{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MST32T3G7PGSDUEZ2JDI3PTNER","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":"5f70f53f7f99d4ac2cf22ac40ffc7023c29bf6bf660fe2a8ec55de47527fcbfe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T01:38:14Z","title_canon_sha256":"8af776f6b77dea9e4769d7ca4d62bfd95e19e4f06b0d3e4d626b7830da119163"},"schema_version":"1.0","source":{"id":"2412.20646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20646","created_at":"2026-07-05T09:55:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20646v1","created_at":"2026-07-05T09:55:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20646","created_at":"2026-07-05T09:55:20Z"},{"alias_kind":"pith_short_12","alias_value":"MST32T3G7PGS","created_at":"2026-07-05T09:55:20Z"},{"alias_kind":"pith_short_16","alias_value":"MST32T3G7PGSDUEZ","created_at":"2026-07-05T09:55:20Z"},{"alias_kind":"pith_short_8","alias_value":"MST32T3G","created_at":"2026-07-05T09:55:20Z"}],"graph_snapshots":[{"event_id":"sha256:3069dde80d7feca502edac262ccd0e20532eb1048bd94970c297ba6d5dd877c4","target":"graph","created_at":"2026-07-05T09:55:20Z","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/2412.20646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-based person search aims to retrieve the matched pedestrians from a large-scale image database according to the text description. The core difficulty of this task is how to extract effective details from pedestrian images and texts, and achieve cross-modal alignment in a common latent space. Prior works adopt image and text encoders pre-trained on unimodal data to extract global and local features from image and text respectively, and then global-local alignment is achieved explicitly. However, these approaches still lack the ability of understanding visual details, and the retrieval accu","authors_text":"Diping Li, Huangqun Chen, Jiafeng Xiao, Ling Xu, Ming Fang, Weifeng Zhang, Wei Shen, Yuxia Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T01:38:14Z","title":"Enhancing Visual Representation for Text-based Person Searching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20646","kind":"arxiv","version":1},"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:caa3293474e2510296e89f91cb167207ff7e1a17f6294ae8083dc23128f486d6","target":"record","created_at":"2026-07-05T09:55:20Z","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":"5f70f53f7f99d4ac2cf22ac40ffc7023c29bf6bf660fe2a8ec55de47527fcbfe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-30T01:38:14Z","title_canon_sha256":"8af776f6b77dea9e4769d7ca4d62bfd95e19e4f06b0d3e4d626b7830da119163"},"schema_version":"1.0","source":{"id":"2412.20646","kind":"arxiv","version":1}},"canonical_sha256":"64a7bd4f66fbcd21d099d2468dbe6d24694b8ec17c70951aab3d43e381b8b6c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64a7bd4f66fbcd21d099d2468dbe6d24694b8ec17c70951aab3d43e381b8b6c9","first_computed_at":"2026-07-05T09:55:20.204472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:20.204472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rmyCoe45BV+nGOVEFwMT9hgOL0p8ykZ0ohODAcSqUbB8XubhIoxHev6Di2wiZADODwfU6e6no8/xRIpTm9u4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:20.205241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:caa3293474e2510296e89f91cb167207ff7e1a17f6294ae8083dc23128f486d6","sha256:3069dde80d7feca502edac262ccd0e20532eb1048bd94970c297ba6d5dd877c4"],"state_sha256":"2928035d3d4289b0c66e867836e08b1505aa49294398c5c2c4deeb7aa9e0208e"}