{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KVHLEGMKEW5EIFR4ENAQOXYTW2","short_pith_number":"pith:KVHLEGMK","canonical_record":{"source":{"id":"2307.07262","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T10:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"92e8d86a304116d8e688a26c9c85a97ecb50d4bcfc20c8d07dbe51540f9d7748","abstract_canon_sha256":"238dbbee192a4ff023142d6753eff05d262866208d000e3b480bf7434f9244c8"},"schema_version":"1.0"},"canonical_sha256":"554eb2198a25ba44163c2341075f13b69c875ba485b3836541c2467f58b52c9b","source":{"kind":"arxiv","id":"2307.07262","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07262","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07262v2","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07262","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"KVHLEGMKEW5E","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"KVHLEGMKEW5EIFR4","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"KVHLEGMK","created_at":"2026-07-05T07:40:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KVHLEGMKEW5EIFR4ENAQOXYTW2","target":"record","payload":{"canonical_record":{"source":{"id":"2307.07262","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T10:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"92e8d86a304116d8e688a26c9c85a97ecb50d4bcfc20c8d07dbe51540f9d7748","abstract_canon_sha256":"238dbbee192a4ff023142d6753eff05d262866208d000e3b480bf7434f9244c8"},"schema_version":"1.0"},"canonical_sha256":"554eb2198a25ba44163c2341075f13b69c875ba485b3836541c2467f58b52c9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:55.081550Z","signature_b64":"4uXMhtgCqRhMjN0LpYpJELnXGInlJDl+f2DLkDFQP7FTfqlRhkaTuMZZZ45UbG30fTLf7DsO7GZtF2u7qq6+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"554eb2198a25ba44163c2341075f13b69c875ba485b3836541c2467f58b52c9b","last_reissued_at":"2026-07-05T07:40:55.081086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:55.081086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.07262","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":"2026-07-05T07:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/ld1/5Imjw+go55fnI3ErwU0IVUGEIc7oPyDMyKsAYNLLOzHHh8EesppFHbhVD4iiGMlLrhAjcHvY9OjcFFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:39:11.122280Z"},"content_sha256":"df4c707a43dfa0eaf0787a917b85ae29bc7971d71ae31d5d4de7cd2fa15edc50","schema_version":"1.0","event_id":"sha256:df4c707a43dfa0eaf0787a917b85ae29bc7971d71ae31d5d4de7cd2fa15edc50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KVHLEGMKEW5EIFR4ENAQOXYTW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MorphPiece : A Linguistic Tokenizer for Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haris Jabbar","submitted_at":"2023-07-14T10:35:04Z","abstract_excerpt":"Tokenization is a critical part of modern NLP pipelines. However, contemporary tokenizers for Large Language Models are based on statistical analysis of text corpora, without much consideration to the linguistic features. I propose a linguistically motivated tokenization scheme, MorphPiece, which is based partly on morphological segmentation of the underlying text. A GPT-style causal language model trained on this tokenizer (called MorphGPT) shows comparable or superior performance on a variety of supervised and unsupervised NLP tasks, compared to the OpenAI GPT-2 model. Specifically I evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07262","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/2307.07262/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":"2026-07-05T07:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHgRG8XNkpGQIIGL7MresnumnwRiGF63rfWaB7gCh7xXTOFxGEFuWqeROo1J/HnmvmUFdSRorntF53/u3CYNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:39:11.122662Z"},"content_sha256":"23f46f0b084e4fafcc9928cbfd775ef9ae1721b6fc2c2fde84f9d9a6388e635a","schema_version":"1.0","event_id":"sha256:23f46f0b084e4fafcc9928cbfd775ef9ae1721b6fc2c2fde84f9d9a6388e635a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KVHLEGMKEW5EIFR4ENAQOXYTW2/bundle.json","state_url":"https://pith.science/pith/KVHLEGMKEW5EIFR4ENAQOXYTW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KVHLEGMKEW5EIFR4ENAQOXYTW2/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":"2026-07-07T11:39:11Z","links":{"resolver":"https://pith.science/pith/KVHLEGMKEW5EIFR4ENAQOXYTW2","bundle":"https://pith.science/pith/KVHLEGMKEW5EIFR4ENAQOXYTW2/bundle.json","state":"https://pith.science/pith/KVHLEGMKEW5EIFR4ENAQOXYTW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KVHLEGMKEW5EIFR4ENAQOXYTW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KVHLEGMKEW5EIFR4ENAQOXYTW2","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":"238dbbee192a4ff023142d6753eff05d262866208d000e3b480bf7434f9244c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T10:35:04Z","title_canon_sha256":"92e8d86a304116d8e688a26c9c85a97ecb50d4bcfc20c8d07dbe51540f9d7748"},"schema_version":"1.0","source":{"id":"2307.07262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07262","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07262v2","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07262","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"KVHLEGMKEW5E","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"KVHLEGMKEW5EIFR4","created_at":"2026-07-05T07:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"KVHLEGMK","created_at":"2026-07-05T07:40:55Z"}],"graph_snapshots":[{"event_id":"sha256:23f46f0b084e4fafcc9928cbfd775ef9ae1721b6fc2c2fde84f9d9a6388e635a","target":"graph","created_at":"2026-07-05T07:40:55Z","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/2307.07262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization is a critical part of modern NLP pipelines. However, contemporary tokenizers for Large Language Models are based on statistical analysis of text corpora, without much consideration to the linguistic features. I propose a linguistically motivated tokenization scheme, MorphPiece, which is based partly on morphological segmentation of the underlying text. A GPT-style causal language model trained on this tokenizer (called MorphGPT) shows comparable or superior performance on a variety of supervised and unsupervised NLP tasks, compared to the OpenAI GPT-2 model. Specifically I evaluat","authors_text":"Haris Jabbar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T10:35:04Z","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07262","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:df4c707a43dfa0eaf0787a917b85ae29bc7971d71ae31d5d4de7cd2fa15edc50","target":"record","created_at":"2026-07-05T07:40:55Z","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":"238dbbee192a4ff023142d6753eff05d262866208d000e3b480bf7434f9244c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T10:35:04Z","title_canon_sha256":"92e8d86a304116d8e688a26c9c85a97ecb50d4bcfc20c8d07dbe51540f9d7748"},"schema_version":"1.0","source":{"id":"2307.07262","kind":"arxiv","version":2}},"canonical_sha256":"554eb2198a25ba44163c2341075f13b69c875ba485b3836541c2467f58b52c9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"554eb2198a25ba44163c2341075f13b69c875ba485b3836541c2467f58b52c9b","first_computed_at":"2026-07-05T07:40:55.081086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:55.081086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4uXMhtgCqRhMjN0LpYpJELnXGInlJDl+f2DLkDFQP7FTfqlRhkaTuMZZZ45UbG30fTLf7DsO7GZtF2u7qq6+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:55.081550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df4c707a43dfa0eaf0787a917b85ae29bc7971d71ae31d5d4de7cd2fa15edc50","sha256:23f46f0b084e4fafcc9928cbfd775ef9ae1721b6fc2c2fde84f9d9a6388e635a"],"state_sha256":"339abe942f0635913ce311a6b84401ad60cce85c566d50f424d878d9b52748be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eKKAqGrVDiN09qFNBeOSr0NmdJUiUIFDsO4hhJXh9fa1PKYWpEczw0Q9XyhkbfTBxoN3V2LnudeCKE+yzyqeAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:39:11.125826Z","bundle_sha256":"0a05d9c02f3f7f6a9fcbbbc6d150b5b1c05997c17ffbbf94011b30f9835f67a0"}}