{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZZC2RY6F3VZIYMW7LX6R3H37GV","short_pith_number":"pith:ZZC2RY6F","canonical_record":{"source":{"id":"2311.04666","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T13:13:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f69a6af2433fc4ba0f6133121d80d8f8906c291c245557eb75286c1f7806dc53","abstract_canon_sha256":"9a4ef5f1c6dde79b11b04518e98644810acefdd363056e3f34b39e2f4b265e15"},"schema_version":"1.0"},"canonical_sha256":"ce45a8e3c5dd728c32df5dfd1d9f7f356c041e90c2765a43a960df5bcbd870e1","source":{"kind":"arxiv","id":"2311.04666","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZZC2RY6F3VZIYMW7LX6R3H37GV","target":"record","payload":{"canonical_record":{"source":{"id":"2311.04666","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-08T13:13:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f69a6af2433fc4ba0f6133121d80d8f8906c291c245557eb75286c1f7806dc53","abstract_canon_sha256":"9a4ef5f1c6dde79b11b04518e98644810acefdd363056e3f34b39e2f4b265e15"},"schema_version":"1.0"},"canonical_sha256":"ce45a8e3c5dd728c32df5dfd1d9f7f356c041e90c2765a43a960df5bcbd870e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:55.244370Z","signature_b64":"N66pllmfbrSf3p4+s46IQdZ9sSB1ZKhmw0XhbJBz6SAmxTTENTuvHoSPWAPLlqUOAlVGXazriSATnlsVwcgSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce45a8e3c5dd728c32df5dfd1d9f7f356c041e90c2765a43a960df5bcbd870e1","last_reissued_at":"2026-07-05T07:31:55.243956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:55.243956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.04666","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:31:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Caf4uFGiXFzAvZEgWdj1WOrkcMIBO9etU6U316rx00aaZYqrnVXu1SHCtHqvfRIljJnQCDvHuR6XYcI2gXaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:44:01.312901Z"},"content_sha256":"97c5f7b1207112f03e8920536a9d9ebae510c1e499cecc5307e4690214a1ff9d","schema_version":"1.0","event_id":"sha256:97c5f7b1207112f03e8920536a9d9ebae510c1e499cecc5307e4690214a1ff9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZZC2RY6F3VZIYMW7LX6R3H37GV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training LLMs using human-like development data corpus","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khushi Bhardwaj, Raj Sanjay Shah, Sashank Varma","submitted_at":"2023-11-08T13:13:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04666","kind":"arxiv","version":4},"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/2311.04666/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":"2026-07-05T07:31:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QZAwRk19SV3aIR9b0rAJIKe9bp8wVc1+9OUeHwwUCTdKweCvI3Mc2AxKelf+yEVvNydovnExqiIPyjtBzqD6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:44:01.313394Z"},"content_sha256":"ac2171f6021f985ccc14121c0c1a2a6b910c4d33798acf87fec602136b75c320","schema_version":"1.0","event_id":"sha256:ac2171f6021f985ccc14121c0c1a2a6b910c4d33798acf87fec602136b75c320"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZZC2RY6F3VZIYMW7LX6R3H37GV/bundle.json","state_url":"https://pith.science/pith/ZZC2RY6F3VZIYMW7LX6R3H37GV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZZC2RY6F3VZIYMW7LX6R3H37GV/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":"2026-08-11T10:44:01Z","links":{"resolver":"https://pith.science/pith/ZZC2RY6F3VZIYMW7LX6R3H37GV","bundle":"https://pith.science/pith/ZZC2RY6F3VZIYMW7LX6R3H37GV/bundle.json","state":"https://pith.science/pith/ZZC2RY6F3VZIYMW7LX6R3H37GV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZZC2RY6F3VZIYMW7LX6R3H37GV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VtlhN3ZF9FqY50efGtned90clnC4zoKVzyixeqbR6R1wP2wC4ag2YoSo1/9dsjl6xm9YVKTEDcLDnyaYmSA2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:44:01.317913Z","bundle_sha256":"11160df6041672847d5f7922721ceffda71de259381337f80199bde939baf8d5"}}