{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2I2GSVDKWWKRF4WG7XJGCHLXN4","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":"1362145a7baefb57fad380621e5aedb1dbd0f16b1c1baad4e3c4df472a85a278","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T07:16:41Z","title_canon_sha256":"429cdf3597de26e6599eab434d06c95c01c03d2d2060553f5e7a62cd6ad1d611"},"schema_version":"1.0","source":{"id":"2506.11515","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11515","created_at":"2026-07-05T11:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11515v1","created_at":"2026-07-05T11:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11515","created_at":"2026-07-05T11:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"2I2GSVDKWWKR","created_at":"2026-07-05T11:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"2I2GSVDKWWKRF4WG","created_at":"2026-07-05T11:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"2I2GSVDK","created_at":"2026-07-05T11:21:05Z"}],"graph_snapshots":[{"event_id":"sha256:ff0cc35b35815fd8343338c2726d8da02cc771c3748db8e41475b028d8558f30","target":"graph","created_at":"2026-07-05T11:21:05Z","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/2506.11515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Two-Tower Vision--Language Models (VLMs) have demonstrated strong performance across various downstream VL tasks. While BridgeTower further enhances performance by building bridges between encoders, it \\textit{(i)} suffers from ineffective layer-by-layer utilization of unimodal representations, \\textit{(ii)} restricts the flexible exploitation of different levels of unimodal semantic knowledge, and \\textit{(iii)} is limited to the evaluation on traditional low-resolution datasets only with the Two-Tower VLM architecture. In this work, we propose Manager, a lightweight, efficient and effective ","authors_text":"Libo Qin, Min-Yen Kan, Wanxiang Che, Xiao Xu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T07:16:41Z","title":"Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11515","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":"sha256:513a1425f1a96a5ba21c98b9266e55a9c45cf2f18908bf2b6406a329fcf6246c","target":"record","created_at":"2026-07-05T11:21:05Z","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":"1362145a7baefb57fad380621e5aedb1dbd0f16b1c1baad4e3c4df472a85a278","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T07:16:41Z","title_canon_sha256":"429cdf3597de26e6599eab434d06c95c01c03d2d2060553f5e7a62cd6ad1d611"},"schema_version":"1.0","source":{"id":"2506.11515","kind":"arxiv","version":1}},"canonical_sha256":"d23469546ab59512f2c6fdd2611d776f2b7f6b71039d2fb2a75cf95c2dd7f759","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d23469546ab59512f2c6fdd2611d776f2b7f6b71039d2fb2a75cf95c2dd7f759","first_computed_at":"2026-07-05T11:21:05.899257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:05.899257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mLruihpSnxsHkk+nfkfE6CpZGlkYhxD6/Tz3JUnoXGIQT921vLW5tyhPxBBe/RZ8dQT2g8Hm7Bdhz3xKD8wQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:05.899757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11515","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:513a1425f1a96a5ba21c98b9266e55a9c45cf2f18908bf2b6406a329fcf6246c","sha256:ff0cc35b35815fd8343338c2726d8da02cc771c3748db8e41475b028d8558f30"],"state_sha256":"faead5535997aea168d6c8fc2e67ac454388aad04eedf8cdfed34952ff1d4ca2"}