{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RTYZIH6IISHER4XLSF3AKYTDFM","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":"162d4e38f4d5fba583afe4315d44cef05942f8992eb14412b8fc7c5c9faa414d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T10:52:52Z","title_canon_sha256":"afcacf980f51b2f017b66c2824012afd7252c204099dc7eec47ac2c052b32ab2"},"schema_version":"1.0","source":{"id":"2308.01684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.01684","created_at":"2026-07-05T07:04:00Z"},{"alias_kind":"arxiv_version","alias_value":"2308.01684v2","created_at":"2026-07-05T07:04:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01684","created_at":"2026-07-05T07:04:00Z"},{"alias_kind":"pith_short_12","alias_value":"RTYZIH6IISHE","created_at":"2026-07-05T07:04:00Z"},{"alias_kind":"pith_short_16","alias_value":"RTYZIH6IISHER4XL","created_at":"2026-07-05T07:04:00Z"},{"alias_kind":"pith_short_8","alias_value":"RTYZIH6I","created_at":"2026-07-05T07:04:00Z"}],"graph_snapshots":[{"event_id":"sha256:38f7ba7eb919d8e65a7f8f5b5b33df4228c500c29efec808008449e8a72e5588","target":"graph","created_at":"2026-07-05T07:04:00Z","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/2308.01684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable performance on a variety of natural language understanding (NLU) tasks, primarily due to their in-context learning ability. This ability could be applied to building babylike models, i.e. models at small scales, improving training efficiency. In this paper, we propose a \"CoThought\" pipeline, which efficiently trains smaller \"baby\" language models (BabyLMs) by leveraging the Chain of Thought prompting of LLMs. Our pipeline restructures a dataset of less than 100M in size using GPT-3.5-turbo, transforming it into task-oriented, human-readable t","authors_text":"Bolei Ma, David R\\\"ugamer, Ercong Nie, Han Yang, Zheyu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T10:52:52Z","title":"Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01684","kind":"arxiv","version":2},"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:bc46c9ff31c020a216e682bbb14d37a889a07c2ae0cb53f6cd2e8d96c4d04f40","target":"record","created_at":"2026-07-05T07:04:00Z","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":"162d4e38f4d5fba583afe4315d44cef05942f8992eb14412b8fc7c5c9faa414d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T10:52:52Z","title_canon_sha256":"afcacf980f51b2f017b66c2824012afd7252c204099dc7eec47ac2c052b32ab2"},"schema_version":"1.0","source":{"id":"2308.01684","kind":"arxiv","version":2}},"canonical_sha256":"8cf1941fc8448e48f2eb91760562632b095188f6ec1b4951db6c2af8ab02a459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cf1941fc8448e48f2eb91760562632b095188f6ec1b4951db6c2af8ab02a459","first_computed_at":"2026-07-05T07:04:00.289250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:00.289250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"acnsydcqIzmrMajs/HR4VI3rmcMHH1fGAUDNHBxj6YVfz21ILonw1NDwdKj7f86wreWfCmhSThDTEgB7KHe/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:00.289704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.01684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc46c9ff31c020a216e682bbb14d37a889a07c2ae0cb53f6cd2e8d96c4d04f40","sha256:38f7ba7eb919d8e65a7f8f5b5b33df4228c500c29efec808008449e8a72e5588"],"state_sha256":"fe96b43f6f8516f3863cd5fdfadb8f239c78f6b72f0ded5fe1e55a7cff8d296f"}