{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:72CZFA7GWF72E5W3NVMUC7KJVE","short_pith_number":"pith:72CZFA7G","schema_version":"1.0","canonical_sha256":"fe859283e6b17fa276db6d59417d49a925126b3b7877615de89fd33dc2221276","source":{"kind":"arxiv","id":"2109.05523","version":1},"attestation_state":"computed","paper":{"title":"Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haijun Shan, Jianqing Fan, Siyuan Wang, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2021-09-12T14:21:15Z","abstract_excerpt":"Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer grain, i.e., phrase level. In this paper, we explore to introduce additional phrase-level supervision for the better identification of mismatched units in the text. In practice, multi-grained semantic labels are automatically constructed for a query image in both sentence-level and phrase-level. We construct text scene graphs for the matched sentences and extra"},"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":"2109.05523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-12T14:21:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"39b036cfaf499d1df5772318d733d11f5b1e158b9647236f3b7ba6bb441e8755","abstract_canon_sha256":"e95ecde84c1d97a86fe437d81e72d2e8b58b43d682c61d0ac4f82e4850b88d57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:39.896751Z","signature_b64":"PzQXMRkacnEEzvpucRDqOn/ohsgq6Ws5lce+Bt9dRo7yGO6Gg6+ChdrdMwrZ0PrG7CDkF8+6Ab2mcUl7wSB+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe859283e6b17fa276db6d59417d49a925126b3b7877615de89fd33dc2221276","last_reissued_at":"2026-07-05T03:13:39.896345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:39.896345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Haijun Shan, Jianqing Fan, Siyuan Wang, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2021-09-12T14:21:15Z","abstract_excerpt":"Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer grain, i.e., phrase level. In this paper, we explore to introduce additional phrase-level supervision for the better identification of mismatched units in the text. In practice, multi-grained semantic labels are automatically constructed for a query image in both sentence-level and phrase-level. We construct text scene graphs for the matched sentences and extra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05523","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/2109.05523/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":"2109.05523","created_at":"2026-07-05T03:13:39.896405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05523v1","created_at":"2026-07-05T03:13:39.896405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05523","created_at":"2026-07-05T03:13:39.896405+00:00"},{"alias_kind":"pith_short_12","alias_value":"72CZFA7GWF72","created_at":"2026-07-05T03:13:39.896405+00:00"},{"alias_kind":"pith_short_16","alias_value":"72CZFA7GWF72E5W3","created_at":"2026-07-05T03:13:39.896405+00:00"},{"alias_kind":"pith_short_8","alias_value":"72CZFA7G","created_at":"2026-07-05T03:13:39.896405+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/72CZFA7GWF72E5W3NVMUC7KJVE","json":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE.json","graph_json":"https://pith.science/api/pith-number/72CZFA7GWF72E5W3NVMUC7KJVE/graph.json","events_json":"https://pith.science/api/pith-number/72CZFA7GWF72E5W3NVMUC7KJVE/events.json","paper":"https://pith.science/paper/72CZFA7G"},"agent_actions":{"view_html":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE","download_json":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE.json","view_paper":"https://pith.science/paper/72CZFA7G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05523&json=true","fetch_graph":"https://pith.science/api/pith-number/72CZFA7GWF72E5W3NVMUC7KJVE/graph.json","fetch_events":"https://pith.science/api/pith-number/72CZFA7GWF72E5W3NVMUC7KJVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE/action/storage_attestation","attest_author":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE/action/author_attestation","sign_citation":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE/action/citation_signature","submit_replication":"https://pith.science/pith/72CZFA7GWF72E5W3NVMUC7KJVE/action/replication_record"}},"created_at":"2026-07-05T03:13:39.896405+00:00","updated_at":"2026-07-05T03:13:39.896405+00:00"}