{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X5HLR35ABEVRWIQTMZXKSPXDDP","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":"04e718cf8aad4aabbd48a70667aae9954c0f77c131e1d1db36a5d622d3add7e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T00:16:36Z","title_canon_sha256":"88aeb6fa964d069d2bc9f05afa8899599b0d7e80167d2e290de84dda87959f53"},"schema_version":"1.0","source":{"id":"2606.01509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01509","created_at":"2026-06-02T02:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01509v1","created_at":"2026-06-02T02:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01509","created_at":"2026-06-02T02:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"X5HLR35ABEVR","created_at":"2026-06-02T02:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"X5HLR35ABEVRWIQT","created_at":"2026-06-02T02:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"X5HLR35A","created_at":"2026-06-02T02:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:f0d0941e977b88d807b1e08487673c9d7f17021d1fd136cb1a7f55ad27c610a5","target":"graph","created_at":"2026-06-02T02:04:35Z","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/2606.01509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) models scale by activating only a small subset of experts per token. However, training such models remains challenging because top-$k$ routing is discrete and non-differentiable, requiring gradient estimators for expert selection whose design remains a central open problem. We introduce ProbMoE, a probabilistic routing framework that models expert selection as a distribution over cardinality-constrained expert subsets and formulates routing as probabilistic inference in this discrete subset space. We first propose ProbMoE Exact-$k$ routing, which samples $k$-expert sub","authors_text":"Guy Van den Broeck, Heng Zhao, Zhe Zeng, Zilei Shao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T00:16:36Z","title":"ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01509","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":"sha256:8b8b36ad350772e310df42c7bd61b9d908308a5900c50286f33d6868755a5be2","target":"record","created_at":"2026-06-02T02:04:35Z","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":"04e718cf8aad4aabbd48a70667aae9954c0f77c131e1d1db36a5d622d3add7e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T00:16:36Z","title_canon_sha256":"88aeb6fa964d069d2bc9f05afa8899599b0d7e80167d2e290de84dda87959f53"},"schema_version":"1.0","source":{"id":"2606.01509","kind":"arxiv","version":1}},"canonical_sha256":"bf4eb8efa0092b1b2213666ea93ee31bfccd499839a05100a25ddcfc49de06ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf4eb8efa0092b1b2213666ea93ee31bfccd499839a05100a25ddcfc49de06ca","first_computed_at":"2026-06-02T02:04:35.058524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:35.058524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HySxDMq5rg/NkHXpIhBMtZYW5On0lChV69rb06u3n5aC628T3m0sv63ZF7LuO+OHPpKFov7SwE016RXnf9KLAQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:35.059039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b8b36ad350772e310df42c7bd61b9d908308a5900c50286f33d6868755a5be2","sha256:f0d0941e977b88d807b1e08487673c9d7f17021d1fd136cb1a7f55ad27c610a5"],"state_sha256":"7dea9cbaab0872a42ce26efdf83cd88d21bac6458636ce942dc200cd76347d51"}