{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T2PISE2R26N47LLVTLSUXLTEPU","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":"7401d26d1979ba49eda38fe7f82b4ca11d54de3b479a91420bf84601e998a644","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T10:57:28Z","title_canon_sha256":"be39f9ee84541592bd1ce4b90f8d26681a7a40569c190af5330c798624e74d64"},"schema_version":"1.0","source":{"id":"2606.28350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28350","created_at":"2026-06-30T00:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28350v1","created_at":"2026-06-30T00:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28350","created_at":"2026-06-30T00:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"T2PISE2R26N4","created_at":"2026-06-30T00:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"T2PISE2R26N47LLV","created_at":"2026-06-30T00:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"T2PISE2R","created_at":"2026-06-30T00:15:11Z"}],"graph_snapshots":[{"event_id":"sha256:cbdbef8a783cf342482e9ec27e3ebbe06502356c4a17704f41124770eba22688","target":"graph","created_at":"2026-06-30T00:15:11Z","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/2606.28350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Wenlong Zhang, Yini Huang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T10:57:28Z","title":"UniCA: Bi-directional Cross-Attention with Positive Similarity Loss for Robust Multi-Modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28350","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":"sha256:38b971edc77463ddde72d86d6707aca043c3ab438f7d9d8b0d4820eb9ff7497d","target":"record","created_at":"2026-06-30T00:15:11Z","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":"7401d26d1979ba49eda38fe7f82b4ca11d54de3b479a91420bf84601e998a644","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-03T10:57:28Z","title_canon_sha256":"be39f9ee84541592bd1ce4b90f8d26681a7a40569c190af5330c798624e74d64"},"schema_version":"1.0","source":{"id":"2606.28350","kind":"arxiv","version":1}},"canonical_sha256":"9e9e891351d79bcfad759ae54bae647d18f062e660bbacfd37962ec5b9af2953","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e9e891351d79bcfad759ae54bae647d18f062e660bbacfd37962ec5b9af2953","first_computed_at":"2026-06-30T00:15:11.658859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:11.658859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PmfuELT/msJs6ISfClcRIILUUm9AQWanWyauEUtOuApxvuv7rL3EhVzPr/kcCC0RiQcOecsVp/s+Uii7ff//CQ==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:11.659271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38b971edc77463ddde72d86d6707aca043c3ab438f7d9d8b0d4820eb9ff7497d","sha256:cbdbef8a783cf342482e9ec27e3ebbe06502356c4a17704f41124770eba22688"],"state_sha256":"15aff88e57130c9fcc5c88d0e652a0cd6ccb7b62418689912a66420f01c727c4"}