{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:345KRE4MNBEDTW6ZDKYYBK6O7N","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":"287f98af7c165319c9df1b46d3963b2d55a079e759764579bf392f617008cae2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T23:34:39Z","title_canon_sha256":"b1ce45cd20c6fd2cf159de2803f03861864d4bf64c3e6a077f304f2a2ec54f0c"},"schema_version":"1.0","source":{"id":"2310.11628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11628","created_at":"2026-07-05T07:02:10Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11628v1","created_at":"2026-07-05T07:02:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11628","created_at":"2026-07-05T07:02:10Z"},{"alias_kind":"pith_short_12","alias_value":"345KRE4MNBED","created_at":"2026-07-05T07:02:10Z"},{"alias_kind":"pith_short_16","alias_value":"345KRE4MNBEDTW6Z","created_at":"2026-07-05T07:02:10Z"},{"alias_kind":"pith_short_8","alias_value":"345KRE4M","created_at":"2026-07-05T07:02:10Z"}],"graph_snapshots":[{"event_id":"sha256:0f65a1b28d6bbf784d6f648c254ed76d4c68fc369124133ce15e8a040dd247f2","target":"graph","created_at":"2026-07-05T07:02:10Z","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/2310.11628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the limitations of such a tokenization strategy, particularly for documents not written in English and for representing numbers. On the other extreme, byte/character-level language models are much less restricted but suffer from increased sequence description lengths and a subsequent quadratic expansion in self-attention computation. Recent attempts to compress and l","authors_text":"Avijit Thawani, Jay Pujara, Saurabh Ghanekar, Xiaoyuan Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T23:34:39Z","title":"Learn Your Tokens: Word-Pooled Tokenization for Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11628","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:f53bee39cff5f11137458e613db6cef4c15b5aba46b1cdb54a8338cd60d782f6","target":"record","created_at":"2026-07-05T07:02:10Z","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":"287f98af7c165319c9df1b46d3963b2d55a079e759764579bf392f617008cae2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T23:34:39Z","title_canon_sha256":"b1ce45cd20c6fd2cf159de2803f03861864d4bf64c3e6a077f304f2a2ec54f0c"},"schema_version":"1.0","source":{"id":"2310.11628","kind":"arxiv","version":1}},"canonical_sha256":"df3aa8938c684839dbd91ab180abcefb6c3ff725369678bd957627756d33e682","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df3aa8938c684839dbd91ab180abcefb6c3ff725369678bd957627756d33e682","first_computed_at":"2026-07-05T07:02:10.254584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:10.254584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XYgIlYZzKzerSlhlfNZJ59OrTBGFpak5H+IVIH/2ebxmaQQedNG5E85I5QAfrqPu3J+j4eetvw4R1Gyl5RAlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:10.254991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f53bee39cff5f11137458e613db6cef4c15b5aba46b1cdb54a8338cd60d782f6","sha256:0f65a1b28d6bbf784d6f648c254ed76d4c68fc369124133ce15e8a040dd247f2"],"state_sha256":"bf324de574a4a8c6227e01c4090afb079ab3e3cc0cd275ea8b533ed8656f66a3"}