{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BY5CYJQUIOVABNAQGDGHN2FSQ6","short_pith_number":"pith:BY5CYJQU","canonical_record":{"source":{"id":"2403.01289","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T19:01:40Z","cross_cats_sorted":[],"title_canon_sha256":"52cb1bcbb726f4102f221fcc2a303329f7781aac3b067ede0957bd7a96831a0a","abstract_canon_sha256":"5e0fcd5a67e66a89263ecd955a4e1a40e94784f33f22f212135f66a09f09d2b4"},"schema_version":"1.0"},"canonical_sha256":"0e3a2c261443aa00b41030cc76e8b287922204c37198652b10a39dc8e464a23e","source":{"kind":"arxiv","id":"2403.01289","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01289","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01289v2","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01289","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"BY5CYJQUIOVA","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"BY5CYJQUIOVABNAQ","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"BY5CYJQU","created_at":"2026-07-05T08:25:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BY5CYJQUIOVABNAQGDGHN2FSQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01289","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T19:01:40Z","cross_cats_sorted":[],"title_canon_sha256":"52cb1bcbb726f4102f221fcc2a303329f7781aac3b067ede0957bd7a96831a0a","abstract_canon_sha256":"5e0fcd5a67e66a89263ecd955a4e1a40e94784f33f22f212135f66a09f09d2b4"},"schema_version":"1.0"},"canonical_sha256":"0e3a2c261443aa00b41030cc76e8b287922204c37198652b10a39dc8e464a23e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:32.642232Z","signature_b64":"fNQTLN+nBSoY0cEqJPc3Qav564hWk3YMRczut9Lz4OJegcHVSxcTz71vp9J7vmpShNq39TTRHCgN/1HotbwoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e3a2c261443aa00b41030cc76e8b287922204c37198652b10a39dc8e464a23e","last_reissued_at":"2026-07-05T08:25:32.641818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:32.641818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01289","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":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6IqGaIacQ51ykAKXmyc1eh0XU4vd0Hn29OJUVVJwl2uWUhBx//CLyP+fPKPKN0nD4dbUrfo1W4M9PsXlEV8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:06:53.573565Z"},"content_sha256":"42085126d3e99e0e0357c5f3c264c1bd596814904a9d9acd513cfc4cc6c5a610","schema_version":"1.0","event_id":"sha256:42085126d3e99e0e0357c5f3c264c1bd596814904a9d9acd513cfc4cc6c5a610"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BY5CYJQUIOVABNAQGDGHN2FSQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Greed is All You Need: An Evaluation of Tokenizer Inference Methods","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Tanner, Craig W.Schmidt, Omri Uzan, Yuval Pinter","submitted_at":"2024-03-02T19:01:40Z","abstract_excerpt":"While subword tokenizers such as BPE and WordPiece are typically used to build vocabularies for NLP models, the method of decoding text into a sequence of tokens from these vocabularies is often left unspecified, or ill-suited to the method in which they were constructed. We provide a controlled analysis of seven tokenizer inference methods across four different algorithms and three vocabulary sizes, performed on a novel intrinsic evaluation suite we curated for English, combining measures rooted in morphology, cognition, and information theory. We show that for the most commonly used tokenize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01289","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/2403.01289/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":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"edpQ/0wXl8QSrW6pDV4RndkjK3EOtdqX5ppjouoOhtpOJeDZf0Es5wz5sbHaqP3GQQTWH791v/DcgZ3EaNe7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:06:53.573972Z"},"content_sha256":"2253028a6edc090216d36f60d02aa354b578fe7ea2b06320a42d1a16652f4a77","schema_version":"1.0","event_id":"sha256:2253028a6edc090216d36f60d02aa354b578fe7ea2b06320a42d1a16652f4a77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BY5CYJQUIOVABNAQGDGHN2FSQ6/bundle.json","state_url":"https://pith.science/pith/BY5CYJQUIOVABNAQGDGHN2FSQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BY5CYJQUIOVABNAQGDGHN2FSQ6/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":"2026-07-07T05:06:53Z","links":{"resolver":"https://pith.science/pith/BY5CYJQUIOVABNAQGDGHN2FSQ6","bundle":"https://pith.science/pith/BY5CYJQUIOVABNAQGDGHN2FSQ6/bundle.json","state":"https://pith.science/pith/BY5CYJQUIOVABNAQGDGHN2FSQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BY5CYJQUIOVABNAQGDGHN2FSQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BY5CYJQUIOVABNAQGDGHN2FSQ6","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":"5e0fcd5a67e66a89263ecd955a4e1a40e94784f33f22f212135f66a09f09d2b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T19:01:40Z","title_canon_sha256":"52cb1bcbb726f4102f221fcc2a303329f7781aac3b067ede0957bd7a96831a0a"},"schema_version":"1.0","source":{"id":"2403.01289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01289","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01289v2","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01289","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"BY5CYJQUIOVA","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"BY5CYJQUIOVABNAQ","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"BY5CYJQU","created_at":"2026-07-05T08:25:32Z"}],"graph_snapshots":[{"event_id":"sha256:2253028a6edc090216d36f60d02aa354b578fe7ea2b06320a42d1a16652f4a77","target":"graph","created_at":"2026-07-05T08:25:32Z","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/2403.01289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While subword tokenizers such as BPE and WordPiece are typically used to build vocabularies for NLP models, the method of decoding text into a sequence of tokens from these vocabularies is often left unspecified, or ill-suited to the method in which they were constructed. We provide a controlled analysis of seven tokenizer inference methods across four different algorithms and three vocabulary sizes, performed on a novel intrinsic evaluation suite we curated for English, combining measures rooted in morphology, cognition, and information theory. We show that for the most commonly used tokenize","authors_text":"Chris Tanner, Craig W.Schmidt, Omri Uzan, Yuval Pinter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T19:01:40Z","title":"Greed is All You Need: An Evaluation of Tokenizer Inference Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01289","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":"sha256:42085126d3e99e0e0357c5f3c264c1bd596814904a9d9acd513cfc4cc6c5a610","target":"record","created_at":"2026-07-05T08:25:32Z","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":"5e0fcd5a67e66a89263ecd955a4e1a40e94784f33f22f212135f66a09f09d2b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T19:01:40Z","title_canon_sha256":"52cb1bcbb726f4102f221fcc2a303329f7781aac3b067ede0957bd7a96831a0a"},"schema_version":"1.0","source":{"id":"2403.01289","kind":"arxiv","version":2}},"canonical_sha256":"0e3a2c261443aa00b41030cc76e8b287922204c37198652b10a39dc8e464a23e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e3a2c261443aa00b41030cc76e8b287922204c37198652b10a39dc8e464a23e","first_computed_at":"2026-07-05T08:25:32.641818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:32.641818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fNQTLN+nBSoY0cEqJPc3Qav564hWk3YMRczut9Lz4OJegcHVSxcTz71vp9J7vmpShNq39TTRHCgN/1HotbwoAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:32.642232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42085126d3e99e0e0357c5f3c264c1bd596814904a9d9acd513cfc4cc6c5a610","sha256:2253028a6edc090216d36f60d02aa354b578fe7ea2b06320a42d1a16652f4a77"],"state_sha256":"e7f3c848f57767da706000a039dd5e3814860957f9ca53124c1ffab6fd618258"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eICqC7du+ZKdtG8rHrkm+FlN8LXB1v4JIfD+V2tHNwN/jl0wSC7SagGO2QwKFXZ9GYEHxoicyU05Pzu311dvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:06:53.576455Z","bundle_sha256":"095e5950bd459ed52d8d32714560c553734183bcf51df375a50b167431317a66"}}