{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CQFUYTTCFHDH77MJHTIQ3Z52NF","short_pith_number":"pith:CQFUYTTC","canonical_record":{"source":{"id":"2103.06874","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T18:57:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e7a35d0618cdfb88376e018db2959dc158952ddbe9f68950458ae1370292c20f","abstract_canon_sha256":"de29c9786669d0c44ad02516084dce2c46509360c2db3e3ee9e496e8a5e151bc"},"schema_version":"1.0"},"canonical_sha256":"140b4c4e6229c67ffd893cd10de7ba696628078615b37e00d19d6ae69ea77592","source":{"kind":"arxiv","id":"2103.06874","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06874","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06874v4","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06874","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"CQFUYTTCFHDH","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"CQFUYTTCFHDH77MJ","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"CQFUYTTC","created_at":"2026-07-05T04:24:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CQFUYTTCFHDH77MJHTIQ3Z52NF","target":"record","payload":{"canonical_record":{"source":{"id":"2103.06874","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T18:57:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e7a35d0618cdfb88376e018db2959dc158952ddbe9f68950458ae1370292c20f","abstract_canon_sha256":"de29c9786669d0c44ad02516084dce2c46509360c2db3e3ee9e496e8a5e151bc"},"schema_version":"1.0"},"canonical_sha256":"140b4c4e6229c67ffd893cd10de7ba696628078615b37e00d19d6ae69ea77592","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:21.399800Z","signature_b64":"AFFVPm3POufURTaTMPWnFynX3Iu2FGtTUxPiICA/23PXedqw7QlfWgH731lFaSK3hFzYImXbGyeXM6rykXLQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"140b4c4e6229c67ffd893cd10de7ba696628078615b37e00d19d6ae69ea77592","last_reissued_at":"2026-07-05T04:24:21.399374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:21.399374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.06874","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yE93uBOI8X7yQSmFpWgKkMozfVsNmd/XZ1fRHIu+C0rLgWAt+we59Ll86O21cJ9ZFAwNg8mQVQUNxchJ63+zAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:38:02.407800Z"},"content_sha256":"4c4dcfca2fc76778ec63aef2e8513ee7b5eacecb4b308fd9dd9536c194e0c219","schema_version":"1.0","event_id":"sha256:4c4dcfca2fc76778ec63aef2e8513ee7b5eacecb4b308fd9dd9536c194e0c219"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CQFUYTTCFHDH77MJHTIQ3Z52NF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Garrette, Iulia Turc, John Wieting, Jonathan H. Clark","submitted_at":"2021-03-11T18:57:44Z","abstract_excerpt":"Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step. While recent tokenization approaches based on data-derived subword lexicons are less brittle than manually engineered tokenizers, these techniques are not equally suited to all languages, and the use of any fixed vocabulary may limit a model's ability to adapt. In this paper, we present CANINE, a neural encoder that operates directly on character sequences, without explicit tokenization or vocabulary, and a pre-training strategy that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06874","kind":"arxiv","version":4},"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/2103.06874/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":"2026-07-05T04:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArwsKKmwKeeA/XOcKs+6EE1QIikwXeoc8xBD0E8mq2BVfJhHdWKyRZaD1A4DJF6EX64010hF9fVe4VyBAfSlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:38:02.408381Z"},"content_sha256":"4aba2ac60d795b25d09b15450e082c9eba81278a4bd3933e725bb25408ea9dfd","schema_version":"1.0","event_id":"sha256:4aba2ac60d795b25d09b15450e082c9eba81278a4bd3933e725bb25408ea9dfd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQFUYTTCFHDH77MJHTIQ3Z52NF/bundle.json","state_url":"https://pith.science/pith/CQFUYTTCFHDH77MJHTIQ3Z52NF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQFUYTTCFHDH77MJHTIQ3Z52NF/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":"2026-08-06T02:38:02Z","links":{"resolver":"https://pith.science/pith/CQFUYTTCFHDH77MJHTIQ3Z52NF","bundle":"https://pith.science/pith/CQFUYTTCFHDH77MJHTIQ3Z52NF/bundle.json","state":"https://pith.science/pith/CQFUYTTCFHDH77MJHTIQ3Z52NF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQFUYTTCFHDH77MJHTIQ3Z52NF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CQFUYTTCFHDH77MJHTIQ3Z52NF","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":"de29c9786669d0c44ad02516084dce2c46509360c2db3e3ee9e496e8a5e151bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T18:57:44Z","title_canon_sha256":"e7a35d0618cdfb88376e018db2959dc158952ddbe9f68950458ae1370292c20f"},"schema_version":"1.0","source":{"id":"2103.06874","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06874","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06874v4","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06874","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"CQFUYTTCFHDH","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"CQFUYTTCFHDH77MJ","created_at":"2026-07-05T04:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"CQFUYTTC","created_at":"2026-07-05T04:24:21Z"}],"graph_snapshots":[{"event_id":"sha256:4aba2ac60d795b25d09b15450e082c9eba81278a4bd3933e725bb25408ea9dfd","target":"graph","created_at":"2026-07-05T04:24:21Z","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/2103.06874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step. While recent tokenization approaches based on data-derived subword lexicons are less brittle than manually engineered tokenizers, these techniques are not equally suited to all languages, and the use of any fixed vocabulary may limit a model's ability to adapt. In this paper, we present CANINE, a neural encoder that operates directly on character sequences, without explicit tokenization or vocabulary, and a pre-training strategy that","authors_text":"Dan Garrette, Iulia Turc, John Wieting, Jonathan H. Clark","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T18:57:44Z","title":"CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06874","kind":"arxiv","version":4},"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":"sha256:4c4dcfca2fc76778ec63aef2e8513ee7b5eacecb4b308fd9dd9536c194e0c219","target":"record","created_at":"2026-07-05T04:24:21Z","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":"de29c9786669d0c44ad02516084dce2c46509360c2db3e3ee9e496e8a5e151bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-11T18:57:44Z","title_canon_sha256":"e7a35d0618cdfb88376e018db2959dc158952ddbe9f68950458ae1370292c20f"},"schema_version":"1.0","source":{"id":"2103.06874","kind":"arxiv","version":4}},"canonical_sha256":"140b4c4e6229c67ffd893cd10de7ba696628078615b37e00d19d6ae69ea77592","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"140b4c4e6229c67ffd893cd10de7ba696628078615b37e00d19d6ae69ea77592","first_computed_at":"2026-07-05T04:24:21.399374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:21.399374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AFFVPm3POufURTaTMPWnFynX3Iu2FGtTUxPiICA/23PXedqw7QlfWgH731lFaSK3hFzYImXbGyeXM6rykXLQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:21.399800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.06874","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c4dcfca2fc76778ec63aef2e8513ee7b5eacecb4b308fd9dd9536c194e0c219","sha256:4aba2ac60d795b25d09b15450e082c9eba81278a4bd3933e725bb25408ea9dfd"],"state_sha256":"30ec2bc218ae7e6013b0595ceffe41ee084aca37afc94bc010c48c43f5f01945"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6+YbrmXkRFrT5+Jgxq4jhsxOImWCMt6fi8JK02UhTN3x1Q5tIOKFJlUlr5gbp/LBB78R2UzS8r7DEfW+pWvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:38:02.412897Z","bundle_sha256":"c4c70a39f1881464717975f66d9769b9046a0c105cf26eff553ae9eb73902411"}}