{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SWLAK2OWF3OCQMXWGTOO2KDKIG","short_pith_number":"pith:SWLAK2OW","canonical_record":{"source":{"id":"2304.14780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T11:40:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9826d61bd3000f3fd8dbc0e99d9a78c686465e24e5db0b972f2b4ed20b686942","abstract_canon_sha256":"9a70083cfda592ed39e2a2e16e5bd868273f3ec395a79cc41e8fd08df33ea177"},"schema_version":"1.0"},"canonical_sha256":"95960569d62edc2832f634dced286a41aed2d1dee052e606d6b0996beb1c5548","source":{"kind":"arxiv","id":"2304.14780","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14780","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14780v1","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14780","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"SWLAK2OWF3OC","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"SWLAK2OWF3OCQMXW","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"SWLAK2OW","created_at":"2026-07-05T06:05:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SWLAK2OWF3OCQMXWGTOO2KDKIG","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T11:40:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9826d61bd3000f3fd8dbc0e99d9a78c686465e24e5db0b972f2b4ed20b686942","abstract_canon_sha256":"9a70083cfda592ed39e2a2e16e5bd868273f3ec395a79cc41e8fd08df33ea177"},"schema_version":"1.0"},"canonical_sha256":"95960569d62edc2832f634dced286a41aed2d1dee052e606d6b0996beb1c5548","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:20.823062Z","signature_b64":"qx8BoQVCMUdv1ls74T1oL0B789c9fmrCmXYXrlFALawzGPzWcL3FFnfL6NS6iQQU54Ho4YwloH/YIZyXq+81DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95960569d62edc2832f634dced286a41aed2d1dee052e606d6b0996beb1c5548","last_reissued_at":"2026-07-05T06:05:20.822716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:20.822716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14780","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EDMdvL3zwlO2yCs/yrlTXrawb7dgSTzl5WwRRjY4H7bRPffjmrz0jSNK0+4uhD08zn5CJ03zcPkF6S+8vdOkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:20:54.343946Z"},"content_sha256":"8761456c28d8adbfac461d402346ba3c01e545f50e40a0d878740ec0c77f6157","schema_version":"1.0","event_id":"sha256:8761456c28d8adbfac461d402346ba3c01e545f50e40a0d878740ec0c77f6157"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SWLAK2OWF3OCQMXWGTOO2KDKIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training and Evaluation of a Multilingual Tokenizer for GPT-SW3","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Felix Stollenwerk","submitted_at":"2023-04-28T11:40:48Z","abstract_excerpt":"This paper provides a detailed discussion of the multilingual tokenizer used for GPT-SW3. It was trained on the Nordic Pile using the SentencePiece library and the BPE algorithm. We outline the tokenizer's most important features and share details on its learned vocabulary. In addition, we systematically analyze the properties and evaluate the performance of the tokenizer with regard to the different languages present in the data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14780","kind":"arxiv","version":1},"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/2304.14780/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":"2026-07-05T06:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kj9c4eZnThnx0Kk1glwriaeQ/zWuuC6iET1d2V7MAjDKYfxpXL5ARJqoGgkN5bmPufTr0F/P+nSYRAO8swe6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:20:54.344716Z"},"content_sha256":"0f2b276ffad0b4f617900abad4ecffeee7aae0f5de7498e167a88ab3037716bb","schema_version":"1.0","event_id":"sha256:0f2b276ffad0b4f617900abad4ecffeee7aae0f5de7498e167a88ab3037716bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWLAK2OWF3OCQMXWGTOO2KDKIG/bundle.json","state_url":"https://pith.science/pith/SWLAK2OWF3OCQMXWGTOO2KDKIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWLAK2OWF3OCQMXWGTOO2KDKIG/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":"2026-08-08T18:20:54Z","links":{"resolver":"https://pith.science/pith/SWLAK2OWF3OCQMXWGTOO2KDKIG","bundle":"https://pith.science/pith/SWLAK2OWF3OCQMXWGTOO2KDKIG/bundle.json","state":"https://pith.science/pith/SWLAK2OWF3OCQMXWGTOO2KDKIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWLAK2OWF3OCQMXWGTOO2KDKIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SWLAK2OWF3OCQMXWGTOO2KDKIG","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":"9a70083cfda592ed39e2a2e16e5bd868273f3ec395a79cc41e8fd08df33ea177","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T11:40:48Z","title_canon_sha256":"9826d61bd3000f3fd8dbc0e99d9a78c686465e24e5db0b972f2b4ed20b686942"},"schema_version":"1.0","source":{"id":"2304.14780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14780","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14780v1","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14780","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"SWLAK2OWF3OC","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"SWLAK2OWF3OCQMXW","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"SWLAK2OW","created_at":"2026-07-05T06:05:20Z"}],"graph_snapshots":[{"event_id":"sha256:0f2b276ffad0b4f617900abad4ecffeee7aae0f5de7498e167a88ab3037716bb","target":"graph","created_at":"2026-07-05T06:05:20Z","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/2304.14780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper provides a detailed discussion of the multilingual tokenizer used for GPT-SW3. It was trained on the Nordic Pile using the SentencePiece library and the BPE algorithm. We outline the tokenizer's most important features and share details on its learned vocabulary. In addition, we systematically analyze the properties and evaluate the performance of the tokenizer with regard to the different languages present in the data.","authors_text":"Felix Stollenwerk","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T11:40:48Z","title":"Training and Evaluation of a Multilingual Tokenizer for GPT-SW3"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14780","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":"sha256:8761456c28d8adbfac461d402346ba3c01e545f50e40a0d878740ec0c77f6157","target":"record","created_at":"2026-07-05T06:05:20Z","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":"9a70083cfda592ed39e2a2e16e5bd868273f3ec395a79cc41e8fd08df33ea177","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T11:40:48Z","title_canon_sha256":"9826d61bd3000f3fd8dbc0e99d9a78c686465e24e5db0b972f2b4ed20b686942"},"schema_version":"1.0","source":{"id":"2304.14780","kind":"arxiv","version":1}},"canonical_sha256":"95960569d62edc2832f634dced286a41aed2d1dee052e606d6b0996beb1c5548","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95960569d62edc2832f634dced286a41aed2d1dee052e606d6b0996beb1c5548","first_computed_at":"2026-07-05T06:05:20.822716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:20.822716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qx8BoQVCMUdv1ls74T1oL0B789c9fmrCmXYXrlFALawzGPzWcL3FFnfL6NS6iQQU54Ho4YwloH/YIZyXq+81DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:20.823062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8761456c28d8adbfac461d402346ba3c01e545f50e40a0d878740ec0c77f6157","sha256:0f2b276ffad0b4f617900abad4ecffeee7aae0f5de7498e167a88ab3037716bb"],"state_sha256":"d1adf6a6c4dfe201ca643ea0f0acee0de16797d72a72964d72b54b6cc8fd3f13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkPmT6YRPhnp1J9TsmykK/ka+wsXF9IcmO/qBJF9nTrC2o7w+q/6HQhTYILd0fgfhOP1bA9dPMtw+F86dLmzBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:20:54.350207Z","bundle_sha256":"f984f34f31419b09dd5951ec945b8250ed3e97dc80ed4da860245895272b6c72"}}