{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ACOHDHWEAOJLFFBYXHPNNS3NDE","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":"244e384bc2171ebd2e9dae3bae885e15ac0f77e2edaaeb743e4fac84a9d66f90","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-09T18:44:38Z","title_canon_sha256":"223c492c6cb0e0e1af30c360e52c22884c14521a00716ba00c60a0ca9271f543"},"schema_version":"1.0","source":{"id":"1808.04444","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04444","created_at":"2026-05-17T23:58:47Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04444v2","created_at":"2026-05-17T23:58:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04444","created_at":"2026-05-17T23:58:47Z"},{"alias_kind":"pith_short_12","alias_value":"ACOHDHWEAOJL","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ACOHDHWEAOJLFFBY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ACOHDHWE","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:dde801555079b918f7aa655b3d3a8c8559aca0ded2b4778e1d4183b36ad7a3cd","target":"graph","created_at":"2026-05-17T23:58:47Z","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"},"paper":{"abstract_excerpt":"LSTMs and other RNN variants have shown strong performance on character-level language modeling. These models are typically trained using truncated backpropagation through time, and it is common to assume that their success stems from their ability to remember long-term contexts. In this paper, we show that a deep (64-layer) transformer model with fixed context outperforms RNN variants by a large margin, achieving state of the art on two popular benchmarks: 1.13 bits per character on text8 and 1.06 on enwik8. To get good results at this depth, we show that it is important to add auxiliary loss","authors_text":"Dokook Choe, Llion Jones, Mandy Guo, Noah Constant, Rami Al-Rfou","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-09T18:44:38Z","title":"Character-Level Language Modeling with Deeper Self-Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04444","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:f6a32d709455c8e79b5481744a66867aa9ee451e7975809f9e699a9194db72cf","target":"record","created_at":"2026-05-17T23:58:47Z","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":"244e384bc2171ebd2e9dae3bae885e15ac0f77e2edaaeb743e4fac84a9d66f90","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-09T18:44:38Z","title_canon_sha256":"223c492c6cb0e0e1af30c360e52c22884c14521a00716ba00c60a0ca9271f543"},"schema_version":"1.0","source":{"id":"1808.04444","kind":"arxiv","version":2}},"canonical_sha256":"009c719ec40392b29438b9ded6cb6d193b20f988aa96f7412afcf856f6a58a57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"009c719ec40392b29438b9ded6cb6d193b20f988aa96f7412afcf856f6a58a57","first_computed_at":"2026-05-17T23:58:47.692179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:47.692179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eXy+wFFtM07v/jyDCdkJ+8lFRTzOIWEf4MTU0PfM8VhLwW5CxAVhZXV5Oq4jARYJlDKkGhdj1+5NFS5DuuP5AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:47.692660Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.04444","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6a32d709455c8e79b5481744a66867aa9ee451e7975809f9e699a9194db72cf","sha256:dde801555079b918f7aa655b3d3a8c8559aca0ded2b4778e1d4183b36ad7a3cd"],"state_sha256":"6057fa692296bdb25992c42b4f2ed8e610150cc185fdcca4ee91d7619f9b8a31"}