{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DNQMSDSWSNAOG5UW4T4UUIWCDY","short_pith_number":"pith:DNQMSDSW","canonical_record":{"source":{"id":"2409.15452","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T18:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"9c8d88ef1bfb573840f879c73b73d1cc8de5305fe7bb0d90eaedf410c3bc8ce7","abstract_canon_sha256":"781e51c60b9ff2143ed17e60315c8ba0b7958e11764b27a1a12ac09fcad7bbf3"},"schema_version":"1.0"},"canonical_sha256":"1b60c90e569340e37696e4f94a22c21e27a6bc319008ad572e164fb652e37597","source":{"kind":"arxiv","id":"2409.15452","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15452","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15452v2","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15452","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"DNQMSDSWSNAO","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"DNQMSDSWSNAOG5UW","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"DNQMSDSW","created_at":"2026-07-05T09:14:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DNQMSDSWSNAOG5UW4T4UUIWCDY","target":"record","payload":{"canonical_record":{"source":{"id":"2409.15452","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T18:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"9c8d88ef1bfb573840f879c73b73d1cc8de5305fe7bb0d90eaedf410c3bc8ce7","abstract_canon_sha256":"781e51c60b9ff2143ed17e60315c8ba0b7958e11764b27a1a12ac09fcad7bbf3"},"schema_version":"1.0"},"canonical_sha256":"1b60c90e569340e37696e4f94a22c21e27a6bc319008ad572e164fb652e37597","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:39.071037Z","signature_b64":"tcBIwbfowO4xnI1ZmQdW+c+BZFLCVwB9nMA6NiDfs6gociCllm9ySjq+YYpebYuRP6hbPzQCHdL179JseAMPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b60c90e569340e37696e4f94a22c21e27a6bc319008ad572e164fb652e37597","last_reissued_at":"2026-07-05T09:14:39.070526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:39.070526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.15452","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGrhTFUSHv4s4NOk1D4e1tftABLliTkLxNQmb4ilDdFQgom0vW1AsqXksKpfUJwZ6g8F2m+PbAXG+NxK3xSoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T15:36:42.525121Z"},"content_sha256":"4e2a4885abf50d16b96d74f2eb63e9d56ca3e6b5aa90190deee7afd92d8ee3bc","schema_version":"1.0","event_id":"sha256:4e2a4885abf50d16b96d74f2eb63e9d56ca3e6b5aa90190deee7afd92d8ee3bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DNQMSDSWSNAOG5UW4T4UUIWCDY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CUTE: Measuring LLMs' Understanding of Their Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Helmut Schmid, Lukas Edman","submitted_at":"2024-09-23T18:27:03Z","abstract_excerpt":"Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. This raises the question: To what extent can LLMs learn orthographic information? To answer this, we propose a new benchmark, CUTE, which features a collection of tasks designed to test the orthographic knowledge of LLMs. We evaluate popular LLMs on CUTE, finding that most of them seem to know the spelling of their tokens, yet fail to use this information effectively to manipulate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15452","kind":"arxiv","version":2},"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/2409.15452/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":"2026-07-05T09:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"maty67iSPk53B/+4adHYJUrsmWmCJjE//riN95Ns11vw4b8UvsI7N2jiNu8/ip0leqQe28ZRMtc74BJZwkklAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T15:36:42.525520Z"},"content_sha256":"334da4fe32813a8a6f7906f2e939ad3156480254060079e62473afe5b2ccf4d1","schema_version":"1.0","event_id":"sha256:334da4fe32813a8a6f7906f2e939ad3156480254060079e62473afe5b2ccf4d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DNQMSDSWSNAOG5UW4T4UUIWCDY/bundle.json","state_url":"https://pith.science/pith/DNQMSDSWSNAOG5UW4T4UUIWCDY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DNQMSDSWSNAOG5UW4T4UUIWCDY/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":"2026-07-08T15:36:42Z","links":{"resolver":"https://pith.science/pith/DNQMSDSWSNAOG5UW4T4UUIWCDY","bundle":"https://pith.science/pith/DNQMSDSWSNAOG5UW4T4UUIWCDY/bundle.json","state":"https://pith.science/pith/DNQMSDSWSNAOG5UW4T4UUIWCDY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DNQMSDSWSNAOG5UW4T4UUIWCDY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DNQMSDSWSNAOG5UW4T4UUIWCDY","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":"781e51c60b9ff2143ed17e60315c8ba0b7958e11764b27a1a12ac09fcad7bbf3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T18:27:03Z","title_canon_sha256":"9c8d88ef1bfb573840f879c73b73d1cc8de5305fe7bb0d90eaedf410c3bc8ce7"},"schema_version":"1.0","source":{"id":"2409.15452","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15452","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15452v2","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15452","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"DNQMSDSWSNAO","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"DNQMSDSWSNAOG5UW","created_at":"2026-07-05T09:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"DNQMSDSW","created_at":"2026-07-05T09:14:39Z"}],"graph_snapshots":[{"event_id":"sha256:334da4fe32813a8a6f7906f2e939ad3156480254060079e62473afe5b2ccf4d1","target":"graph","created_at":"2026-07-05T09:14:39Z","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/2409.15452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direct access to individual characters. This raises the question: To what extent can LLMs learn orthographic information? To answer this, we propose a new benchmark, CUTE, which features a collection of tasks designed to test the orthographic knowledge of LLMs. We evaluate popular LLMs on CUTE, finding that most of them seem to know the spelling of their tokens, yet fail to use this information effectively to manipulate t","authors_text":"Alexander Fraser, Helmut Schmid, Lukas Edman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T18:27:03Z","title":"CUTE: Measuring LLMs' Understanding of Their Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15452","kind":"arxiv","version":2},"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":"sha256:4e2a4885abf50d16b96d74f2eb63e9d56ca3e6b5aa90190deee7afd92d8ee3bc","target":"record","created_at":"2026-07-05T09:14:39Z","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":"781e51c60b9ff2143ed17e60315c8ba0b7958e11764b27a1a12ac09fcad7bbf3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T18:27:03Z","title_canon_sha256":"9c8d88ef1bfb573840f879c73b73d1cc8de5305fe7bb0d90eaedf410c3bc8ce7"},"schema_version":"1.0","source":{"id":"2409.15452","kind":"arxiv","version":2}},"canonical_sha256":"1b60c90e569340e37696e4f94a22c21e27a6bc319008ad572e164fb652e37597","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b60c90e569340e37696e4f94a22c21e27a6bc319008ad572e164fb652e37597","first_computed_at":"2026-07-05T09:14:39.070526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:39.070526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tcBIwbfowO4xnI1ZmQdW+c+BZFLCVwB9nMA6NiDfs6gociCllm9ySjq+YYpebYuRP6hbPzQCHdL179JseAMPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:39.071037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15452","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e2a4885abf50d16b96d74f2eb63e9d56ca3e6b5aa90190deee7afd92d8ee3bc","sha256:334da4fe32813a8a6f7906f2e939ad3156480254060079e62473afe5b2ccf4d1"],"state_sha256":"12abaf67796f98e575ff21e06fd70ed55d0ae4f55765405a3167d8de915d7ddc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XeAwvSU4LdQfmBIfXoeTqiAPktFyFd2bRMXg9MJlBiZ3U69fQoy9ZZLcw1ggejTrIfaQlCDP8loUuz7ZKwwRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T15:36:42.527864Z","bundle_sha256":"cd6cce276bed29521cbd3f44994a3b63d9855b1fa101c47352f651fd64f5941c"}}