{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LJEO4HHJLYGYEVZROBPZV7TLMX","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":"c5909f5b7ce1981d10250c807e33fbffedcdc7756ca33dc26c85a28907341181","cross_cats_sorted":["cs.FL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:26:14Z","title_canon_sha256":"34b89823c76c1d2556551c84f06cb8e86c05d142e6878586a2c2acf89661bea5"},"schema_version":"1.0","source":{"id":"2506.07956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07956","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07956v1","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07956","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"LJEO4HHJLYGY","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"LJEO4HHJLYGYEVZR","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"LJEO4HHJ","created_at":"2026-07-05T11:18:36Z"}],"graph_snapshots":[{"event_id":"sha256:defcb3b79fe662047bef17a5e82235bb7af0519e1daae4756823f266dd28a4e4","target":"graph","created_at":"2026-07-05T11:18:36Z","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/2506.07956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language models represent probability distributions over character strings as distributions over (shorter) token strings derived via a deterministic tokenizer, such as byte-pair encoding. While this approach is highly effective at scaling up language models to large corpora, its current incarnations have a concerning property: the model assigns nonzero probability mass to an exponential number of $\\it{noncanonical}$ token encodings of each character string -- these are token strings that decode to valid character strings but are impossible under the deterministic tokenizer (i.e., they w","authors_text":"Benjamin Lebrun, Brian DuSell, Clemente Pasti, Juan Luis Gastaldi, Mario Giulianelli, Ryan Cotterell, Tianyu Liu, Timothy J. O'Donnell, Tim Vieira, Yahya Emara","cross_cats":["cs.FL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:26:14Z","title":"Language Models over Canonical Byte-Pair Encodings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07956","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:ccc12da246ad5ffbdcb814db88406095cbf973d687fa2bea52f9d044e48ca5a2","target":"record","created_at":"2026-07-05T11:18:36Z","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":"c5909f5b7ce1981d10250c807e33fbffedcdc7756ca33dc26c85a28907341181","cross_cats_sorted":["cs.FL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-09T17:26:14Z","title_canon_sha256":"34b89823c76c1d2556551c84f06cb8e86c05d142e6878586a2c2acf89661bea5"},"schema_version":"1.0","source":{"id":"2506.07956","kind":"arxiv","version":1}},"canonical_sha256":"5a48ee1ce95e0d825731705f9afe6b65daae3e6adec477616c2a87de4c8f208d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a48ee1ce95e0d825731705f9afe6b65daae3e6adec477616c2a87de4c8f208d","first_computed_at":"2026-07-05T11:18:36.033126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:36.033126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MyyrDoYyyjW42LI3zq+A6RKKQbEb8k+gXjgQksmB/WaLoRBKevMmqwkpYHMCDNsYlM7sCLmnG6w14FwaZ+VQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:36.033686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccc12da246ad5ffbdcb814db88406095cbf973d687fa2bea52f9d044e48ca5a2","sha256:defcb3b79fe662047bef17a5e82235bb7af0519e1daae4756823f266dd28a4e4"],"state_sha256":"7c3eb28ad42106cdb5dfa5909474d2eee7ec4f2eecd7a93cc84f42a73892bc70"}