{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I5DNKIGPUA2CK2XIKTF46DHYIL","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":"d06b74403d234911d169d359db43733c4852dc87d0152aad00146e8f83835ec5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T08:58:07Z","title_canon_sha256":"0615ff91657f7d992213fbada0cb78067001d68220ccad4a18c3c9fb688611ff"},"schema_version":"1.0","source":{"id":"2401.15969","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15969","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15969v2","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15969","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"I5DNKIGPUA2C","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"I5DNKIGPUA2CK2XI","created_at":"2026-07-05T08:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"I5DNKIGP","created_at":"2026-07-05T08:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:779aa7cdcfb611052726550add8fd4c357ba327a17e8e43df7875af57299a24a","target":"graph","created_at":"2026-07-05T08:09:48Z","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/2401.15969/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) models are a promising way to scale up model capacity without significantly increasing computational cost. A key component of MoEs is the router, which decides which subset of parameters (experts) process which feature embeddings (tokens). In this paper, we present a comprehensive study of routers in MoEs for computer vision tasks. We introduce a unified MoE formulation that subsumes different MoEs with two parametric routing tensors. This formulation covers both sparse MoE, which uses a binary or hard assignment between experts and tokens, and soft MoE, which uses a s","authors_text":"Carlos Riquelme, Joan Puigcerver, Mathieu Blondel, Tianlin Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T08:58:07Z","title":"Routers in Vision Mixture of Experts: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15969","kind":"arxiv","version":2},"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":"sha256:8bd1f81f96055293cfd8094819ef4def3c8bf3a8bc9b5bd5e5b6f6d93f27dde3","target":"record","created_at":"2026-07-05T08:09:48Z","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":"d06b74403d234911d169d359db43733c4852dc87d0152aad00146e8f83835ec5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T08:58:07Z","title_canon_sha256":"0615ff91657f7d992213fbada0cb78067001d68220ccad4a18c3c9fb688611ff"},"schema_version":"1.0","source":{"id":"2401.15969","kind":"arxiv","version":2}},"canonical_sha256":"4746d520cfa034256ae854cbcf0cf842d80cf951b63d14bc1d9f02968280240f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4746d520cfa034256ae854cbcf0cf842d80cf951b63d14bc1d9f02968280240f","first_computed_at":"2026-07-05T08:09:48.095739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:48.095739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ChBHPSaYgUdA91Uc0GH2iwIkMdawra87oW6yDa8Jfbu2M8JW4+ScinlRuZjL+jLt5Qmj6X15D04T+Oa4U4ZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:48.096277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15969","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bd1f81f96055293cfd8094819ef4def3c8bf3a8bc9b5bd5e5b6f6d93f27dde3","sha256:779aa7cdcfb611052726550add8fd4c357ba327a17e8e43df7875af57299a24a"],"state_sha256":"6657b5dbde7ccaa19fca6baa5b41f6fe78aa82e7a68d4001d9e425f632fb0387"}