{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CLOBH25A3V4ZRMQ4TXJ5MU4ZX7","short_pith_number":"pith:CLOBH25A","canonical_record":{"source":{"id":"2407.12709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:31:38Z","cross_cats_sorted":[],"title_canon_sha256":"96f49edfa4b17d4f5c0d675823058deca8efeb57220e4dbc6ffcd52e6fbeff46","abstract_canon_sha256":"134eb13b1afdb3ca7f61fea58a0e787228b8f4c65f7755d39fbccff470ba2003"},"schema_version":"1.0"},"canonical_sha256":"12dc13eba0dd7998b21c9dd3d65399bfca0be1a55e0ac8bb455a49d724c974f3","source":{"kind":"arxiv","id":"2407.12709","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12709","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12709v1","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12709","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"CLOBH25A3V4Z","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_16","alias_value":"CLOBH25A3V4ZRMQ4","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_8","alias_value":"CLOBH25A","created_at":"2026-07-05T08:45:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CLOBH25A3V4ZRMQ4TXJ5MU4ZX7","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:31:38Z","cross_cats_sorted":[],"title_canon_sha256":"96f49edfa4b17d4f5c0d675823058deca8efeb57220e4dbc6ffcd52e6fbeff46","abstract_canon_sha256":"134eb13b1afdb3ca7f61fea58a0e787228b8f4c65f7755d39fbccff470ba2003"},"schema_version":"1.0"},"canonical_sha256":"12dc13eba0dd7998b21c9dd3d65399bfca0be1a55e0ac8bb455a49d724c974f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:08.605272Z","signature_b64":"v3wcUbP4WvL5en0Q+IViE55rDmck0CET+dG7dP1bDl1zTUiYULd9ZiYDSBnvrVH0MdqqfQtnjn3KP899dKtwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12dc13eba0dd7998b21c9dd3d65399bfca0be1a55e0ac8bb455a49d724c974f3","last_reissued_at":"2026-07-05T08:45:08.604923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:08.604923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12709","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":"2026-07-05T08:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kk9v9VtpxF2Iv9MCh5EvEThlbgGo4LmU91Cv8VIBp5LzytOpTAvb5LrTKueecKm+s0VInkCaRy4LtNNhtH0jAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:29:15.497973Z"},"content_sha256":"89323b39e1104e740f23670068c2de19f5e3651177e306b6364774df7467ccad","schema_version":"1.0","event_id":"sha256:89323b39e1104e740f23670068c2de19f5e3651177e306b6364774df7467ccad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CLOBH25A3V4ZRMQ4TXJ5MU4ZX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongwei Chen, Leyang Shen, Liqiang Nie, Rui Shao, Weili Guan","submitted_at":"2024-07-17T16:31:38Z","abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be attributed to task interference. In this paper, we propose a mixture of multimodal experts (MoME) to mitigate task interference and obtain a generalist MLLM. Our MoME is composed of two key components, a mixture of vision experts (MoVE) and a mixture of language experts (MoLE). MoVE can adaptively modulate the features transformed from various vision encoders, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12709","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/2407.12709/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":"2026-07-05T08:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7q+90BfjzZ0SznzL8r6Qx3v1s4bnJ3OXvR9XvdUB3OzYz2mjoZt4EPWkGe+sfTqZ8cujwLlt95aQSYLDXVuDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:29:15.498867Z"},"content_sha256":"d83e9216b119ef6f73cd1b0bc7c34fa298b2d5f5ebe3134dd438f6e9044de8ef","schema_version":"1.0","event_id":"sha256:d83e9216b119ef6f73cd1b0bc7c34fa298b2d5f5ebe3134dd438f6e9044de8ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLOBH25A3V4ZRMQ4TXJ5MU4ZX7/bundle.json","state_url":"https://pith.science/pith/CLOBH25A3V4ZRMQ4TXJ5MU4ZX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLOBH25A3V4ZRMQ4TXJ5MU4ZX7/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":"2026-08-07T18:29:15Z","links":{"resolver":"https://pith.science/pith/CLOBH25A3V4ZRMQ4TXJ5MU4ZX7","bundle":"https://pith.science/pith/CLOBH25A3V4ZRMQ4TXJ5MU4ZX7/bundle.json","state":"https://pith.science/pith/CLOBH25A3V4ZRMQ4TXJ5MU4ZX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLOBH25A3V4ZRMQ4TXJ5MU4ZX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CLOBH25A3V4ZRMQ4TXJ5MU4ZX7","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":"134eb13b1afdb3ca7f61fea58a0e787228b8f4c65f7755d39fbccff470ba2003","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:31:38Z","title_canon_sha256":"96f49edfa4b17d4f5c0d675823058deca8efeb57220e4dbc6ffcd52e6fbeff46"},"schema_version":"1.0","source":{"id":"2407.12709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12709","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12709v1","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12709","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"CLOBH25A3V4Z","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_16","alias_value":"CLOBH25A3V4ZRMQ4","created_at":"2026-07-05T08:45:08Z"},{"alias_kind":"pith_short_8","alias_value":"CLOBH25A","created_at":"2026-07-05T08:45:08Z"}],"graph_snapshots":[{"event_id":"sha256:d83e9216b119ef6f73cd1b0bc7c34fa298b2d5f5ebe3134dd438f6e9044de8ef","target":"graph","created_at":"2026-07-05T08:45:08Z","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/2407.12709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be attributed to task interference. In this paper, we propose a mixture of multimodal experts (MoME) to mitigate task interference and obtain a generalist MLLM. Our MoME is composed of two key components, a mixture of vision experts (MoVE) and a mixture of language experts (MoLE). MoVE can adaptively modulate the features transformed from various vision encoders, an","authors_text":"Gongwei Chen, Leyang Shen, Liqiang Nie, Rui Shao, Weili Guan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:31:38Z","title":"MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12709","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":"sha256:89323b39e1104e740f23670068c2de19f5e3651177e306b6364774df7467ccad","target":"record","created_at":"2026-07-05T08:45:08Z","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":"134eb13b1afdb3ca7f61fea58a0e787228b8f4c65f7755d39fbccff470ba2003","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:31:38Z","title_canon_sha256":"96f49edfa4b17d4f5c0d675823058deca8efeb57220e4dbc6ffcd52e6fbeff46"},"schema_version":"1.0","source":{"id":"2407.12709","kind":"arxiv","version":1}},"canonical_sha256":"12dc13eba0dd7998b21c9dd3d65399bfca0be1a55e0ac8bb455a49d724c974f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12dc13eba0dd7998b21c9dd3d65399bfca0be1a55e0ac8bb455a49d724c974f3","first_computed_at":"2026-07-05T08:45:08.604923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:08.604923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v3wcUbP4WvL5en0Q+IViE55rDmck0CET+dG7dP1bDl1zTUiYULd9ZiYDSBnvrVH0MdqqfQtnjn3KP899dKtwBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:08.605272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89323b39e1104e740f23670068c2de19f5e3651177e306b6364774df7467ccad","sha256:d83e9216b119ef6f73cd1b0bc7c34fa298b2d5f5ebe3134dd438f6e9044de8ef"],"state_sha256":"5f3fe2d311fc728464dc341f633e8bc144292cd835e9e042727251c76ba62be5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+iTd0tFfMMPvu+yciVlr+n5Zcxfp67gfSeBO31oqAeNGQbk7LIDef9FGJ9EnyTSI27T4lXfB315YD1C+CUMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:29:15.504905Z","bundle_sha256":"e1b4dccb00922ee811d041dbb0f2fdaa4ab997ec70258aa048b4d8f18ec6de1c"}}