{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WEHN33J2Y2TN7QH2WPUDPMDCN5","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":"33cf6972cede7be62c7316267bbdc9cb558737ae09e4958ed5bae3eafdcf409e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:48:07Z","title_canon_sha256":"58a6948ffe2376b992a29c7b6008f32f399699b4995fdf1429684b8eed147bc0"},"schema_version":"1.0","source":{"id":"2505.24541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24541","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24541v1","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24541","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_12","alias_value":"WEHN33J2Y2TN","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_16","alias_value":"WEHN33J2Y2TN7QH2","created_at":"2026-07-05T11:12:51Z"},{"alias_kind":"pith_short_8","alias_value":"WEHN33J2","created_at":"2026-07-05T11:12:51Z"}],"graph_snapshots":[{"event_id":"sha256:e7b11f42766c3d3b00d19e1e37449664b9d71e9e9b2f2080a272729f7d64f87f","target":"graph","created_at":"2026-07-05T11:12:51Z","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/2505.24541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) require a nuanced interpretation of complex image information, typically leveraging a vision encoder to perceive various visual scenarios. However, relying solely on a single vision encoder to handle diverse task domains proves difficult and inevitably leads to conflicts. Recent work enhances data perception by directly integrating multiple domain-specific vision encoders, yet this structure adds complexity and limits the potential for joint optimization. In this paper, we introduce Mixpert, an efficient mixture-of-vision-experts architecture that inher","authors_text":"Lingxi Xie, Longhui Wei, Qi Tian, Xin He, Xumeng Han","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:48:07Z","title":"Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24541","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":"sha256:9934515b36a26cec3ebd06a2530b27abdc293112e8bfef9425eab550ce83cb4f","target":"record","created_at":"2026-07-05T11:12:51Z","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":"33cf6972cede7be62c7316267bbdc9cb558737ae09e4958ed5bae3eafdcf409e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T12:48:07Z","title_canon_sha256":"58a6948ffe2376b992a29c7b6008f32f399699b4995fdf1429684b8eed147bc0"},"schema_version":"1.0","source":{"id":"2505.24541","kind":"arxiv","version":1}},"canonical_sha256":"b10edded3ac6a6dfc0fab3e837b0626f465c933f0f70846626233750ae89df99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b10edded3ac6a6dfc0fab3e837b0626f465c933f0f70846626233750ae89df99","first_computed_at":"2026-07-05T11:12:51.975900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:51.975900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/9hXAemVTDqgWmQ5Qs/1oqqsKNvqZ3v065E+ppAKBPAbpL7soYcGQbOhhBkCgKUO+8jiEvVjwCA6yVqpROWXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:51.976394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9934515b36a26cec3ebd06a2530b27abdc293112e8bfef9425eab550ce83cb4f","sha256:e7b11f42766c3d3b00d19e1e37449664b9d71e9e9b2f2080a272729f7d64f87f"],"state_sha256":"207e83d71ce18b255d7a5fd86459a6cde1538569886c8b68a89c7d2a53d8e43a"}