{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I2JE3Z4J3DJZF7OQNXAAH64SVL","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":"4ba268bd679049ed6788790b4e62591d07ecb87b4c539edce3de1f26da156103","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T13:30:48Z","title_canon_sha256":"6e0f1bfcac05122a8abb90aef8308ee0c08252a72bd333e94723ca7eea15ce5b"},"schema_version":"1.0","source":{"id":"2406.12907","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12907","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12907v3","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12907","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_12","alias_value":"I2JE3Z4J3DJZ","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_16","alias_value":"I2JE3Z4J3DJZF7OQ","created_at":"2026-07-05T09:38:27Z"},{"alias_kind":"pith_short_8","alias_value":"I2JE3Z4J","created_at":"2026-07-05T09:38:27Z"}],"graph_snapshots":[{"event_id":"sha256:15640da89a33e1d1a5fe5b257e9fb31f1f3e1c95aabb32bcbf4a391901fb27e2","target":"graph","created_at":"2026-07-05T09:38:27Z","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/2406.12907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Kaplan et al. [2020] (`Kaplan') and Hoffmann et al. [2022] (`Chinchilla') studied the scaling behavior of transformers trained on next-token language prediction. These studies produced different estimates for how the number of parameters ($N$) and training tokens ($D$) should be set to achieve the lowest possible loss for a given compute budget ($C$). Kaplan: $N_\\text{optimal} \\propto C^{0.73}$, Chinchilla: $N_\\text{optimal} \\propto C^{0.50}$. This paper finds that much of this discrepancy can be attributed to Kaplan counting non-embedding rather than total parameters, combined with their anal","authors_text":"Jinyeop Song, Tim Pearce","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T13:30:48Z","title":"Reconciling Kaplan and Chinchilla Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12907","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":"sha256:3030ae71d08c249cbd3d5dc5fd04cb1e4389f15b1c61bb92d3f3196f438cbcd4","target":"record","created_at":"2026-07-05T09:38:27Z","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":"4ba268bd679049ed6788790b4e62591d07ecb87b4c539edce3de1f26da156103","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T13:30:48Z","title_canon_sha256":"6e0f1bfcac05122a8abb90aef8308ee0c08252a72bd333e94723ca7eea15ce5b"},"schema_version":"1.0","source":{"id":"2406.12907","kind":"arxiv","version":3}},"canonical_sha256":"46924de789d8d392fdd06dc003fb92aad520e1cccbdc459d0c507f8cb6be2c95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46924de789d8d392fdd06dc003fb92aad520e1cccbdc459d0c507f8cb6be2c95","first_computed_at":"2026-07-05T09:38:27.412717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:27.412717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vi00Ks9VC+yjQxDuNuygYe6yY+Sq2HyI73cbyovkUkIfV5iBBSJ1JZF9ZZpD6WaXyF2qLGj8FhOXtHq5UzGtBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:27.413198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12907","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3030ae71d08c249cbd3d5dc5fd04cb1e4389f15b1c61bb92d3f3196f438cbcd4","sha256:15640da89a33e1d1a5fe5b257e9fb31f1f3e1c95aabb32bcbf4a391901fb27e2"],"state_sha256":"0d85dddfdba58d14c9c285e65777379f16ea2a6ba94715384dd8448660d75c37"}