{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5ENVLNOUW3XN7HDQ3QR6EPL4QJ","short_pith_number":"pith:5ENVLNOU","schema_version":"1.0","canonical_sha256":"e91b55b5d4b6eedf9c70dc23e23d7c8278f52781b160fc03cfd0a57028612a1d","source":{"kind":"arxiv","id":"2509.09118","version":1},"attestation_state":"computed","paper":{"title":"Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaicheng Yang, Qichuan Ding, Tianlu Zheng, Xiang An, Yifan Zhang, Ziyong Feng","submitted_at":"2025-09-11T03:06:22Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.09118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-11T03:06:22Z","cross_cats_sorted":[],"title_canon_sha256":"92c94dfbeb941cc141a0753d8a904e4a6eb9caa820369c62af51e2356e620cab","abstract_canon_sha256":"63d912b7e380a217db1a437d7bfc6407e12df4b5b95bf1eb918ed6fca82ae3cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:29.784993Z","signature_b64":"5g0Pec/euvgYhj4o2R4XLXarCxoyOtcRMX2I+RR0VzMwVLoee8cFNGmfrL9QfM92/YQowhqjA4OyX0KqFRJkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e91b55b5d4b6eedf9c70dc23e23d7c8278f52781b160fc03cfd0a57028612a1d","last_reissued_at":"2026-07-05T12:09:29.784513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:29.784513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaicheng Yang, Qichuan Ding, Tianlu Zheng, Xiang An, Yifan Zhang, Ziyong Feng","submitted_at":"2025-09-11T03:06:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09118","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.09118/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.09118","created_at":"2026-07-05T12:09:29.784576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09118v1","created_at":"2026-07-05T12:09:29.784576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09118","created_at":"2026-07-05T12:09:29.784576+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ENVLNOUW3XN","created_at":"2026-07-05T12:09:29.784576+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ENVLNOUW3XN7HDQ","created_at":"2026-07-05T12:09:29.784576+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ENVLNOU","created_at":"2026-07-05T12:09:29.784576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ","json":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ.json","graph_json":"https://pith.science/api/pith-number/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/graph.json","events_json":"https://pith.science/api/pith-number/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/events.json","paper":"https://pith.science/paper/5ENVLNOU"},"agent_actions":{"view_html":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ","download_json":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ.json","view_paper":"https://pith.science/paper/5ENVLNOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09118&json=true","fetch_graph":"https://pith.science/api/pith-number/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/action/storage_attestation","attest_author":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/action/author_attestation","sign_citation":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/action/citation_signature","submit_replication":"https://pith.science/pith/5ENVLNOUW3XN7HDQ3QR6EPL4QJ/action/replication_record"}},"created_at":"2026-07-05T12:09:29.784576+00:00","updated_at":"2026-07-05T12:09:29.784576+00:00"}