{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7RDKHMXPEWZIE43VSUQCFWU2U3","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":"b28c3b986dfdf9c9428add5e209f1f67932ba4b475dd290105d55db696d6f3b9","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T09:00:21Z","title_canon_sha256":"68edd1439cfb4acac4535ea14eafa1060444bbf7209cc30b9056bb46790a3b8d"},"schema_version":"1.0","source":{"id":"2312.07987","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07987","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07987v3","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07987","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"pith_short_12","alias_value":"7RDKHMXPEWZI","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"pith_short_16","alias_value":"7RDKHMXPEWZIE43V","created_at":"2026-07-05T09:13:48Z"},{"alias_kind":"pith_short_8","alias_value":"7RDKHMXP","created_at":"2026-07-05T09:13:48Z"}],"graph_snapshots":[{"event_id":"sha256:ba0d57c303e1c4685c47fe68c0120a19561e24717d4867ae39ea8853af3af152","target":"graph","created_at":"2026-07-05T09:13:48Z","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/2312.07987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite many recent works on Mixture of Experts (MoEs) for resource-efficient Transformer language models, existing methods mostly focus on MoEs for feedforward layers. Previous attempts at extending MoE to the self-attention layer fail to match the performance of the parameter-matched baseline. Our novel SwitchHead is an effective MoE method for the attention layer that successfully reduces both the compute and memory requirements, achieving wall-clock speedup, while matching the language modeling performance of the baseline Transformer. Our novel MoE mechanism allows SwitchHead to compute up","authors_text":"J\\\"urgen Schmidhuber, Kazuki Irie, Piotr Pi\\k{e}kos, R\\'obert Csord\\'as","cross_cats":["cs.CL","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T09:00:21Z","title":"SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07987","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:b2f163b833db5f4021d6206df0c663b9df8b000ac9dc11f049f676fd72d09b00","target":"record","created_at":"2026-07-05T09:13:48Z","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":"b28c3b986dfdf9c9428add5e209f1f67932ba4b475dd290105d55db696d6f3b9","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T09:00:21Z","title_canon_sha256":"68edd1439cfb4acac4535ea14eafa1060444bbf7209cc30b9056bb46790a3b8d"},"schema_version":"1.0","source":{"id":"2312.07987","kind":"arxiv","version":3}},"canonical_sha256":"fc46a3b2ef25b2827375952022da9aa6fb1ebc1b02f6e085a5fba2b420e2c34f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc46a3b2ef25b2827375952022da9aa6fb1ebc1b02f6e085a5fba2b420e2c34f","first_computed_at":"2026-07-05T09:13:48.719532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:48.719532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qMqRseLjyx9D7lzvETFDJsDpqV4CKFdcd16G9pe1huSFpmoge9u2WolACSfXwgKPbjwd90xS6l+j1hUKRIbdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:48.719992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07987","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2f163b833db5f4021d6206df0c663b9df8b000ac9dc11f049f676fd72d09b00","sha256:ba0d57c303e1c4685c47fe68c0120a19561e24717d4867ae39ea8853af3af152"],"state_sha256":"78e9fb43abe6f72a945722231a93ca52702d42a2be1a1229ce984fda59f16827"}