{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MGKSERVWT4HMPU65YPFJB2US2Y","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":"c298ace201086b001001849c3132fe38cc590ef16fa87d170e6e85aee9c4919f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T00:38:57Z","title_canon_sha256":"adfffbe13bc7d7906e3ee7a9df2564f65a097cbbf75bc5e5dc0ae8d39f6d4bdf"},"schema_version":"1.0","source":{"id":"2310.07096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07096","created_at":"2026-07-05T06:59:40Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07096v1","created_at":"2026-07-05T06:59:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07096","created_at":"2026-07-05T06:59:40Z"},{"alias_kind":"pith_short_12","alias_value":"MGKSERVWT4HM","created_at":"2026-07-05T06:59:40Z"},{"alias_kind":"pith_short_16","alias_value":"MGKSERVWT4HMPU65","created_at":"2026-07-05T06:59:40Z"},{"alias_kind":"pith_short_8","alias_value":"MGKSERVW","created_at":"2026-07-05T06:59:40Z"}],"graph_snapshots":[{"event_id":"sha256:6a9bc90af9a53d7610340321d12aec795345d98b7f7fa07db2285efb360f58be","target":"graph","created_at":"2026-07-05T06:59:40Z","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/2310.07096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Universal Transformer (UT) is a variant of the Transformer that shares parameters across its layers. Empirical evidence shows that UTs have better compositional generalization than Vanilla Transformers (VTs) in formal language tasks. The parameter-sharing also affords it better parameter efficiency than VTs. Despite its many advantages, scaling UT parameters is much more compute and memory intensive than scaling up a VT. This paper proposes the Sparse Universal Transformer (SUT), which leverages Sparse Mixture of Experts (SMoE) and a new stick-breaking-based dynamic halting mechanism to re","authors_text":"Aaron Courville, Chuang Gan, Shawn Tan, Yikang Shen, Zhenfang Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T00:38:57Z","title":"Sparse Universal Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07096","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":"sha256:82594c5ec01eadea00dfd998eb32f05bd698ff3038fe5794b9cfeb2385e04532","target":"record","created_at":"2026-07-05T06:59:40Z","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":"c298ace201086b001001849c3132fe38cc590ef16fa87d170e6e85aee9c4919f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T00:38:57Z","title_canon_sha256":"adfffbe13bc7d7906e3ee7a9df2564f65a097cbbf75bc5e5dc0ae8d39f6d4bdf"},"schema_version":"1.0","source":{"id":"2310.07096","kind":"arxiv","version":1}},"canonical_sha256":"61952246b69f0ec7d3ddc3ca90ea92d605c1a84a9821b335ddf8569db05c3ad2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61952246b69f0ec7d3ddc3ca90ea92d605c1a84a9821b335ddf8569db05c3ad2","first_computed_at":"2026-07-05T06:59:40.431198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:40.431198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eP4mzQYxW4A5BjbXD9fqlAZx8TJO/idVysr63O5koEXDMDAAFkWI81vSg3ggsH6z9CrWo1RbMytttyZefdOJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:40.431608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82594c5ec01eadea00dfd998eb32f05bd698ff3038fe5794b9cfeb2385e04532","sha256:6a9bc90af9a53d7610340321d12aec795345d98b7f7fa07db2285efb360f58be"],"state_sha256":"04f0c4c59227fd86c3d2a0b6ec56a7fa068edd40d556e2f77bc4fd3f7f0fd752"}