{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T2PISE2R26N47LLVTLSUXLTEPU","short_pith_number":"pith:T2PISE2R","schema_version":"1.0","canonical_sha256":"9e9e891351d79bcfad759ae54bae647d18f062e660bbacfd37962ec5b9af2953","source":{"kind":"arxiv","id":"2606.28350","version":1},"attestation_state":"computed","paper":{"title":"UniCA: Bi-directional Cross-Attention with Positive Similarity Loss for Robust Multi-Modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Wenlong Zhang, Yini Huang","submitted_at":"2026-06-03T10:57:28Z","abstract_excerpt":"Multi-modal retrieval has become increasingly critical for handling the growing volume of integrated visual-textual data in real-world applications, but existing frameworks rely on implicit fusion via text encoder self-attention, limiting explicit cross-modal semantic alignment. To address this gap, this paper proposes UniCA (Unified Cross-Attention Encoder), a multi-modal retrieval model with four key innovations: 1) a bi-directional cross-attention (Bi-CA) block that enables active semantic exchange between visual and textual tokens prior to concatenation, capturing inter-modal correlations "},"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":"2606.28350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T10:57:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"be39f9ee84541592bd1ce4b90f8d26681a7a40569c190af5330c798624e74d64","abstract_canon_sha256":"7401d26d1979ba49eda38fe7f82b4ca11d54de3b479a91420bf84601e998a644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:11.659271Z","signature_b64":"PmfuELT/msJs6ISfClcRIILUUm9AQWanWyauEUtOuApxvuv7rL3EhVzPr/kcCC0RiQcOecsVp/s+Uii7ff//CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e9e891351d79bcfad759ae54bae647d18f062e660bbacfd37962ec5b9af2953","last_reissued_at":"2026-06-30T00:15:11.658859Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:11.658859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniCA: Bi-directional Cross-Attention with Positive Similarity Loss for Robust Multi-Modal Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Wenlong Zhang, Yini Huang","submitted_at":"2026-06-03T10:57:28Z","abstract_excerpt":"Multi-modal retrieval has become increasingly critical for handling the growing volume of integrated visual-textual data in real-world applications, but existing frameworks rely on implicit fusion via text encoder self-attention, limiting explicit cross-modal semantic alignment. To address this gap, this paper proposes UniCA (Unified Cross-Attention Encoder), a multi-modal retrieval model with four key innovations: 1) a bi-directional cross-attention (Bi-CA) block that enables active semantic exchange between visual and textual tokens prior to concatenation, capturing inter-modal correlations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28350","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/2606.28350/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":"2606.28350","created_at":"2026-06-30T00:15:11.658917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28350v1","created_at":"2026-06-30T00:15:11.658917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28350","created_at":"2026-06-30T00:15:11.658917+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2PISE2R26N4","created_at":"2026-06-30T00:15:11.658917+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2PISE2R26N47LLV","created_at":"2026-06-30T00:15:11.658917+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2PISE2R","created_at":"2026-06-30T00:15:11.658917+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/T2PISE2R26N47LLVTLSUXLTEPU","json":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU.json","graph_json":"https://pith.science/api/pith-number/T2PISE2R26N47LLVTLSUXLTEPU/graph.json","events_json":"https://pith.science/api/pith-number/T2PISE2R26N47LLVTLSUXLTEPU/events.json","paper":"https://pith.science/paper/T2PISE2R"},"agent_actions":{"view_html":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU","download_json":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU.json","view_paper":"https://pith.science/paper/T2PISE2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28350&json=true","fetch_graph":"https://pith.science/api/pith-number/T2PISE2R26N47LLVTLSUXLTEPU/graph.json","fetch_events":"https://pith.science/api/pith-number/T2PISE2R26N47LLVTLSUXLTEPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU/action/storage_attestation","attest_author":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU/action/author_attestation","sign_citation":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU/action/citation_signature","submit_replication":"https://pith.science/pith/T2PISE2R26N47LLVTLSUXLTEPU/action/replication_record"}},"created_at":"2026-06-30T00:15:11.658917+00:00","updated_at":"2026-06-30T00:15:11.658917+00:00"}