{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J65UMJLJW6JCR44EZADZFS3TBT","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":"f58b703cafc08941a459d26222fe1493be6ffb66ac3f5ff52d2a96d74c89e63d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T03:11:13Z","title_canon_sha256":"c3db159047a6167d7aece206cd99e5c115391b8ffdb022a6705277bf9b6be679"},"schema_version":"1.0","source":{"id":"2211.12677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12677","created_at":"2026-07-05T05:18:53Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12677v1","created_at":"2026-07-05T05:18:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12677","created_at":"2026-07-05T05:18:53Z"},{"alias_kind":"pith_short_12","alias_value":"J65UMJLJW6JC","created_at":"2026-07-05T05:18:53Z"},{"alias_kind":"pith_short_16","alias_value":"J65UMJLJW6JCR44E","created_at":"2026-07-05T05:18:53Z"},{"alias_kind":"pith_short_8","alias_value":"J65UMJLJ","created_at":"2026-07-05T05:18:53Z"}],"graph_snapshots":[{"event_id":"sha256:097ca2090a031bf540bf5a41ba6727fce9f3cf8f8b00210c06e89a5c4321de39","target":"graph","created_at":"2026-07-05T05:18:53Z","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/2211.12677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language models mostly take sub-words as input, a design that balances the trade-off between vocabulary size, number of parameters, and performance. However, sub-word tokenization still has disadvantages like not being robust to noise and difficult to generalize to new languages. Also, the current trend of scaling up models reveals that larger models require larger embeddings but that makes parallelization hard. Previous work on image classification proves splitting raw input into a sequence of chucks is a strong, model-agnostic inductive bias. Based on this observation, we rethink the ","authors_text":"Chu-Tak Lee, Qipeng Guo, Xipeng Qiu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T03:11:13Z","title":"Word-Level Representation From Bytes For Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12677","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:ecb2c97cbe3a61f62c56a4191756f863ad7fc6d4dd5b664dedb6c7e5f5a36744","target":"record","created_at":"2026-07-05T05:18:53Z","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":"f58b703cafc08941a459d26222fe1493be6ffb66ac3f5ff52d2a96d74c89e63d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-23T03:11:13Z","title_canon_sha256":"c3db159047a6167d7aece206cd99e5c115391b8ffdb022a6705277bf9b6be679"},"schema_version":"1.0","source":{"id":"2211.12677","kind":"arxiv","version":1}},"canonical_sha256":"4fbb462569b79228f384c80792cb730cc0ad2b02853dad5fee72f334202f8a75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fbb462569b79228f384c80792cb730cc0ad2b02853dad5fee72f334202f8a75","first_computed_at":"2026-07-05T05:18:53.601774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:53.601774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7AUOqLXj/Q5frxDGTjpKl4Yhj1wqcf4/evVDcwUbY7HAulij5Dof+JJAX9RZ1TVzT5a9smZJ1k+9UJl8b919Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:53.602248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.12677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecb2c97cbe3a61f62c56a4191756f863ad7fc6d4dd5b664dedb6c7e5f5a36744","sha256:097ca2090a031bf540bf5a41ba6727fce9f3cf8f8b00210c06e89a5c4321de39"],"state_sha256":"6d36395c4c113fb2a5c061c80c138f2ccefc3ea713107e0c2acd196bba461a28"}