{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GUZ6GPMARS54F5A5MQQXOB6UG3","short_pith_number":"pith:GUZ6GPMA","canonical_record":{"source":{"id":"2402.18376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T14:52:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a990694e92e9cfd156ba74811cedf498751c13aabb5f0143c07a96a3f0dfd136","abstract_canon_sha256":"18581e685ff17d5e010a8b11a265a72b962d2167490c13a43b1af04e5ca13474"},"schema_version":"1.0"},"canonical_sha256":"3533e33d808cbbc2f41d64217707d436ce8d6d9947c410933ab2f57d19e0ed3d","source":{"kind":"arxiv","id":"2402.18376","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18376","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18376v2","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18376","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"GUZ6GPMARS54","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"GUZ6GPMARS54F5A5","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"GUZ6GPMA","created_at":"2026-07-05T09:16:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GUZ6GPMARS54F5A5MQQXOB6UG3","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T14:52:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a990694e92e9cfd156ba74811cedf498751c13aabb5f0143c07a96a3f0dfd136","abstract_canon_sha256":"18581e685ff17d5e010a8b11a265a72b962d2167490c13a43b1af04e5ca13474"},"schema_version":"1.0"},"canonical_sha256":"3533e33d808cbbc2f41d64217707d436ce8d6d9947c410933ab2f57d19e0ed3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:46.688843Z","signature_b64":"7Oo2RxL5vjNg99A+B+HdtSf+gyCQN6W8R1CdSDZ4CGC1swcBmCBCP7Aaavbq8Un/bEAMivro0SwM21qlQOMkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3533e33d808cbbc2f41d64217707d436ce8d6d9947c410933ab2f57d19e0ed3d","last_reissued_at":"2026-07-05T09:16:46.688343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:46.688343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18376","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":"2026-07-05T09:16:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWTrMqPH8zzNUrENH3cTQnBwTdxWfB9SgO3zcuT9opwMair56l4tct4PGdkPNwmIOROjcXKexPJ1vzrO1uqPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:25:42.090042Z"},"content_sha256":"e9f376d6970a298578c0707d2be66140b13268f61db04270f4fb0d8b0ad2169f","schema_version":"1.0","event_id":"sha256:e9f376d6970a298578c0707d2be66140b13268f61db04270f4fb0d8b0ad2169f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GUZ6GPMARS54F5A5MQQXOB6UG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tokenization Is More Than Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alec Alameddine, Chris Tanner, Craig W. Schmidt, Haoran Zhang, Omri Uzan, Varshini Reddy, Yuval Pinter","submitted_at":"2024-02-28T14:52:15Z","abstract_excerpt":"Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has been suggested that the effectiveness of BPE stems from its ability to condense text into a relatively small number of tokens. We test the hypothesis that fewer tokens lead to better downstream performance by introducing PathPiece, a new tokenizer that segments a document's text into the minimum number of tokens for a given vocabulary. Through extensive exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18376","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/2402.18376/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":"2026-07-05T09:16:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buuA2tE9DACogYe1lMOg95XeVRRIjHh4crEw5ytShHQHMqfSqVo1KEkV218A3GVmOpOAsPHUv//fUTBsp1wPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:25:42.090434Z"},"content_sha256":"38d5626c1954fe2ead748b82cced18ed1f597617f04cdd264d11d87ef125b63a","schema_version":"1.0","event_id":"sha256:38d5626c1954fe2ead748b82cced18ed1f597617f04cdd264d11d87ef125b63a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUZ6GPMARS54F5A5MQQXOB6UG3/bundle.json","state_url":"https://pith.science/pith/GUZ6GPMARS54F5A5MQQXOB6UG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUZ6GPMARS54F5A5MQQXOB6UG3/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":"2026-07-07T10:25:42Z","links":{"resolver":"https://pith.science/pith/GUZ6GPMARS54F5A5MQQXOB6UG3","bundle":"https://pith.science/pith/GUZ6GPMARS54F5A5MQQXOB6UG3/bundle.json","state":"https://pith.science/pith/GUZ6GPMARS54F5A5MQQXOB6UG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUZ6GPMARS54F5A5MQQXOB6UG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GUZ6GPMARS54F5A5MQQXOB6UG3","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":"18581e685ff17d5e010a8b11a265a72b962d2167490c13a43b1af04e5ca13474","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T14:52:15Z","title_canon_sha256":"a990694e92e9cfd156ba74811cedf498751c13aabb5f0143c07a96a3f0dfd136"},"schema_version":"1.0","source":{"id":"2402.18376","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18376","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18376v2","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18376","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"GUZ6GPMARS54","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"GUZ6GPMARS54F5A5","created_at":"2026-07-05T09:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"GUZ6GPMA","created_at":"2026-07-05T09:16:46Z"}],"graph_snapshots":[{"event_id":"sha256:38d5626c1954fe2ead748b82cced18ed1f597617f04cdd264d11d87ef125b63a","target":"graph","created_at":"2026-07-05T09:16:46Z","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/2402.18376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has been suggested that the effectiveness of BPE stems from its ability to condense text into a relatively small number of tokens. We test the hypothesis that fewer tokens lead to better downstream performance by introducing PathPiece, a new tokenizer that segments a document's text into the minimum number of tokens for a given vocabulary. Through extensive exper","authors_text":"Alec Alameddine, Chris Tanner, Craig W. Schmidt, Haoran Zhang, Omri Uzan, Varshini Reddy, Yuval Pinter","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T14:52:15Z","title":"Tokenization Is More Than Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18376","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:e9f376d6970a298578c0707d2be66140b13268f61db04270f4fb0d8b0ad2169f","target":"record","created_at":"2026-07-05T09:16:46Z","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":"18581e685ff17d5e010a8b11a265a72b962d2167490c13a43b1af04e5ca13474","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T14:52:15Z","title_canon_sha256":"a990694e92e9cfd156ba74811cedf498751c13aabb5f0143c07a96a3f0dfd136"},"schema_version":"1.0","source":{"id":"2402.18376","kind":"arxiv","version":2}},"canonical_sha256":"3533e33d808cbbc2f41d64217707d436ce8d6d9947c410933ab2f57d19e0ed3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3533e33d808cbbc2f41d64217707d436ce8d6d9947c410933ab2f57d19e0ed3d","first_computed_at":"2026-07-05T09:16:46.688343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:46.688343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Oo2RxL5vjNg99A+B+HdtSf+gyCQN6W8R1CdSDZ4CGC1swcBmCBCP7Aaavbq8Un/bEAMivro0SwM21qlQOMkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:46.688843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18376","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9f376d6970a298578c0707d2be66140b13268f61db04270f4fb0d8b0ad2169f","sha256:38d5626c1954fe2ead748b82cced18ed1f597617f04cdd264d11d87ef125b63a"],"state_sha256":"91bc02c1bdd9928a04bb695b61a0c849687f55806d619d360fd79f6819718ed1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZWKoztOCaxYCyht2+8yHf5bJwsqRS0hjb5r+fdRqvoSj/EIKqtNbxiBeRSmblJou2GvxQ2YgOWjLYQtBgtaCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:25:42.092371Z","bundle_sha256":"6b31efe6a4480c6f70a4fcba2cae623b243058da24dfce6e868e2cdf2866bf8e"}}