{"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NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step.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"}