{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DO6SBW3FO4MN67YNZA526QCYOY","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":"952c8895ceb889f12183ca7bc6a19b308615505fe318e19164422e7a91d11166","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T01:05:28Z","title_canon_sha256":"e8d593ff3f8a6605fca249a464dddef02ef6c35e8760389365fcaf77f24f04e2"},"schema_version":"1.0","source":{"id":"2411.06646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.06646","created_at":"2026-07-05T09:33:49Z"},{"alias_kind":"arxiv_version","alias_value":"2411.06646v1","created_at":"2026-07-05T09:33:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06646","created_at":"2026-07-05T09:33:49Z"},{"alias_kind":"pith_short_12","alias_value":"DO6SBW3FO4MN","created_at":"2026-07-05T09:33:49Z"},{"alias_kind":"pith_short_16","alias_value":"DO6SBW3FO4MN67YN","created_at":"2026-07-05T09:33:49Z"},{"alias_kind":"pith_short_8","alias_value":"DO6SBW3F","created_at":"2026-07-05T09:33:49Z"}],"graph_snapshots":[{"event_id":"sha256:692d89904ab4165096d08e86e2c1a45c213fce20e505ee79afd33a91d8c5aee4","target":"graph","created_at":"2026-07-05T09:33:49Z","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/2411.06646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When training deep neural networks, a model's generalization error is often observed to follow a power scaling law dependent both on the model size and the data size. Perhaps the best known example of such scaling laws are for transformer-based large language models, where networks with billions of parameters are trained on trillions of tokens of text. Yet, despite sustained widespread interest, a rigorous understanding of why transformer scaling laws exist is still missing. To answer this question, we establish novel statistical estimation and mathematical approximation theories for transform","authors_text":"Alex Havrilla, Wenjing Liao","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T01:05:28Z","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06646","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:f253df894f72bf72486137883aa5c05694d62eed6993c953e9f2d1b5523e122a","target":"record","created_at":"2026-07-05T09:33:49Z","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":"952c8895ceb889f12183ca7bc6a19b308615505fe318e19164422e7a91d11166","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T01:05:28Z","title_canon_sha256":"e8d593ff3f8a6605fca249a464dddef02ef6c35e8760389365fcaf77f24f04e2"},"schema_version":"1.0","source":{"id":"2411.06646","kind":"arxiv","version":1}},"canonical_sha256":"1bbd20db657718df7f0dc83baf4058762ff45cfceb829837adb6a1ab95b04b14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bbd20db657718df7f0dc83baf4058762ff45cfceb829837adb6a1ab95b04b14","first_computed_at":"2026-07-05T09:33:49.327327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:49.327327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vyc8FOCuQHpfPHHjioN+cXIbhyMTGWvqLhFGV6stF0BxT3XlCM/p3IdGv0l5/oxENjyPxIQlARPgu6rpFZeKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:49.327759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.06646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f253df894f72bf72486137883aa5c05694d62eed6993c953e9f2d1b5523e122a","sha256:692d89904ab4165096d08e86e2c1a45c213fce20e505ee79afd33a91d8c5aee4"],"state_sha256":"1ceaf2b17f050113a469362138a7a0c0fa75ade6e0373d1834c33cb282bb091b"}