{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CUPLFF23ZVGZOT5DJSD7BBDXPJ","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":"dc4c3f8adeb5c1962ab13b367f84f0d48dcc32aad69f0bc01c0291d2a1c4419f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-23T22:24:14Z","title_canon_sha256":"a4bfd605e76046f0caf34469f1cc5d9c3adb1fa5f3d850b5423bfb1d6a885587"},"schema_version":"1.0","source":{"id":"2106.12672","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12672","created_at":"2026-07-05T03:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12672v3","created_at":"2026-07-05T03:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12672","created_at":"2026-07-05T03:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"CUPLFF23ZVGZ","created_at":"2026-07-05T03:59:22Z"},{"alias_kind":"pith_short_16","alias_value":"CUPLFF23ZVGZOT5D","created_at":"2026-07-05T03:59:22Z"},{"alias_kind":"pith_short_8","alias_value":"CUPLFF23","created_at":"2026-07-05T03:59:22Z"}],"graph_snapshots":[{"event_id":"sha256:9b6907b1ab5b408d30f3076dcc93d7815c6a82343305629dbfa1be6a4f148ab1","target":"graph","created_at":"2026-07-05T03:59:22Z","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/2106.12672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art models in natural language processing rely on separate rigid subword tokenization algorithms, which limit their generalization ability and adaptation to new settings. In this paper, we propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model. To this end, we introduce a soft gradient-based subword tokenization module (GBST) that automatically learns latent subword representations from characters in a data-driven fashion. Concretely, GBST enumerates candidate subword blocks and learns to score them in a position-wise fashion using a ","authors_text":"Cong Yu, Dara Bahri, Donald Metzler, Hyung Won Chung, Jai Gupta, Sebastian Ruder, Simon Baumgartner, Vinh Q. Tran, Yi Tay, Zhen Qin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-23T22:24:14Z","title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12672","kind":"arxiv","version":3},"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:a499519d369877d9b0e63ff31490fdfcda6e045ae66421bd025d8b060388c26e","target":"record","created_at":"2026-07-05T03:59:22Z","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":"dc4c3f8adeb5c1962ab13b367f84f0d48dcc32aad69f0bc01c0291d2a1c4419f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-23T22:24:14Z","title_canon_sha256":"a4bfd605e76046f0caf34469f1cc5d9c3adb1fa5f3d850b5423bfb1d6a885587"},"schema_version":"1.0","source":{"id":"2106.12672","kind":"arxiv","version":3}},"canonical_sha256":"151eb2975bcd4d974fa34c87f084777a4792d4eb615b284644a89835480c01a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"151eb2975bcd4d974fa34c87f084777a4792d4eb615b284644a89835480c01a9","first_computed_at":"2026-07-05T03:59:22.660415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:59:22.660415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MHtUorNzOegY7jnhrHYPapS9FMC0Rc5hdq3H0rjWchnia4MInwiquFDoVyyqKtSJtvjeum/n7PjM4YeAv8HmAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:59:22.660939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.12672","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a499519d369877d9b0e63ff31490fdfcda6e045ae66421bd025d8b060388c26e","sha256:9b6907b1ab5b408d30f3076dcc93d7815c6a82343305629dbfa1be6a4f148ab1"],"state_sha256":"3f592cc2dfc359eb0f6ae4ae653fa8538a3723a1ae681e2d947bcdb4cd94642b"}