{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UPOMWJDHSFXIF3Z5PDPMMRNCJW","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":"0f3ffafc1e0d288ce9bacee06f0624a81266112b5efb15de39780e7ccbc9a5bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T03:04:37Z","title_canon_sha256":"7f5cb0488f5da6847c6a64b85912f3cdc099e0958aaa5ec7b17b52746039d3c7"},"schema_version":"1.0","source":{"id":"2208.08608","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.08608","created_at":"2026-07-05T04:51:42Z"},{"alias_kind":"arxiv_version","alias_value":"2208.08608v2","created_at":"2026-07-05T04:51:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08608","created_at":"2026-07-05T04:51:42Z"},{"alias_kind":"pith_short_12","alias_value":"UPOMWJDHSFXI","created_at":"2026-07-05T04:51:42Z"},{"alias_kind":"pith_short_16","alias_value":"UPOMWJDHSFXIF3Z5","created_at":"2026-07-05T04:51:42Z"},{"alias_kind":"pith_short_8","alias_value":"UPOMWJDH","created_at":"2026-07-05T04:51:42Z"}],"graph_snapshots":[{"event_id":"sha256:ce2b066a66ca2c63b65b1da205a4b155d4fc535610f004f2bbf3af2825e9bb27","target":"graph","created_at":"2026-07-05T04:51:42Z","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/2208.08608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-based person retrieval aims to find the query person based on a textual description. The key is to learn a common latent space mapping between visual-textual modalities. To achieve this goal, existing works employ segmentation to obtain explicitly cross-modal alignments or utilize attention to explore salient alignments. These methods have two shortcomings: 1) Labeling cross-modal alignments are time-consuming. 2) Attention methods can explore salient cross-modal alignments but may ignore some subtle and valuable pairs. To relieve these issues, we introduce an Implicit Visual-Textual (IVT","authors_text":"Bo Ren, Haoqian Wu, Keyu Chen, Ruizhi Qiao, Wei Wen, Xiao Wang, Xiujun Shu, Yiran Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T03:04:37Z","title":"See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08608","kind":"arxiv","version":2},"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:dbce8f9de7354de1cfbb305ade1a00a7cd31c1903cd7d946eed0d48dde1aaff9","target":"record","created_at":"2026-07-05T04:51:42Z","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":"0f3ffafc1e0d288ce9bacee06f0624a81266112b5efb15de39780e7ccbc9a5bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T03:04:37Z","title_canon_sha256":"7f5cb0488f5da6847c6a64b85912f3cdc099e0958aaa5ec7b17b52746039d3c7"},"schema_version":"1.0","source":{"id":"2208.08608","kind":"arxiv","version":2}},"canonical_sha256":"a3dccb2467916e82ef3d78dec645a24d88c56bfe5de230831faef4c7f111de6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3dccb2467916e82ef3d78dec645a24d88c56bfe5de230831faef4c7f111de6d","first_computed_at":"2026-07-05T04:51:42.872334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:42.872334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0zp5Vy1umFbgQR5xmrOUFji7MegQ23VJp5IPOlildE44L39XSSTdelB+I05gedqGEFerRk77iFsc0wFTKOfYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:42.872683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.08608","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbce8f9de7354de1cfbb305ade1a00a7cd31c1903cd7d946eed0d48dde1aaff9","sha256:ce2b066a66ca2c63b65b1da205a4b155d4fc535610f004f2bbf3af2825e9bb27"],"state_sha256":"b97d10df3bdf3b6fcaad27c3ea9a8d13dddbd1ca66b7e6e4fe659373f8dbe8ff"}