{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZZC2RY6F3VZIYMW7LX6R3H37GV","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":"9a4ef5f1c6dde79b11b04518e98644810acefdd363056e3f34b39e2f4b265e15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T13:13:23Z","title_canon_sha256":"f69a6af2433fc4ba0f6133121d80d8f8906c291c245557eb75286c1f7806dc53"},"schema_version":"1.0","source":{"id":"2311.04666","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04666","created_at":"2026-07-05T07:31:55Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04666v4","created_at":"2026-07-05T07:31:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04666","created_at":"2026-07-05T07:31:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZZC2RY6F3VZI","created_at":"2026-07-05T07:31:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZZC2RY6F3VZIYMW7","created_at":"2026-07-05T07:31:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZZC2RY6F","created_at":"2026-07-05T07:31:55Z"}],"graph_snapshots":[{"event_id":"sha256:ac2171f6021f985ccc14121c0c1a2a6b910c4d33798acf87fec602136b75c320","target":"graph","created_at":"2026-07-05T07:31:55Z","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/2311.04666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Large Language Models (LLMs) have shown success in a diverse set of language inference and understanding tasks. The pre-training stage of LLMs looks at a large corpus of raw textual data. The BabyLM shared task compares LLM pre-training to human language acquisition, where the number of tokens seen by 13-year-old kids is magnitudes smaller than the number of tokens seen by LLMs. In this work, we pre-train and evaluate LLMs on their ability to learn contextual word representations using roughly the same number of tokens as seen by children. We provide a strong set of baselines; with","authors_text":"Khushi Bhardwaj, Raj Sanjay Shah, Sashank Varma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T13:13:23Z","title":"Pre-training LLMs using human-like development data corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04666","kind":"arxiv","version":4},"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":"sha256:97c5f7b1207112f03e8920536a9d9ebae510c1e499cecc5307e4690214a1ff9d","target":"record","created_at":"2026-07-05T07:31:55Z","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":"9a4ef5f1c6dde79b11b04518e98644810acefdd363056e3f34b39e2f4b265e15","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T13:13:23Z","title_canon_sha256":"f69a6af2433fc4ba0f6133121d80d8f8906c291c245557eb75286c1f7806dc53"},"schema_version":"1.0","source":{"id":"2311.04666","kind":"arxiv","version":4}},"canonical_sha256":"ce45a8e3c5dd728c32df5dfd1d9f7f356c041e90c2765a43a960df5bcbd870e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce45a8e3c5dd728c32df5dfd1d9f7f356c041e90c2765a43a960df5bcbd870e1","first_computed_at":"2026-07-05T07:31:55.243956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:55.243956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N66pllmfbrSf3p4+s46IQdZ9sSB1ZKhmw0XhbJBz6SAmxTTENTuvHoSPWAPLlqUOAlVGXazriSATnlsVwcgSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:55.244370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04666","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97c5f7b1207112f03e8920536a9d9ebae510c1e499cecc5307e4690214a1ff9d","sha256:ac2171f6021f985ccc14121c0c1a2a6b910c4d33798acf87fec602136b75c320"],"state_sha256":"68d296e3da8e1e4ab758e960576cf6f3a458f36748ddafe627c3726e03edd7be"}