{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SINZQWDONTRBGB6PUSPP55CPXY","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":"7dcee475695c6b0da6ae8f23ae911be360b6d60395058739422c7981d4891bac","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T14:05:41Z","title_canon_sha256":"9346493178ef4a6694ac38dd8a488ce1a4d692db608dc481438c7912680fb8c5"},"schema_version":"1.0","source":{"id":"2606.17952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17952","created_at":"2026-06-19T16:10:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17952v1","created_at":"2026-06-19T16:10:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17952","created_at":"2026-06-19T16:10:44Z"},{"alias_kind":"pith_short_12","alias_value":"SINZQWDONTRB","created_at":"2026-06-19T16:10:44Z"},{"alias_kind":"pith_short_16","alias_value":"SINZQWDONTRBGB6P","created_at":"2026-06-19T16:10:44Z"},{"alias_kind":"pith_short_8","alias_value":"SINZQWDO","created_at":"2026-06-19T16:10:44Z"}],"graph_snapshots":[{"event_id":"sha256:7be14fe9be626abc8b2523572fbf3e04fbeed693bd8e2ff44c5482ce7abd8431","target":"graph","created_at":"2026-06-19T16:10:44Z","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/2606.17952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse Mixture-of-Experts (MoE) architectures enable scaling LLM parameters under a fixed inference budget by activating only a small subset of experts via top-$k$ routing. While this preserves causality and suits autoregressive language models, the discrete top-$k$ operator is not differentiable, forcing a fixed number of active experts per input and resulting in inefficient use of computation. We propose SoftMoE, which replaces discrete routing with a truncated soft top-$k$ LapSum relaxation, allowing gradient-based optimization of expert routing. We further parameterize the mean number of a","authors_text":"Jacek Tabor, {\\L}ukasz Struski, Marcin Kurdziel, Miko{\\l}aj Zasada","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T14:05:41Z","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17952","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":"sha256:233789209b5ef91b40c67fdd21b6b3e6744fd6838e00c159a683f49fdbc0eee7","target":"record","created_at":"2026-06-19T16:10:44Z","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":"7dcee475695c6b0da6ae8f23ae911be360b6d60395058739422c7981d4891bac","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T14:05:41Z","title_canon_sha256":"9346493178ef4a6694ac38dd8a488ce1a4d692db608dc481438c7912680fb8c5"},"schema_version":"1.0","source":{"id":"2606.17952","kind":"arxiv","version":1}},"canonical_sha256":"921b98586e6ce21307cfa49efef44fbe09308583830c1b6080b9cf082e16ab2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"921b98586e6ce21307cfa49efef44fbe09308583830c1b6080b9cf082e16ab2b","first_computed_at":"2026-06-19T16:10:44.377666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:44.377666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysrVTqDhBzzzio+Tfq9WZCJWPl72Oug7pUZGXXj0AuAgeF7Gtw5yd/ZcIGDvtoIe0xfS76S4BnEeqAiPFINWCg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:44.378012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:233789209b5ef91b40c67fdd21b6b3e6744fd6838e00c159a683f49fdbc0eee7","sha256:7be14fe9be626abc8b2523572fbf3e04fbeed693bd8e2ff44c5482ce7abd8431"],"state_sha256":"79458e0e90c8644c6a1da5d272d89f38894c2fb4667365cb95fb5a779bdc738c"}