{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ILWPYN5GN4UGUOJ6FA3TTRUY5R","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":"b728fa68dc2fd3b78c11bbe608d7e2339d3ce2e19868bd4cf3689707c31f74b7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-20T02:48:01Z","title_canon_sha256":"f800c0480fd2f5b368619f8a7c491318f25115b8e9aece4f3477cf3b141fb199"},"schema_version":"1.0","source":{"id":"2211.10851","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.10851","created_at":"2026-07-05T07:12:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.10851v4","created_at":"2026-07-05T07:12:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10851","created_at":"2026-07-05T07:12:47Z"},{"alias_kind":"pith_short_12","alias_value":"ILWPYN5GN4UG","created_at":"2026-07-05T07:12:47Z"},{"alias_kind":"pith_short_16","alias_value":"ILWPYN5GN4UGUOJ6","created_at":"2026-07-05T07:12:47Z"},{"alias_kind":"pith_short_8","alias_value":"ILWPYN5G","created_at":"2026-07-05T07:12:47Z"}],"graph_snapshots":[{"event_id":"sha256:1fe9fd40bfb44c3610eb944d8c17e9e6008e34b2bcc92415cc37fd2849322673","target":"graph","created_at":"2026-07-05T07:12:47Z","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/2211.10851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning views the maximization of rewards and avoidance of punishments as central to explaining goal-directed behavior. However, over a life, organisms will need to learn about many different aspects of the world's structure: the states of the world and state-vector transition dynamics. The number of combinations of states grows exponentially as an agent incorporates new knowledge, and there is no obvious weighted combination of pre-existing rewards or costs defined for a given combination of states, as such a weighting would need to encode information about good and bad combina","authors_text":"Thomas J. Ringstrom","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-20T02:48:01Z","title":"Reward is not Necessary: How to Create a Modular & Compositional Self-Preserving Agent for Life-Long Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10851","kind":"arxiv","version":4},"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:f0865f9f8c39d2d0fb70606e92365877595ba84e05e497f49ed1f808be35c87a","target":"record","created_at":"2026-07-05T07:12:47Z","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":"b728fa68dc2fd3b78c11bbe608d7e2339d3ce2e19868bd4cf3689707c31f74b7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-20T02:48:01Z","title_canon_sha256":"f800c0480fd2f5b368619f8a7c491318f25115b8e9aece4f3477cf3b141fb199"},"schema_version":"1.0","source":{"id":"2211.10851","kind":"arxiv","version":4}},"canonical_sha256":"42ecfc37a66f286a393e283739c698ec444c8c76045d57eb59ba84fef71f144a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42ecfc37a66f286a393e283739c698ec444c8c76045d57eb59ba84fef71f144a","first_computed_at":"2026-07-05T07:12:47.371708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:47.371708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"slyY2llyf5T4o2TwEvOMtk9a5X6Zm9xtxEX22/5M+DwDB0dF5tYlHFZikCPCrTPLbskauXkuB8YpkndaHUqbDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:47.372253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.10851","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0865f9f8c39d2d0fb70606e92365877595ba84e05e497f49ed1f808be35c87a","sha256:1fe9fd40bfb44c3610eb944d8c17e9e6008e34b2bcc92415cc37fd2849322673"],"state_sha256":"6b9a7c0bb558a442cd10283b70b7f75afa1cf816714ab1f36f6e66238311bea1"}