{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AAGXIIHE6XUPQLBA5WJUGUHUB2","short_pith_number":"pith:AAGXIIHE","schema_version":"1.0","canonical_sha256":"000d7420e4f5e8f82c20ed934350f40eaf443a493194750e41f3e32287367a0c","source":{"kind":"arxiv","id":"2308.10045","version":2},"attestation_state":"computed","paper":{"title":"An Empirical Study of CLIP for Text-based Person Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Mang Ye, Min Cao, Min Zhang, Yang Bai, Ziyin Zeng","submitted_at":"2023-08-19T15:08:10Z","abstract_excerpt":"Text-based Person Search (TBPS) aims to retrieve the person images using natural language descriptions. Recently, Contrastive Language Image Pretraining (CLIP), a universal large cross-modal vision-language pre-training model, has remarkably performed over various cross-modal downstream tasks due to its powerful cross-modal semantic learning capacity. TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS. In order to explore the potential of the visual-language pre-training model for downstream TBPS tasks, this paper makes the first atte"},"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":"2308.10045","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-19T15:08:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4890d8de96f2beee28c09c4e757a81f4d0965647116d30000d590dc2a17a0232","abstract_canon_sha256":"2248ed03e930d0261e4a4871db5d4bfb3f44e7be5cbb235287e805e847dd5840"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:39.301211Z","signature_b64":"BqXG8E9digmWM4de+v1+KEnmOM72mF8m8MwjwWNX/p967AExk0gk+zpR0mGgHKqopi2qBQdGW64u4wqyk9DfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"000d7420e4f5e8f82c20ed934350f40eaf443a493194750e41f3e32287367a0c","last_reissued_at":"2026-07-05T07:26:39.300731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:39.300731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of CLIP for Text-based Person Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Mang Ye, Min Cao, Min Zhang, Yang Bai, Ziyin Zeng","submitted_at":"2023-08-19T15:08:10Z","abstract_excerpt":"Text-based Person Search (TBPS) aims to retrieve the person images using natural language descriptions. Recently, Contrastive Language Image Pretraining (CLIP), a universal large cross-modal vision-language pre-training model, has remarkably performed over various cross-modal downstream tasks due to its powerful cross-modal semantic learning capacity. TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS. In order to explore the potential of the visual-language pre-training model for downstream TBPS tasks, this paper makes the first atte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10045","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/2308.10045/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":"2308.10045","created_at":"2026-07-05T07:26:39.300789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10045v2","created_at":"2026-07-05T07:26:39.300789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10045","created_at":"2026-07-05T07:26:39.300789+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAGXIIHE6XUP","created_at":"2026-07-05T07:26:39.300789+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAGXIIHE6XUPQLBA","created_at":"2026-07-05T07:26:39.300789+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAGXIIHE","created_at":"2026-07-05T07:26:39.300789+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/AAGXIIHE6XUPQLBA5WJUGUHUB2","json":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2.json","graph_json":"https://pith.science/api/pith-number/AAGXIIHE6XUPQLBA5WJUGUHUB2/graph.json","events_json":"https://pith.science/api/pith-number/AAGXIIHE6XUPQLBA5WJUGUHUB2/events.json","paper":"https://pith.science/paper/AAGXIIHE"},"agent_actions":{"view_html":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2","download_json":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2.json","view_paper":"https://pith.science/paper/AAGXIIHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10045&json=true","fetch_graph":"https://pith.science/api/pith-number/AAGXIIHE6XUPQLBA5WJUGUHUB2/graph.json","fetch_events":"https://pith.science/api/pith-number/AAGXIIHE6XUPQLBA5WJUGUHUB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2/action/storage_attestation","attest_author":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2/action/author_attestation","sign_citation":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2/action/citation_signature","submit_replication":"https://pith.science/pith/AAGXIIHE6XUPQLBA5WJUGUHUB2/action/replication_record"}},"created_at":"2026-07-05T07:26:39.300789+00:00","updated_at":"2026-07-05T07:26:39.300789+00:00"}