{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3TOHR7WHJZXXAO5ZVCWHWNLLQ7","short_pith_number":"pith:3TOHR7WH","schema_version":"1.0","canonical_sha256":"dcdc78fec74e6f703bb9a8ac7b356b87df3ce91a36da8f7b9375d596b6abb688","source":{"kind":"arxiv","id":"1902.06766","version":1},"attestation_state":"computed","paper":{"title":"Parenting: Safe Reinforcement Learning from Human Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Christopher Frye, Ilya Feige","submitted_at":"2019-02-18T19:10:18Z","abstract_excerpt":"Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operating in environments where humans understand the existing dangers, human involvement in the learning process has proved a promising approach to AI Safety. Here we demonstrate that a precise framework for learning from human input, loosely inspired by the way humans parent children, solves a broad class of safety problems in this context. We show that our Parenting algorithm solve"},"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":"1902.06766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-18T19:10:18Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ed671a14f21e1124d4093536f3e1ab85c103037519cc2978c5847f61d041c537","abstract_canon_sha256":"9f3f39cdbfd3712b0d7aefcc2e7bdddc300fdd62b743e9d8036fcb1d6a404b21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:40.844042Z","signature_b64":"m23liK4jcJKr3+afcjxLISQvieams0gkpxC6gQJhlUG84MJkKpUrqpOyFjdEnCVuxfvnmL5rGl7B1SP5axmmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcdc78fec74e6f703bb9a8ac7b356b87df3ce91a36da8f7b9375d596b6abb688","last_reissued_at":"2026-05-17T23:53:40.843517Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:40.843517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parenting: Safe Reinforcement Learning from Human Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Christopher Frye, Ilya Feige","submitted_at":"2019-02-18T19:10:18Z","abstract_excerpt":"Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operating in environments where humans understand the existing dangers, human involvement in the learning process has proved a promising approach to AI Safety. Here we demonstrate that a precise framework for learning from human input, loosely inspired by the way humans parent children, solves a broad class of safety problems in this context. We show that our Parenting algorithm solve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06766","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":""},"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":"1902.06766","created_at":"2026-05-17T23:53:40.843591+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.06766v1","created_at":"2026-05-17T23:53:40.843591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06766","created_at":"2026-05-17T23:53:40.843591+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TOHR7WHJZXX","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TOHR7WHJZXXAO5Z","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TOHR7WH","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7","json":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7.json","graph_json":"https://pith.science/api/pith-number/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/graph.json","events_json":"https://pith.science/api/pith-number/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/events.json","paper":"https://pith.science/paper/3TOHR7WH"},"agent_actions":{"view_html":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7","download_json":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7.json","view_paper":"https://pith.science/paper/3TOHR7WH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.06766&json=true","fetch_graph":"https://pith.science/api/pith-number/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/action/storage_attestation","attest_author":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/action/author_attestation","sign_citation":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/action/citation_signature","submit_replication":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/action/replication_record"}},"created_at":"2026-05-17T23:53:40.843591+00:00","updated_at":"2026-05-17T23:53:40.843591+00:00"}