{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7KSBU23XHFBDSMWG3QNYK6IBVD","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":"750835b9df73d9fc46e79999993cbd5878c37e81ca5565194fd7cf422860b764","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T14:27:01Z","title_canon_sha256":"66631183353fa9c9963e50deef47caa6063b289e0c37a9a310afa6f90f42e947"},"schema_version":"1.0","source":{"id":"2401.10011","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10011","created_at":"2026-07-05T11:55:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10011v3","created_at":"2026-07-05T11:55:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10011","created_at":"2026-07-05T11:55:13Z"},{"alias_kind":"pith_short_12","alias_value":"7KSBU23XHFBD","created_at":"2026-07-05T11:55:13Z"},{"alias_kind":"pith_short_16","alias_value":"7KSBU23XHFBDSMWG","created_at":"2026-07-05T11:55:13Z"},{"alias_kind":"pith_short_8","alias_value":"7KSBU23X","created_at":"2026-07-05T11:55:13Z"}],"graph_snapshots":[{"event_id":"sha256:81a4b3239c628fa6c67451438c09d5b66d869b8d053c92c05310c4d59b85555a","target":"graph","created_at":"2026-07-05T11:55:13Z","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/2401.10011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weakly supervised text-based person retrieval seeks to retrieve images of a target person using textual descriptions, without relying on identity annotations and is more challenging and practical. The primary challenge is the intra-class differences, encompassing intra-modal feature variations and cross-modal semantic gaps. Prior works have focused on instance-level samples and ignored prototypical features of each person which are intrinsic and invariant. Toward this, we propose a Cross-Modal Prototypical Contrastive Learning (CPCL) method. In practice, the CPCL introduces the CLIP model to w","authors_text":"Bowen Huang, Chuanlin Lan, Dongxiao Yu, Jibin Yang, Xiaowei Zhang, Xinpeng Zhao, Yanwei Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T14:27:01Z","title":"CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10011","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":"sha256:89c27902cbf7953e833a37e19733d89d5ca2360233d828ba4709aaa613751826","target":"record","created_at":"2026-07-05T11:55:13Z","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":"750835b9df73d9fc46e79999993cbd5878c37e81ca5565194fd7cf422860b764","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T14:27:01Z","title_canon_sha256":"66631183353fa9c9963e50deef47caa6063b289e0c37a9a310afa6f90f42e947"},"schema_version":"1.0","source":{"id":"2401.10011","kind":"arxiv","version":3}},"canonical_sha256":"faa41a6b7739423932c6dc1b857901a8c17b7d5ff684d805628dea79e6dc0ea4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"faa41a6b7739423932c6dc1b857901a8c17b7d5ff684d805628dea79e6dc0ea4","first_computed_at":"2026-07-05T11:55:13.606699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:13.606699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sxhbu1Ns/7Fy00sCyIHlp/pgTnQ8oNnXCk4I1W3YrpyKOCYD81Y12wtxtleyhgnqreA9NHP3U7f14eu8dctGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:13.607181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.10011","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89c27902cbf7953e833a37e19733d89d5ca2360233d828ba4709aaa613751826","sha256:81a4b3239c628fa6c67451438c09d5b66d869b8d053c92c05310c4d59b85555a"],"state_sha256":"41c6537ecef463a9c618a67541a9058ac1d7ace7fa0f95d5bf54bacbd0542d39"}