{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GYPZL2QAU2FGDIYRTUBWETHH6W","short_pith_number":"pith:GYPZL2QA","schema_version":"1.0","canonical_sha256":"361f95ea00a68a61a3119d03624ce7f5b45669f705299b3e2e64be04a30779ae","source":{"kind":"arxiv","id":"2506.10550","version":1},"attestation_state":"computed","paper":{"title":"ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing He, Kexin Zhang, Lingling Li, Puhua Chen, Yiqing Wang","submitted_at":"2025-06-12T10:17:30Z","abstract_excerpt":"This report presents ContextRefine-CLIP (CR-CLIP), an efficient model for visual-textual multi-instance retrieval tasks. The approach is based on the dual-encoder AVION, on which we introduce a cross-modal attention flow module to achieve bidirectional dynamic interaction and refinement between visual and textual features to generate more context-aware joint representations. For soft-label relevance matrices provided in tasks such as EPIC-KITCHENS-100, CR-CLIP can work with Symmetric Multi-Similarity Loss to achieve more accurate semantic alignment and optimization using the refined features. "},"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":"2506.10550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-12T10:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"1971626e81411ee28c7a33df9038f453d13d6fbc4567ba5d633e95b429479864","abstract_canon_sha256":"9117c4ae66b16ebe72342c36011ef6665d0304c28b8821dec43b107c4a6051fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:26.181709Z","signature_b64":"6KT8V5Acz40n4Kzha5LiAr20JTiHMHwuSMXApu2AGnstCErBeDEJsv5nEhYU5ysh5NNbLFFW4mJydp1/aaCTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"361f95ea00a68a61a3119d03624ce7f5b45669f705299b3e2e64be04a30779ae","last_reissued_at":"2026-07-05T11:20:26.181190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:26.181190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing He, Kexin Zhang, Lingling Li, Puhua Chen, Yiqing Wang","submitted_at":"2025-06-12T10:17:30Z","abstract_excerpt":"This report presents ContextRefine-CLIP (CR-CLIP), an efficient model for visual-textual multi-instance retrieval tasks. The approach is based on the dual-encoder AVION, on which we introduce a cross-modal attention flow module to achieve bidirectional dynamic interaction and refinement between visual and textual features to generate more context-aware joint representations. For soft-label relevance matrices provided in tasks such as EPIC-KITCHENS-100, CR-CLIP can work with Symmetric Multi-Similarity Loss to achieve more accurate semantic alignment and optimization using the refined features. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10550","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/2506.10550/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":"2506.10550","created_at":"2026-07-05T11:20:26.181271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10550v1","created_at":"2026-07-05T11:20:26.181271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10550","created_at":"2026-07-05T11:20:26.181271+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYPZL2QAU2FG","created_at":"2026-07-05T11:20:26.181271+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYPZL2QAU2FGDIYR","created_at":"2026-07-05T11:20:26.181271+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYPZL2QA","created_at":"2026-07-05T11:20:26.181271+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/GYPZL2QAU2FGDIYRTUBWETHH6W","json":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W.json","graph_json":"https://pith.science/api/pith-number/GYPZL2QAU2FGDIYRTUBWETHH6W/graph.json","events_json":"https://pith.science/api/pith-number/GYPZL2QAU2FGDIYRTUBWETHH6W/events.json","paper":"https://pith.science/paper/GYPZL2QA"},"agent_actions":{"view_html":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W","download_json":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W.json","view_paper":"https://pith.science/paper/GYPZL2QA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10550&json=true","fetch_graph":"https://pith.science/api/pith-number/GYPZL2QAU2FGDIYRTUBWETHH6W/graph.json","fetch_events":"https://pith.science/api/pith-number/GYPZL2QAU2FGDIYRTUBWETHH6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W/action/storage_attestation","attest_author":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W/action/author_attestation","sign_citation":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W/action/citation_signature","submit_replication":"https://pith.science/pith/GYPZL2QAU2FGDIYRTUBWETHH6W/action/replication_record"}},"created_at":"2026-07-05T11:20:26.181271+00:00","updated_at":"2026-07-05T11:20:26.181271+00:00"}