{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RXEVKJPL6RFTBWYKWSZQTX7Q3C","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":"481ac926c1c6032ea88f34af87ae62d86c527f526077d8e12689baa12b4d9e8a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T11:41:55Z","title_canon_sha256":"733f5bb573df0b8f616069210901908d98e1cbc783e1a2eb3991aff5f3c3b266"},"schema_version":"1.0","source":{"id":"2502.20008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20008","created_at":"2026-07-05T10:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20008v1","created_at":"2026-07-05T10:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20008","created_at":"2026-07-05T10:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"RXEVKJPL6RFT","created_at":"2026-07-05T10:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"RXEVKJPL6RFTBWYK","created_at":"2026-07-05T10:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"RXEVKJPL","created_at":"2026-07-05T10:20:56Z"}],"graph_snapshots":[{"event_id":"sha256:45e8485f0cef02e2a3f26f9049cbaa5e497955f29847b55d174266f0f03488b6","target":"graph","created_at":"2026-07-05T10:20:56Z","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/2502.20008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information retrieval is indispensable for today's Internet applications, yet traditional semantic matching techniques often fall short in capturing the fine-grained cross-modal interactions required for complex queries. Although late-fusion two-tower architectures attempt to bridge this gap by independently encoding visual and textual data before merging them at a high level, they frequently overlook the subtle interplay essential for comprehensive understanding. In this work, we rigorously assess these limitations and introduce a unified retrieval framework that fuses visual and textual cues","authors_text":"Lang Huang, Qiyu Wu, Toshihiko Yamasaki, Zhongtao Miao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T11:41:55Z","title":"Joint Fusion and Encoding: Advancing Multimodal Retrieval from the Ground Up"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20008","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":"sha256:5dc50ec0a2c68dd73709f09ee5ab943b6989a275cb79ee9c758d41a7f8847bb9","target":"record","created_at":"2026-07-05T10:20:56Z","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":"481ac926c1c6032ea88f34af87ae62d86c527f526077d8e12689baa12b4d9e8a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T11:41:55Z","title_canon_sha256":"733f5bb573df0b8f616069210901908d98e1cbc783e1a2eb3991aff5f3c3b266"},"schema_version":"1.0","source":{"id":"2502.20008","kind":"arxiv","version":1}},"canonical_sha256":"8dc95525ebf44b30db0ab4b309dff0d8a5c0bbf003f243ca22168cd7c3c252ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dc95525ebf44b30db0ab4b309dff0d8a5c0bbf003f243ca22168cd7c3c252ec","first_computed_at":"2026-07-05T10:20:56.779836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:56.779836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6f+uzfBQ2oytLSx+pABK1T5YkLqTk9Hxh5HozVUXrtxkz5OVlje5vRZLIRydFrnP9X7CnUQLxQa1uCbuA/TDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:56.783594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dc50ec0a2c68dd73709f09ee5ab943b6989a275cb79ee9c758d41a7f8847bb9","sha256:45e8485f0cef02e2a3f26f9049cbaa5e497955f29847b55d174266f0f03488b6"],"state_sha256":"79e9c68fe291b50e210d7d130d6ccbad978ea9dcce0c6bc843c383dbb4e928db"}