{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WFNXSDPEF7TCBZ3XSPBJ26WYK6","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":"935ca6d1d161336e83410ef493b5d7f168bfaeffed61604688115234f2c184d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-16T01:26:10Z","title_canon_sha256":"857b9b25013594a27880162d5af138a2ac493a1665491d6b7d10f146f60aa73b"},"schema_version":"1.0","source":{"id":"2207.07802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07802","created_at":"2026-07-05T04:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07802v1","created_at":"2026-07-05T04:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07802","created_at":"2026-07-05T04:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"WFNXSDPEF7TC","created_at":"2026-07-05T04:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"WFNXSDPEF7TCBZ3X","created_at":"2026-07-05T04:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"WFNXSDPE","created_at":"2026-07-05T04:40:56Z"}],"graph_snapshots":[{"event_id":"sha256:791485c56695df4eac6a92dcb3c692df7caa023c28b8726e9c72cf2724fd0f6d","target":"graph","created_at":"2026-07-05T04:40:56Z","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/2207.07802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image person re-identification (ReID) aims to search for pedestrian images of an interested identity via textual descriptions. It is challenging due to both rich intra-modal variations and significant inter-modal gaps. Existing works usually ignore the difference in feature granularity between the two modalities, i.e., the visual features are usually fine-grained while textual features are coarse, which is mainly responsible for the large inter-modal gaps. In this paper, we propose an end-to-end framework based on transformers to learn granularity-unified representations for both modal","authors_text":"Changxing Ding, Jian Wang, Meng Fang, Xinyu Zhang, Zhifeng Lin, Zhiyin Shao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-16T01:26:10Z","title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07802","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":"sha256:997613b1fc2eb0330e079767604240061e29a5625b65ab191835b81e640c970e","target":"record","created_at":"2026-07-05T04:40:56Z","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":"935ca6d1d161336e83410ef493b5d7f168bfaeffed61604688115234f2c184d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-16T01:26:10Z","title_canon_sha256":"857b9b25013594a27880162d5af138a2ac493a1665491d6b7d10f146f60aa73b"},"schema_version":"1.0","source":{"id":"2207.07802","kind":"arxiv","version":1}},"canonical_sha256":"b15b790de42fe620e77793c29d7ad857bcd373a7854a35c2027e8a4ad0cd1244","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b15b790de42fe620e77793c29d7ad857bcd373a7854a35c2027e8a4ad0cd1244","first_computed_at":"2026-07-05T04:40:56.587497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:56.587497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vErQ5kOwMC/9p4EtYUWSsQ0L1AQz4EksMPWI7iDLEXx0Qs53mbo599Fj8P8c+Tg7uzH8fqmZp0gsES499agTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:56.587891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:997613b1fc2eb0330e079767604240061e29a5625b65ab191835b81e640c970e","sha256:791485c56695df4eac6a92dcb3c692df7caa023c28b8726e9c72cf2724fd0f6d"],"state_sha256":"ef38d5b183574d425dda51fbc76b8821a8a3f0b2d10cae746c5d3b637bd57eef"}