{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPVQK3GMMT7MCK3JG5I2DWMFZV","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":"18673aada542fe8042981e2f8d3d3137630574eb1023d5454e8bc3a96bc07008","cross_cats_sorted":["cs.AI","cs.CY","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T19:35:44Z","title_canon_sha256":"9f5506d9d0ebf4c4284f3d6cfc79d5b211ad771870768d751b2bda2c0212b3c8"},"schema_version":"1.0","source":{"id":"2410.03884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03884","created_at":"2026-07-05T09:16:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03884v1","created_at":"2026-07-05T09:16:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03884","created_at":"2026-07-05T09:16:25Z"},{"alias_kind":"pith_short_12","alias_value":"RPVQK3GMMT7M","created_at":"2026-07-05T09:16:25Z"},{"alias_kind":"pith_short_16","alias_value":"RPVQK3GMMT7MCK3J","created_at":"2026-07-05T09:16:25Z"},{"alias_kind":"pith_short_8","alias_value":"RPVQK3GM","created_at":"2026-07-05T09:16:25Z"}],"graph_snapshots":[{"event_id":"sha256:f0800d467bd00c60f161a11f8fd5e824de0619694d202c5b9fb9117f0cc7ab43","target":"graph","created_at":"2026-07-05T09:16:25Z","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/2410.03884/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies highlight the potential of large language models in creating educational tools for children, yet significant challenges remain in maintaining key child-specific properties such as linguistic nuances, cognitive needs, and safety standards. In this paper, we explore foundational steps toward the development of child-specific language models, emphasizing the necessity of high-quality pre-training data. We introduce a novel user-centric data collection pipeline that involves gathering and validating a corpus specifically written for and sometimes by children. Additionally, we propos","authors_text":"Davood Rafiei, Mir Tafseer Nayeem","cross_cats":["cs.AI","cs.CY","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T19:35:44Z","title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03884","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":"sha256:68dfa4e3e8cafb1e9084871e840c46da184bace16dc727e3936a1cebbc3f0292","target":"record","created_at":"2026-07-05T09:16:25Z","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":"18673aada542fe8042981e2f8d3d3137630574eb1023d5454e8bc3a96bc07008","cross_cats_sorted":["cs.AI","cs.CY","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T19:35:44Z","title_canon_sha256":"9f5506d9d0ebf4c4284f3d6cfc79d5b211ad771870768d751b2bda2c0212b3c8"},"schema_version":"1.0","source":{"id":"2410.03884","kind":"arxiv","version":1}},"canonical_sha256":"8beb056ccc64fec12b693751a1d985cd666e97fc2875357bfbef62514f7d1e56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8beb056ccc64fec12b693751a1d985cd666e97fc2875357bfbef62514f7d1e56","first_computed_at":"2026-07-05T09:16:25.819307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:25.819307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9WYd/CDgn4BNXNJqv26lp+tjlbuGRuo2YveYH69oNhCFpFfQHVxyummbaGS5snDtaOIC1DbyM277D0OAHjNPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:25.819783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68dfa4e3e8cafb1e9084871e840c46da184bace16dc727e3936a1cebbc3f0292","sha256:f0800d467bd00c60f161a11f8fd5e824de0619694d202c5b9fb9117f0cc7ab43"],"state_sha256":"a4992df45ac8c8811c480d82e3e20aac07cf058427b0799c139d3a8a0e7f6220"}