{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5ENVLNOUW3XN7HDQ3QR6EPL4QJ","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":"63d912b7e380a217db1a437d7bfc6407e12df4b5b95bf1eb918ed6fca82ae3cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T03:06:22Z","title_canon_sha256":"92c94dfbeb941cc141a0753d8a904e4a6eb9caa820369c62af51e2356e620cab"},"schema_version":"1.0","source":{"id":"2509.09118","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09118","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09118v1","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09118","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"5ENVLNOUW3XN","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"5ENVLNOUW3XN7HDQ","created_at":"2026-07-05T12:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"5ENVLNOU","created_at":"2026-07-05T12:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:4f6b4d3f975974e0c22d1a1b6843d813a04a1245b89be0456dfbd9cbd529e627","target":"graph","created_at":"2026-07-05T12:09:29Z","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/2509.09118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Contrastive Language-Image Pre-training (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-scale annotated vision-language data focused on person-centric images, and (ii) the inherent limitations of global contrastive learning, which struggles to maintain discriminative local features crucial for fine-grained matching while remaining vulnerable to noisy text tokens. This work advances CLIP for person representation learning through synergistic improvements in data cu","authors_text":"Kaicheng Yang, Qichuan Ding, Tianlu Zheng, Xiang An, Yifan Zhang, Ziyong Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T03:06:22Z","title":"Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09118","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":"sha256:6797aa2bf81b8cc5f77b33a57c247f840cbc9cfaa6a72fafaadc226cd19623d4","target":"record","created_at":"2026-07-05T12:09:29Z","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":"63d912b7e380a217db1a437d7bfc6407e12df4b5b95bf1eb918ed6fca82ae3cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T03:06:22Z","title_canon_sha256":"92c94dfbeb941cc141a0753d8a904e4a6eb9caa820369c62af51e2356e620cab"},"schema_version":"1.0","source":{"id":"2509.09118","kind":"arxiv","version":1}},"canonical_sha256":"e91b55b5d4b6eedf9c70dc23e23d7c8278f52781b160fc03cfd0a57028612a1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e91b55b5d4b6eedf9c70dc23e23d7c8278f52781b160fc03cfd0a57028612a1d","first_computed_at":"2026-07-05T12:09:29.784513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:29.784513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5g0Pec/euvgYhj4o2R4XLXarCxoyOtcRMX2I+RR0VzMwVLoee8cFNGmfrL9QfM92/YQowhqjA4OyX0KqFRJkCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:29.784993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09118","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6797aa2bf81b8cc5f77b33a57c247f840cbc9cfaa6a72fafaadc226cd19623d4","sha256:4f6b4d3f975974e0c22d1a1b6843d813a04a1245b89be0456dfbd9cbd529e627"],"state_sha256":"bd8f3ff2431ff08eea839415c7d78e622b2cdbba4f365937335d36b16e97575b"}