{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CYH5EEAM2EMGRCQF2LG3GE3AFX","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":"f223261f50ade1d7ae3ed80d406b127c43fa13b12a433403ee9299a275589f7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-06T17:51:59Z","title_canon_sha256":"92511804ddf7e20c26665451f6ad04f8261626d70e13203bc7f2bbaa0bbbac5a"},"schema_version":"1.0","source":{"id":"2206.02770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02770","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02770v1","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02770","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"CYH5EEAM2EMG","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"CYH5EEAM2EMGRCQF","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"CYH5EEAM","created_at":"2026-07-05T04:29:21Z"}],"graph_snapshots":[{"event_id":"sha256:a2feb0101aca95aee2c1756748b794e4a63a8359338f9f73dade67c1542193bf","target":"graph","created_at":"2026-07-05T04:29:21Z","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/2206.02770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large sparsely-activated models have obtained excellent performance in multiple domains. However, such models are typically trained on a single modality at a time. We present the Language-Image MoE, LIMoE, a sparse mixture of experts model capable of multimodal learning. LIMoE accepts both images and text simultaneously, while being trained using a contrastive loss. MoEs are a natural fit for a multimodal backbone, since expert layers can learn an appropriate partitioning of modalities. However, new challenges arise; in particular, training stability and balanced expert utilization, for which ","authors_text":"Basil Mustafa, Carlos Riquelme, Joan Puigcerver, Neil Houlsby, Rodolphe Jenatton","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-06T17:51:59Z","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02770","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":"sha256:66c21ebcd0222787a30b3f12d1b53f976c558743ecad62efc872f99dc490fb5b","target":"record","created_at":"2026-07-05T04:29:21Z","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":"f223261f50ade1d7ae3ed80d406b127c43fa13b12a433403ee9299a275589f7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-06T17:51:59Z","title_canon_sha256":"92511804ddf7e20c26665451f6ad04f8261626d70e13203bc7f2bbaa0bbbac5a"},"schema_version":"1.0","source":{"id":"2206.02770","kind":"arxiv","version":1}},"canonical_sha256":"160fd2100cd118688a05d2cdb313602ddfb6eb33d2cd8abe3fd644ef99bedf09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"160fd2100cd118688a05d2cdb313602ddfb6eb33d2cd8abe3fd644ef99bedf09","first_computed_at":"2026-07-05T04:29:21.070082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:21.070082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1vyGxrtTmnY9Fyw0z/Nashff8W9LuNfNlMI+VoV8/jsPRftc/yjEpuQASGOrf6mDVvU8mzZPCAAXpRTyGEbdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:21.070435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66c21ebcd0222787a30b3f12d1b53f976c558743ecad62efc872f99dc490fb5b","sha256:a2feb0101aca95aee2c1756748b794e4a63a8359338f9f73dade67c1542193bf"],"state_sha256":"8ef50bfc9cddb69883d70289b74588748e5bdbe7789ff4f3e5c3dc50d0fa34fc"}