{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HXMHXSWPBPE7PFX4VSNHRW3ISE","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":"72bb734c4932d3d5cb4d289761cb7451016d2a4805329d9dfa90c79e7f38d64e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T16:53:59Z","title_canon_sha256":"5b89242964b904fbfdb0a63a34e5f97776ec455d5f6a461afb866177522e4b56"},"schema_version":"1.0","source":{"id":"1908.10322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.10322","created_at":"2026-07-05T00:00:10Z"},{"alias_kind":"arxiv_version","alias_value":"1908.10322v1","created_at":"2026-07-05T00:00:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10322","created_at":"2026-07-05T00:00:10Z"},{"alias_kind":"pith_short_12","alias_value":"HXMHXSWPBPE7","created_at":"2026-07-05T00:00:10Z"},{"alias_kind":"pith_short_16","alias_value":"HXMHXSWPBPE7PFX4","created_at":"2026-07-05T00:00:10Z"},{"alias_kind":"pith_short_8","alias_value":"HXMHXSWP","created_at":"2026-07-05T00:00:10Z"}],"graph_snapshots":[{"event_id":"sha256:da87282228cfd1e50f66558be1616f578b494ec4d7461da6f8f63e44abe346e2","target":"graph","created_at":"2026-07-05T00:00:10Z","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/1908.10322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Purely character-based language models (LMs) have been lagging in quality on large scale datasets, and current state-of-the-art LMs rely on word tokenization. It has been assumed that injecting the prior knowledge of a tokenizer into the model is essential to achieving competitive results. In this paper, we show that contrary to this conventional wisdom, tokenizer-free LMs with sufficient capacity can achieve competitive performance on a large scale dataset. We train a vanilla transformer network with 40 self-attention layers on the One Billion Word (lm1b) benchmark and achieve a new state of ","authors_text":"Dokook Choe, Heeyoung Lee, Mandy Guo, Noah Constant, Rami Al-Rfou","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T16:53:59Z","title":"Bridging the Gap for Tokenizer-Free Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10322","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:b55e1f25429ef3a262934f3fd02984f9d46dd0a871f97d51c4487391c6fce0c9","target":"record","created_at":"2026-07-05T00:00:10Z","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":"72bb734c4932d3d5cb4d289761cb7451016d2a4805329d9dfa90c79e7f38d64e","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T16:53:59Z","title_canon_sha256":"5b89242964b904fbfdb0a63a34e5f97776ec455d5f6a461afb866177522e4b56"},"schema_version":"1.0","source":{"id":"1908.10322","kind":"arxiv","version":1}},"canonical_sha256":"3dd87bcacf0bc9f796fcac9a78db689133345832ee33b7a281ba06e1ac8623ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dd87bcacf0bc9f796fcac9a78db689133345832ee33b7a281ba06e1ac8623ea","first_computed_at":"2026-07-05T00:00:10.972877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:00:10.972877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hNbsl9WDkFLXIUnbbwbf2x6YKK0lXZaKwQ3Wncy+9erEihxVKUM3H5ef0vcAViFns5wuTsl1yRqjhJbQn5scCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:00:10.973279Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.10322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b55e1f25429ef3a262934f3fd02984f9d46dd0a871f97d51c4487391c6fce0c9","sha256:da87282228cfd1e50f66558be1616f578b494ec4d7461da6f8f63e44abe346e2"],"state_sha256":"93ed76b3efd2db85da397641b587a0dbb73292f6e16815ccc37be86934de881a"}