{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CUPLFF23ZVGZOT5DJSD7BBDXPJ","short_pith_number":"pith:CUPLFF23","canonical_record":{"source":{"id":"2106.12672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-23T22:24:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a4bfd605e76046f0caf34469f1cc5d9c3adb1fa5f3d850b5423bfb1d6a885587","abstract_canon_sha256":"dc4c3f8adeb5c1962ab13b367f84f0d48dcc32aad69f0bc01c0291d2a1c4419f"},"schema_version":"1.0"},"canonical_sha256":"151eb2975bcd4d974fa34c87f084777a4792d4eb615b284644a89835480c01a9","source":{"kind":"arxiv","id":"2106.12672","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CUPLFF23ZVGZOT5DJSD7BBDXPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.12672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-23T22:24:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a4bfd605e76046f0caf34469f1cc5d9c3adb1fa5f3d850b5423bfb1d6a885587","abstract_canon_sha256":"dc4c3f8adeb5c1962ab13b367f84f0d48dcc32aad69f0bc01c0291d2a1c4419f"},"schema_version":"1.0"},"canonical_sha256":"151eb2975bcd4d974fa34c87f084777a4792d4eb615b284644a89835480c01a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:22.660939Z","signature_b64":"MHtUorNzOegY7jnhrHYPapS9FMC0Rc5hdq3H0rjWchnia4MInwiquFDoVyyqKtSJtvjeum/n7PjM4YeAv8HmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"151eb2975bcd4d974fa34c87f084777a4792d4eb615b284644a89835480c01a9","last_reissued_at":"2026-07-05T03:59:22.660415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:22.660415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.12672","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8re6ysyPzdIqqHqKlP6Ms5OVSMrYm5qEBCvGsU7SYrjhvpUzOXYDZ/yUGS4eu5ARLWZdjY46xSrPWYxekuJJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:36:53.132049Z"},"content_sha256":"a499519d369877d9b0e63ff31490fdfcda6e045ae66421bd025d8b060388c26e","schema_version":"1.0","event_id":"sha256:a499519d369877d9b0e63ff31490fdfcda6e045ae66421bd025d8b060388c26e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CUPLFF23ZVGZOT5DJSD7BBDXPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cong Yu, Dara Bahri, Donald Metzler, Hyung Won Chung, Jai Gupta, Sebastian Ruder, Simon Baumgartner, Vinh Q. Tran, Yi Tay, Zhen Qin","submitted_at":"2021-06-23T22:24:14Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12672","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.12672/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sohOZ6UtT50E4XUMxvuV7Ig0J0bZSdf4hX0xR139dII5aH2gKgPN6axAddkHdS+fMHEvDseMAy5C86nEahUJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:36:53.132440Z"},"content_sha256":"9b6907b1ab5b408d30f3076dcc93d7815c6a82343305629dbfa1be6a4f148ab1","schema_version":"1.0","event_id":"sha256:9b6907b1ab5b408d30f3076dcc93d7815c6a82343305629dbfa1be6a4f148ab1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUPLFF23ZVGZOT5DJSD7BBDXPJ/bundle.json","state_url":"https://pith.science/pith/CUPLFF23ZVGZOT5DJSD7BBDXPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUPLFF23ZVGZOT5DJSD7BBDXPJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T23:36:53Z","links":{"resolver":"https://pith.science/pith/CUPLFF23ZVGZOT5DJSD7BBDXPJ","bundle":"https://pith.science/pith/CUPLFF23ZVGZOT5DJSD7BBDXPJ/bundle.json","state":"https://pith.science/pith/CUPLFF23ZVGZOT5DJSD7BBDXPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUPLFF23ZVGZOT5DJSD7BBDXPJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUe96badE9wLSpc1CcPuZxQZHEhR8t8eCvfIj87t0/xm8k690KXQoCWfIRbAp5C0LD8+bGCr2YlSmpPeOYNhCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:36:53.134615Z","bundle_sha256":"d677d6281ac7e084946a81246231b6267fd4aafe26ff05f28f2d6815b231d6c1"}}