{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SKSXPQ6CLW3PCLIOCX7IC25SWK","short_pith_number":"pith:SKSXPQ6C","canonical_record":{"source":{"id":"2311.09580","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T05:31:21Z","cross_cats_sorted":[],"title_canon_sha256":"02bf3d2734b7cbde47924a587f43835f29deb3e582cdbaf405da37a60bf4b8d7","abstract_canon_sha256":"a6f70cac6bb6bdd937e26aa4b50aa3c276c70f53a85f7e0e4d490a08277e9607"},"schema_version":"1.0"},"canonical_sha256":"92a577c3c25db6f12d0e15fe816bb2b2b59a4f8b213e207eeae7da5f46626076","source":{"kind":"arxiv","id":"2311.09580","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09580","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09580v3","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09580","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"SKSXPQ6CLW3P","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"SKSXPQ6CLW3PCLIO","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"SKSXPQ6C","created_at":"2026-07-05T09:11:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SKSXPQ6CLW3PCLIOCX7IC25SWK","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09580","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T05:31:21Z","cross_cats_sorted":[],"title_canon_sha256":"02bf3d2734b7cbde47924a587f43835f29deb3e582cdbaf405da37a60bf4b8d7","abstract_canon_sha256":"a6f70cac6bb6bdd937e26aa4b50aa3c276c70f53a85f7e0e4d490a08277e9607"},"schema_version":"1.0"},"canonical_sha256":"92a577c3c25db6f12d0e15fe816bb2b2b59a4f8b213e207eeae7da5f46626076","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:45.810502Z","signature_b64":"RIeOUiJ27JYkvkoXpcVaxPakq69M9I88wWKulceKm34rab3MrjYSXMxpzCe7eOmFF7heWQOLG1SfLdDtsjvXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92a577c3c25db6f12d0e15fe816bb2b2b59a4f8b213e207eeae7da5f46626076","last_reissued_at":"2026-07-05T09:11:45.809982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:45.809982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09580","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:11:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+O+80PXpVKGfDKQWu1VzuNFvzHDss+t8ap0s7Wn31zbs3lBcNWkMZtP00Pi9j4pUkX5ls0y+ckjVnBsqjmXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:22.662993Z"},"content_sha256":"a7a1b6844ac444a437349d73924a457bd266e9cdba59b53e81f03d49b7f866f0","schema_version":"1.0","event_id":"sha256:a7a1b6844ac444a437349d73924a457bd266e9cdba59b53e81f03d49b7f866f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SKSXPQ6CLW3PCLIOCX7IC25SWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haofei Yu, Lawrence Jang, Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Zhengyang Qi","submitted_at":"2023-11-16T05:31:21Z","abstract_excerpt":"Advances in multimodal models have greatly improved how interactions relevant to various tasks are modeled. Today's multimodal models mainly focus on the correspondence between images and text, using this for tasks like image-text matching. However, this covers only a subset of real-world interactions. Novel interactions, such as sarcasm expressed through opposing spoken words and gestures or humor expressed through utterances and tone of voice, remain challenging. In this paper, we introduce an approach to enhance multimodal models, which we call Multimodal Mixtures of Experts (MMoE). The key"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09580","kind":"arxiv","version":3},"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/2311.09580/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":"2026-07-05T09:11:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5acuAaHl6OenqPdWpWDhhqSxafRbVT0M6mfutixB3Ieiu22g5ZK8y6O+zhQIzdteAX1YxaT4J377eZIprihzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:22.663573Z"},"content_sha256":"51524ee49ab247678468f09c1be6a601702ad5c766e208220d18bf5d59d281ee","schema_version":"1.0","event_id":"sha256:51524ee49ab247678468f09c1be6a601702ad5c766e208220d18bf5d59d281ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKSXPQ6CLW3PCLIOCX7IC25SWK/bundle.json","state_url":"https://pith.science/pith/SKSXPQ6CLW3PCLIOCX7IC25SWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKSXPQ6CLW3PCLIOCX7IC25SWK/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":"2026-08-08T12:12:22Z","links":{"resolver":"https://pith.science/pith/SKSXPQ6CLW3PCLIOCX7IC25SWK","bundle":"https://pith.science/pith/SKSXPQ6CLW3PCLIOCX7IC25SWK/bundle.json","state":"https://pith.science/pith/SKSXPQ6CLW3PCLIOCX7IC25SWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKSXPQ6CLW3PCLIOCX7IC25SWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SKSXPQ6CLW3PCLIOCX7IC25SWK","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":"a6f70cac6bb6bdd937e26aa4b50aa3c276c70f53a85f7e0e4d490a08277e9607","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T05:31:21Z","title_canon_sha256":"02bf3d2734b7cbde47924a587f43835f29deb3e582cdbaf405da37a60bf4b8d7"},"schema_version":"1.0","source":{"id":"2311.09580","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09580","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09580v3","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09580","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"SKSXPQ6CLW3P","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"SKSXPQ6CLW3PCLIO","created_at":"2026-07-05T09:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"SKSXPQ6C","created_at":"2026-07-05T09:11:45Z"}],"graph_snapshots":[{"event_id":"sha256:51524ee49ab247678468f09c1be6a601702ad5c766e208220d18bf5d59d281ee","target":"graph","created_at":"2026-07-05T09:11:45Z","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/2311.09580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in multimodal models have greatly improved how interactions relevant to various tasks are modeled. Today's multimodal models mainly focus on the correspondence between images and text, using this for tasks like image-text matching. However, this covers only a subset of real-world interactions. Novel interactions, such as sarcasm expressed through opposing spoken words and gestures or humor expressed through utterances and tone of voice, remain challenging. In this paper, we introduce an approach to enhance multimodal models, which we call Multimodal Mixtures of Experts (MMoE). The key","authors_text":"Haofei Yu, Lawrence Jang, Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Zhengyang Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T05:31:21Z","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09580","kind":"arxiv","version":3},"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:a7a1b6844ac444a437349d73924a457bd266e9cdba59b53e81f03d49b7f866f0","target":"record","created_at":"2026-07-05T09:11:45Z","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":"a6f70cac6bb6bdd937e26aa4b50aa3c276c70f53a85f7e0e4d490a08277e9607","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T05:31:21Z","title_canon_sha256":"02bf3d2734b7cbde47924a587f43835f29deb3e582cdbaf405da37a60bf4b8d7"},"schema_version":"1.0","source":{"id":"2311.09580","kind":"arxiv","version":3}},"canonical_sha256":"92a577c3c25db6f12d0e15fe816bb2b2b59a4f8b213e207eeae7da5f46626076","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92a577c3c25db6f12d0e15fe816bb2b2b59a4f8b213e207eeae7da5f46626076","first_computed_at":"2026-07-05T09:11:45.809982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:45.809982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RIeOUiJ27JYkvkoXpcVaxPakq69M9I88wWKulceKm34rab3MrjYSXMxpzCe7eOmFF7heWQOLG1SfLdDtsjvXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:45.810502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09580","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7a1b6844ac444a437349d73924a457bd266e9cdba59b53e81f03d49b7f866f0","sha256:51524ee49ab247678468f09c1be6a601702ad5c766e208220d18bf5d59d281ee"],"state_sha256":"7c9b0f3a6c99b5f8f133694fe2d7b0ecc18cea90d9415b7c28e4f08d4b041715"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CbKTpe/uDR0wmRl7aOYbZra+iKyv0/hk5T/xQn2+82IM8c8UDoRQH+rEf1yEzqStVwPv8x+Ndm+gXglhy7wADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:12:22.667703Z","bundle_sha256":"50dacf713e948b720f64d921a3a41c9a7f17069041782a860b55496e73745476"}}