{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2I2GSVDKWWKRF4WG7XJGCHLXN4","short_pith_number":"pith:2I2GSVDK","canonical_record":{"source":{"id":"2506.11515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T07:16:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"429cdf3597de26e6599eab434d06c95c01c03d2d2060553f5e7a62cd6ad1d611","abstract_canon_sha256":"1362145a7baefb57fad380621e5aedb1dbd0f16b1c1baad4e3c4df472a85a278"},"schema_version":"1.0"},"canonical_sha256":"d23469546ab59512f2c6fdd2611d776f2b7f6b71039d2fb2a75cf95c2dd7f759","source":{"kind":"arxiv","id":"2506.11515","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2I2GSVDKWWKRF4WG7XJGCHLXN4","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-13T07:16:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"429cdf3597de26e6599eab434d06c95c01c03d2d2060553f5e7a62cd6ad1d611","abstract_canon_sha256":"1362145a7baefb57fad380621e5aedb1dbd0f16b1c1baad4e3c4df472a85a278"},"schema_version":"1.0"},"canonical_sha256":"d23469546ab59512f2c6fdd2611d776f2b7f6b71039d2fb2a75cf95c2dd7f759","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:05.899757Z","signature_b64":"mLruihpSnxsHkk+nfkfE6CpZGlkYhxD6/Tz3JUnoXGIQT921vLW5tyhPxBBe/RZ8dQT2g8Hm7Bdhz3xKD8wQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d23469546ab59512f2c6fdd2611d776f2b7f6b71039d2fb2a75cf95c2dd7f759","last_reissued_at":"2026-07-05T11:21:05.899257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:05.899257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11515","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSW3YCMqjmkUQsToLj4ElzbqWfk5sLB0BMDX8UQ2oc6k3gkoysbbsh8FTUkn44lf8BZpsNvBeixISHKVq27TBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:27:25.871746Z"},"content_sha256":"513a1425f1a96a5ba21c98b9266e55a9c45cf2f18908bf2b6406a329fcf6246c","schema_version":"1.0","event_id":"sha256:513a1425f1a96a5ba21c98b9266e55a9c45cf2f18908bf2b6406a329fcf6246c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2I2GSVDKWWKRF4WG7XJGCHLXN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Libo Qin, Min-Yen Kan, Wanxiang Che, Xiao Xu","submitted_at":"2025-06-13T07:16:41Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11515","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/2506.11515/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v2vJnLK2p/oC63sdE/DI6NzCdODrUG+nMWPI9A8EQDO3c3WbxRLtRPtZaiLPxlwZLyhVs0lytGzKXrTTH4jbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:27:25.872248Z"},"content_sha256":"ff0cc35b35815fd8343338c2726d8da02cc771c3748db8e41475b028d8558f30","schema_version":"1.0","event_id":"sha256:ff0cc35b35815fd8343338c2726d8da02cc771c3748db8e41475b028d8558f30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/bundle.json","state_url":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T06:27:25Z","links":{"resolver":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4","bundle":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/bundle.json","state":"https://pith.science/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2I2GSVDKWWKRF4WG7XJGCHLXN4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+0AFPOqj0AgBrFhYN4kzb7jA5U5QSaOBHtd/h6LKA1ADpLaRvwJ/LWu+ui9z3v0+p61+lY1VLGYwdvOLkiY1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:27:25.876241Z","bundle_sha256":"cda4651addb1af6852489fbd7d07a2345ff56ddd898f68349dcf005e3626cae5"}}