:58:54Z","abstract_excerpt":"An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from fitting other images. We observe that such a many-to-many matching phenomenon is quite common in the widely-used retrieval datasets, where one caption can describe up to 178 images. These large matching-lost data not only confuse the model in training but also weaken the evaluation accuracy. Inspired by visual and textual entailment tasks, we propose a multi-mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10126","kind":"arxiv","version":2},"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/2208.10126/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":"2208.10126","created_at":"2026-07-05T04:53:44.041812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.10126v2","created_at":"2026-07-05T04:53:44.041812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10126","created_at":"2026-07-05T04:53:44.041812+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJXLO2LDM3KQ","created_at":"2026-07-05T04:53:44.041812+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJXLO2LDM3KQE5NU","created_at":"2026-07-05T04:53:44.041812+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJXLO2LD","created_at":"2026-07-05T04:53:44.041812+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/YJXLO2LDM3KQE5NUHCBHDJSTIK","json":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK.json","graph_json":"https://pith.science/api/pith-number/YJXLO2LDM3KQE5NUHCBHDJSTIK/graph.json","events_json":"https://pith.science/api/pith-number/YJXLO2LDM3KQE5NUHCBHDJSTIK/events.json","paper":"https://pith.science/paper/YJXLO2LD"},"agent_actions":{"view_html":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK","download_json":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK.json","view_paper":"https://pith.science/paper/YJXLO2LD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.10126&json=true","fetch_graph":"https://pith.science/api/pith-number/YJXLO2LDM3KQE5NUHCBHDJSTIK/graph.json","fetch_events":"https://pith.science/api/pith-number/YJXLO2LDM3KQE5NUHCBHDJSTIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK/action/storage_attestation","attest_author":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK/action/author_attestation","sign_citation":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK/action/citation_signature","submit_replication":"https://pith.science/pith/YJXLO2LDM3KQE5NUHCBHDJSTIK/action/replication_record"}},"created_at":"2026-07-05T04:53:44.041812+00:00","updated_at":"2026-07-05T04:53:44.041812+00:00"}