{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RPVQK3GMMT7MCK3JG5I2DWMFZV","short_pith_number":"pith:RPVQK3GM","schema_version":"1.0","canonical_sha256":"8beb056ccc64fec12b693751a1d985cd666e97fc2875357bfbef62514f7d1e56","source":{"kind":"arxiv","id":"2410.03884","version":1},"attestation_state":"computed","paper":{"title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Mir Tafseer Nayeem","submitted_at":"2024-10-04T19:35:44Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.03884","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T19:35:44Z","cross_cats_sorted":["cs.AI","cs.CY","cs.HC"],"title_canon_sha256":"9f5506d9d0ebf4c4284f3d6cfc79d5b211ad771870768d751b2bda2c0212b3c8","abstract_canon_sha256":"18673aada542fe8042981e2f8d3d3137630574eb1023d5454e8bc3a96bc07008"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:25.819783Z","signature_b64":"9WYd/CDgn4BNXNJqv26lp+tjlbuGRuo2YveYH69oNhCFpFfQHVxyummbaGS5snDtaOIC1DbyM277D0OAHjNPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8beb056ccc64fec12b693751a1d985cd666e97fc2875357bfbef62514f7d1e56","last_reissued_at":"2026-07-05T09:16:25.819307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:25.819307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KidLM: Advancing Language Models for Children -- Early Insights and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Mir Tafseer Nayeem","submitted_at":"2024-10-04T19:35:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03884","kind":"arxiv","version":1},"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/2410.03884/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.03884","created_at":"2026-07-05T09:16:25.819374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03884v1","created_at":"2026-07-05T09:16:25.819374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03884","created_at":"2026-07-05T09:16:25.819374+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPVQK3GMMT7M","created_at":"2026-07-05T09:16:25.819374+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPVQK3GMMT7MCK3J","created_at":"2026-07-05T09:16:25.819374+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPVQK3GM","created_at":"2026-07-05T09:16:25.819374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01671","citing_title":"When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language Models","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16541","citing_title":"BOOKAGENT: Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV","json":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV.json","graph_json":"https://pith.science/api/pith-number/RPVQK3GMMT7MCK3JG5I2DWMFZV/graph.json","events_json":"https://pith.science/api/pith-number/RPVQK3GMMT7MCK3JG5I2DWMFZV/events.json","paper":"https://pith.science/paper/RPVQK3GM"},"agent_actions":{"view_html":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV","download_json":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV.json","view_paper":"https://pith.science/paper/RPVQK3GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03884&json=true","fetch_graph":"https://pith.science/api/pith-number/RPVQK3GMMT7MCK3JG5I2DWMFZV/graph.json","fetch_events":"https://pith.science/api/pith-number/RPVQK3GMMT7MCK3JG5I2DWMFZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV/action/storage_attestation","attest_author":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV/action/author_attestation","sign_citation":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV/action/citation_signature","submit_replication":"https://pith.science/pith/RPVQK3GMMT7MCK3JG5I2DWMFZV/action/replication_record"}},"created_at":"2026-07-05T09:16:25.819374+00:00","updated_at":"2026-07-05T09:16:25.819374+00:00"}