{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHXZTC5B6GDLA7EZQFLBY4LIAE","short_pith_number":"pith:NHXZTC5B","schema_version":"1.0","canonical_sha256":"69ef998ba1f186b07c9981561c7168013763e2564cb30aae14db2348dc92fb18","source":{"kind":"arxiv","id":"2503.10242","version":1},"attestation_state":"computed","paper":{"title":"MinorBench: A hand-built benchmark for content-based risks for children","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabriel Chua, Rachel Shong, Shaun Khoo","submitted_at":"2025-03-13T10:34:43Z","abstract_excerpt":"Large Language Models (LLMs) are rapidly entering children's lives - through parent-driven adoption, schools, and peer networks - yet current AI ethics and safety research do not adequately address content-related risks specific to minors. In this paper, we highlight these gaps with a real-world case study of an LLM-based chatbot deployed in a middle school setting, revealing how students used and sometimes misused the system. Building on these findings, we propose a new taxonomy of content-based risks for minors and introduce MinorBench, an open-source benchmark designed to evaluate LLMs on t"},"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":"2503.10242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-13T10:34:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39f6f65a1b2759a25912fa13fc68a9e60055ee9df5c345a9485edef836594532","abstract_canon_sha256":"ddc10de8fba1af1e229dab0cc533a2d91816ff8aea38a0986ee77e89758ff26f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:41.259157Z","signature_b64":"VWWsv0/3pSGlw6CgFjtE+nCsFIlUDAXGkO0bEuV5pR+2V1YQZbrqsj6Woww99gWXWR10kwfvknWilqkLBdleCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69ef998ba1f186b07c9981561c7168013763e2564cb30aae14db2348dc92fb18","last_reissued_at":"2026-07-05T10:30:41.258258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:41.258258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MinorBench: A hand-built benchmark for content-based risks for children","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabriel Chua, Rachel Shong, Shaun Khoo","submitted_at":"2025-03-13T10:34:43Z","abstract_excerpt":"Large Language Models (LLMs) are rapidly entering children's lives - through parent-driven adoption, schools, and peer networks - yet current AI ethics and safety research do not adequately address content-related risks specific to minors. In this paper, we highlight these gaps with a real-world case study of an LLM-based chatbot deployed in a middle school setting, revealing how students used and sometimes misused the system. Building on these findings, we propose a new taxonomy of content-based risks for minors and introduce MinorBench, an open-source benchmark designed to evaluate LLMs on t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10242","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/2503.10242/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":"2503.10242","created_at":"2026-07-05T10:30:41.258363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10242v1","created_at":"2026-07-05T10:30:41.258363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10242","created_at":"2026-07-05T10:30:41.258363+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHXZTC5B6GDL","created_at":"2026-07-05T10:30:41.258363+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHXZTC5B6GDLA7EZ","created_at":"2026-07-05T10:30:41.258363+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHXZTC5B","created_at":"2026-07-05T10:30:41.258363+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00395","citing_title":"Child Safety in Generative AI: An Expert-Guided and Incident-Grounded Evaluation Framework","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07539","citing_title":"Prompt Governance? On Governing Technologies Governed by Natural Language","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29685","citing_title":"CAREBench: A Child-Safety Risk Benchmark for Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13510","citing_title":"Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE","json":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE.json","graph_json":"https://pith.science/api/pith-number/NHXZTC5B6GDLA7EZQFLBY4LIAE/graph.json","events_json":"https://pith.science/api/pith-number/NHXZTC5B6GDLA7EZQFLBY4LIAE/events.json","paper":"https://pith.science/paper/NHXZTC5B"},"agent_actions":{"view_html":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE","download_json":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE.json","view_paper":"https://pith.science/paper/NHXZTC5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10242&json=true","fetch_graph":"https://pith.science/api/pith-number/NHXZTC5B6GDLA7EZQFLBY4LIAE/graph.json","fetch_events":"https://pith.science/api/pith-number/NHXZTC5B6GDLA7EZQFLBY4LIAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE/action/storage_attestation","attest_author":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE/action/author_attestation","sign_citation":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE/action/citation_signature","submit_replication":"https://pith.science/pith/NHXZTC5B6GDLA7EZQFLBY4LIAE/action/replication_record"}},"created_at":"2026-07-05T10:30:41.258363+00:00","updated_at":"2026-07-05T10:30:41.258363+00:00"}