{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3TOHR7WHJZXXAO5ZVCWHWNLLQ7","short_pith_number":"pith:3TOHR7WH","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"},"canonical_sha256":"dcdc78fec74e6f703bb9a8ac7b356b87df3ce91a36da8f7b9375d596b6abb688","source":{"kind":"arxiv","id":"1902.06766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.06766","created_at":"2026-05-17T23:53:40Z"},{"alias_kind":"arxiv_version","alias_value":"1902.06766v1","created_at":"2026-05-17T23:53:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06766","created_at":"2026-05-17T23:53:40Z"},{"alias_kind":"pith_short_12","alias_value":"3TOHR7WHJZXX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3TOHR7WHJZXXAO5Z","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3TOHR7WH","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3TOHR7WHJZXXAO5ZVCWHWNLLQ7","target":"record","payload":{"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"},"canonical_sha256":"dcdc78fec74e6f703bb9a8ac7b356b87df3ce91a36da8f7b9375d596b6abb688","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"},"source_kind":"arxiv","source_id":"1902.06766","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DGqJIqT+pvZfteFubskIii4Sb5YqzfclNnkS4xZgfRm+ISHOYtecnvdppFKjAyeVfnlGzYFbCqAaz8faNiFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:14:42.498017Z"},"content_sha256":"dee791ea3a5dc3adef85009fe2360b76f62dc329ab8c9c2d89fcb4cb699e1fe9","schema_version":"1.0","event_id":"sha256:dee791ea3a5dc3adef85009fe2360b76f62dc329ab8c9c2d89fcb4cb699e1fe9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3TOHR7WHJZXXAO5ZVCWHWNLLQ7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIbNSLgdHSC+5+aMO4tEQ2FDUiLObemS7+TCId+mwp0L97fk5WJEvaelvzjiOzxSGKNesUfD19nuDBRKUv1uBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:14:42.498715Z"},"content_sha256":"46baa81771ead38f31382394b4dc5ea8eb5eb613c8bdb18d03bac79151c340e0","schema_version":"1.0","event_id":"sha256:46baa81771ead38f31382394b4dc5ea8eb5eb613c8bdb18d03bac79151c340e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/bundle.json","state_url":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T21:14:42Z","links":{"resolver":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7","bundle":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/bundle.json","state":"https://pith.science/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TOHR7WHJZXXAO5ZVCWHWNLLQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3TOHR7WHJZXXAO5ZVCWHWNLLQ7","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":"9f3f39cdbfd3712b0d7aefcc2e7bdddc300fdd62b743e9d8036fcb1d6a404b21","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-18T19:10:18Z","title_canon_sha256":"ed671a14f21e1124d4093536f3e1ab85c103037519cc2978c5847f61d041c537"},"schema_version":"1.0","source":{"id":"1902.06766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.06766","created_at":"2026-05-17T23:53:40Z"},{"alias_kind":"arxiv_version","alias_value":"1902.06766v1","created_at":"2026-05-17T23:53:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06766","created_at":"2026-05-17T23:53:40Z"},{"alias_kind":"pith_short_12","alias_value":"3TOHR7WHJZXX","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3TOHR7WHJZXXAO5Z","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3TOHR7WH","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:46baa81771ead38f31382394b4dc5ea8eb5eb613c8bdb18d03bac79151c340e0","target":"graph","created_at":"2026-05-17T23:53:40Z","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"},"paper":{"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","authors_text":"Christopher Frye, Ilya Feige","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-18T19:10:18Z","title":"Parenting: Safe Reinforcement Learning from Human Input"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06766","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:dee791ea3a5dc3adef85009fe2360b76f62dc329ab8c9c2d89fcb4cb699e1fe9","target":"record","created_at":"2026-05-17T23:53:40Z","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":"9f3f39cdbfd3712b0d7aefcc2e7bdddc300fdd62b743e9d8036fcb1d6a404b21","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-18T19:10:18Z","title_canon_sha256":"ed671a14f21e1124d4093536f3e1ab85c103037519cc2978c5847f61d041c537"},"schema_version":"1.0","source":{"id":"1902.06766","kind":"arxiv","version":1}},"canonical_sha256":"dcdc78fec74e6f703bb9a8ac7b356b87df3ce91a36da8f7b9375d596b6abb688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcdc78fec74e6f703bb9a8ac7b356b87df3ce91a36da8f7b9375d596b6abb688","first_computed_at":"2026-05-17T23:53:40.843517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:40.843517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m23liK4jcJKr3+afcjxLISQvieams0gkpxC6gQJhlUG84MJkKpUrqpOyFjdEnCVuxfvnmL5rGl7B1SP5axmmBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:40.844042Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.06766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dee791ea3a5dc3adef85009fe2360b76f62dc329ab8c9c2d89fcb4cb699e1fe9","sha256:46baa81771ead38f31382394b4dc5ea8eb5eb613c8bdb18d03bac79151c340e0"],"state_sha256":"251d784810cc7186df95ed3699399315acc62c57a38b72e6553a21d3dd2676f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nH+V6tUn4sqTrbWxp+HYjo6hKyFj6bIQMHOz0IgeSfBt9LdSj8kuqmHF+X0ccPgI7gDls3wUL8MXyHGyK7lMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:14:42.512993Z","bundle_sha256":"5022a065011f9e251fb604c587ca27d13538f4d7961a716d5970fe2d2da85880"}}