{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NBNAQVDQXLQRTEEPRAKRTMYIGJ","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":"c4cbb50b3fe5dc1ce6ee4aa4bd0e21c462bc11ae1df9771aa9c9001ec56dc85e","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T05:29:14Z","title_canon_sha256":"e7f42d75d65cfeb9c0cbade6fe03805c5d1371c3e67ad69cb985d929f0fa3f38"},"schema_version":"1.0","source":{"id":"2404.10292","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10292","created_at":"2026-07-05T10:08:15Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10292v3","created_at":"2026-07-05T10:08:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10292","created_at":"2026-07-05T10:08:15Z"},{"alias_kind":"pith_short_12","alias_value":"NBNAQVDQXLQR","created_at":"2026-07-05T10:08:15Z"},{"alias_kind":"pith_short_16","alias_value":"NBNAQVDQXLQRTEEP","created_at":"2026-07-05T10:08:15Z"},{"alias_kind":"pith_short_8","alias_value":"NBNAQVDQ","created_at":"2026-07-05T10:08:15Z"}],"graph_snapshots":[{"event_id":"sha256:3fee32b846df3d4d2cd26209a981c4c4e5eb647a37b7cfe728b434b72c5487f7","target":"graph","created_at":"2026-07-05T10:08:15Z","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/2404.10292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in theory, the scientific conundrum persists that how much generated data optimally fuels subsequent model training. We observe that only a subset of the data in these constructed datasets plays a decisive role. Therefore, we introduce a new Filtering-WoRA paradigm, which contains a filtering algorithm to identify this crucial data subset and WoRA (Weighted Lo","authors_text":"Gangyi Ding, Hao Fei, Jintao Sun, Zhedong Zheng","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T05:29:14Z","title":"From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10292","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:f61576240ae2beaf9a0d72ee6846fd7973b1bdbf4298ad11b9e0037b223dacde","target":"record","created_at":"2026-07-05T10:08:15Z","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":"c4cbb50b3fe5dc1ce6ee4aa4bd0e21c462bc11ae1df9771aa9c9001ec56dc85e","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T05:29:14Z","title_canon_sha256":"e7f42d75d65cfeb9c0cbade6fe03805c5d1371c3e67ad69cb985d929f0fa3f38"},"schema_version":"1.0","source":{"id":"2404.10292","kind":"arxiv","version":3}},"canonical_sha256":"685a085470bae119908f881519b30832423bbd2585a43309e0e042836f989162","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"685a085470bae119908f881519b30832423bbd2585a43309e0e042836f989162","first_computed_at":"2026-07-05T10:08:15.739814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:15.739814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5kTS6wMET2dYN4j9hBohSvvwwpCi1/HKwf1ZEJUthSYh6aIaqPr3veGeP38QK3fBCJgcgFbW025o8RsIb68Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:15.740249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10292","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f61576240ae2beaf9a0d72ee6846fd7973b1bdbf4298ad11b9e0037b223dacde","sha256:3fee32b846df3d4d2cd26209a981c4c4e5eb647a37b7cfe728b434b72c5487f7"],"state_sha256":"ada33053a736fcf6662537a0d468555841c73382bdf2d0212d3e506593f21b5d"}