{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QJIHUDZPTZZZ5MQJZQTYO6JVYN","short_pith_number":"pith:QJIHUDZP","canonical_record":{"source":{"id":"2407.13623","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T15:58:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d13b0a13b1d68fd9fc79e47235386365927c32617b1e7612b6e0ef12ed2b87c6","abstract_canon_sha256":"8a8f9387c04ffbad86475c62efa54aa39308047a097ae9732118565d5a71566e"},"schema_version":"1.0"},"canonical_sha256":"82507a0f2f9e739eb209cc27877935c34333dcec4f554e21abf387371312e13a","source":{"kind":"arxiv","id":"2407.13623","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13623","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13623v3","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13623","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"pith_short_12","alias_value":"QJIHUDZPTZZZ","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"pith_short_16","alias_value":"QJIHUDZPTZZZ5MQJ","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"pith_short_8","alias_value":"QJIHUDZP","created_at":"2026-07-05T09:29:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QJIHUDZPTZZZ5MQJZQTYO6JVYN","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13623","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T15:58:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d13b0a13b1d68fd9fc79e47235386365927c32617b1e7612b6e0ef12ed2b87c6","abstract_canon_sha256":"8a8f9387c04ffbad86475c62efa54aa39308047a097ae9732118565d5a71566e"},"schema_version":"1.0"},"canonical_sha256":"82507a0f2f9e739eb209cc27877935c34333dcec4f554e21abf387371312e13a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:31.761897Z","signature_b64":"gAVNPZqqnxGRyrpJ5ouc5kGrq57xbz9e1Yz6J520dcxyxE6Q56Wbo+AaowfndMePi9jADtYYmuhu/zryC96SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82507a0f2f9e739eb209cc27877935c34333dcec4f554e21abf387371312e13a","last_reissued_at":"2026-07-05T09:29:31.761350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:31.761350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13623","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:29:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8J5mrRRiuWfqolA+IDuVRfE7l30DMgK21XUn6SNZltTMtcZahMSxDaVOpxZnpnDjEvUIZws98It9dNkip6M6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:13:52.430441Z"},"content_sha256":"34841e06cda8f9713ff89c4ef2947f0ff7f493f642c29334d9e1634c299eaf9b","schema_version":"1.0","event_id":"sha256:34841e06cda8f9713ff89c4ef2947f0ff7f493f642c29334d9e1634c299eaf9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QJIHUDZPTZZZ5MQJZQTYO6JVYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chaofan Tao, Longxu Dou, Min Lin, Ngai Wong, Niklas Muennighoff, Ping Luo, Qian Liu, Zhongwei Wan","submitted_at":"2024-07-18T15:58:54Z","abstract_excerpt":"Research on scaling large language models (LLMs) has primarily focused on model parameters and training data size, overlooking the role of vocabulary size. We investigate how vocabulary size impacts LLM scaling laws by training models ranging from 33M to 3B parameters on up to 500B characters with various vocabulary configurations. We propose three complementary approaches for predicting the compute-optimal vocabulary size: IsoFLOPs analysis, derivative estimation, and parametric fit of the loss function. Our approaches converge on the conclusion that the optimal vocabulary size depends on the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13623","kind":"arxiv","version":3},"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/2407.13623/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":"2026-07-05T09:29:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J06fYTVOkPvFK8V4fhzcAahfdt/GZhd3E3KxTRT64imkMTHtI2tEy2pOLy1OqOBMHkUfS7GTz2aHQOV7vhqpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:13:52.430833Z"},"content_sha256":"fa04acd77f15a6fb269f15ba4161073148f0b3925f52819e4079a591d7adbe91","schema_version":"1.0","event_id":"sha256:fa04acd77f15a6fb269f15ba4161073148f0b3925f52819e4079a591d7adbe91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJIHUDZPTZZZ5MQJZQTYO6JVYN/bundle.json","state_url":"https://pith.science/pith/QJIHUDZPTZZZ5MQJZQTYO6JVYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJIHUDZPTZZZ5MQJZQTYO6JVYN/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":"2026-07-07T05:13:52Z","links":{"resolver":"https://pith.science/pith/QJIHUDZPTZZZ5MQJZQTYO6JVYN","bundle":"https://pith.science/pith/QJIHUDZPTZZZ5MQJZQTYO6JVYN/bundle.json","state":"https://pith.science/pith/QJIHUDZPTZZZ5MQJZQTYO6JVYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJIHUDZPTZZZ5MQJZQTYO6JVYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QJIHUDZPTZZZ5MQJZQTYO6JVYN","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":"8a8f9387c04ffbad86475c62efa54aa39308047a097ae9732118565d5a71566e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T15:58:54Z","title_canon_sha256":"d13b0a13b1d68fd9fc79e47235386365927c32617b1e7612b6e0ef12ed2b87c6"},"schema_version":"1.0","source":{"id":"2407.13623","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13623","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13623v3","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13623","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"pith_short_12","alias_value":"QJIHUDZPTZZZ","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"pith_short_16","alias_value":"QJIHUDZPTZZZ5MQJ","created_at":"2026-07-05T09:29:31Z"},{"alias_kind":"pith_short_8","alias_value":"QJIHUDZP","created_at":"2026-07-05T09:29:31Z"}],"graph_snapshots":[{"event_id":"sha256:fa04acd77f15a6fb269f15ba4161073148f0b3925f52819e4079a591d7adbe91","target":"graph","created_at":"2026-07-05T09:29:31Z","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/2407.13623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Research on scaling large language models (LLMs) has primarily focused on model parameters and training data size, overlooking the role of vocabulary size. We investigate how vocabulary size impacts LLM scaling laws by training models ranging from 33M to 3B parameters on up to 500B characters with various vocabulary configurations. We propose three complementary approaches for predicting the compute-optimal vocabulary size: IsoFLOPs analysis, derivative estimation, and parametric fit of the loss function. Our approaches converge on the conclusion that the optimal vocabulary size depends on the","authors_text":"Chaofan Tao, Longxu Dou, Min Lin, Ngai Wong, Niklas Muennighoff, Ping Luo, Qian Liu, Zhongwei Wan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T15:58:54Z","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13623","kind":"arxiv","version":3},"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":"sha256:34841e06cda8f9713ff89c4ef2947f0ff7f493f642c29334d9e1634c299eaf9b","target":"record","created_at":"2026-07-05T09:29:31Z","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":"8a8f9387c04ffbad86475c62efa54aa39308047a097ae9732118565d5a71566e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T15:58:54Z","title_canon_sha256":"d13b0a13b1d68fd9fc79e47235386365927c32617b1e7612b6e0ef12ed2b87c6"},"schema_version":"1.0","source":{"id":"2407.13623","kind":"arxiv","version":3}},"canonical_sha256":"82507a0f2f9e739eb209cc27877935c34333dcec4f554e21abf387371312e13a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82507a0f2f9e739eb209cc27877935c34333dcec4f554e21abf387371312e13a","first_computed_at":"2026-07-05T09:29:31.761350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:31.761350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gAVNPZqqnxGRyrpJ5ouc5kGrq57xbz9e1Yz6J520dcxyxE6Q56Wbo+AaowfndMePi9jADtYYmuhu/zryC96SDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:31.761897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13623","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34841e06cda8f9713ff89c4ef2947f0ff7f493f642c29334d9e1634c299eaf9b","sha256:fa04acd77f15a6fb269f15ba4161073148f0b3925f52819e4079a591d7adbe91"],"state_sha256":"fd375fcfbb1f91b29c7d256c1ccc231d5992074e199beeab501a28956ba92ae4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mQJZn12mLLw/I1rdFhosWJyQjzRRsc8ftI/6d+fB9Zk8vEM6m9HETcEXZ7lnsApVy05vqgTHmTHQSS5VI5ICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:13:52.433343Z","bundle_sha256":"cf9dea7f54d8cc9699d4542de4ec4701954304ffbc2a95fe3807600a08591bc5"}}