{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ILWPYN5GN4UGUOJ6FA3TTRUY5R","short_pith_number":"pith:ILWPYN5G","schema_version":"1.0","canonical_sha256":"42ecfc37a66f286a393e283739c698ec444c8c76045d57eb59ba84fef71f144a","source":{"kind":"arxiv","id":"2211.10851","version":4},"attestation_state":"computed","paper":{"title":"Reward is not Necessary: How to Create a Modular & Compositional Self-Preserving Agent for Life-Long Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Thomas J. Ringstrom","submitted_at":"2022-11-20T02:48:01Z","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"},"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":"2211.10851","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-20T02:48:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f800c0480fd2f5b368619f8a7c491318f25115b8e9aece4f3477cf3b141fb199","abstract_canon_sha256":"b728fa68dc2fd3b78c11bbe608d7e2339d3ce2e19868bd4cf3689707c31f74b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:47.372253Z","signature_b64":"slyY2llyf5T4o2TwEvOMtk9a5X6Zm9xtxEX22/5M+DwDB0dF5tYlHFZikCPCrTPLbskauXkuB8YpkndaHUqbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42ecfc37a66f286a393e283739c698ec444c8c76045d57eb59ba84fef71f144a","last_reissued_at":"2026-07-05T07:12:47.371708Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:47.371708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward is not Necessary: How to Create a Modular & Compositional Self-Preserving Agent for Life-Long Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Thomas J. Ringstrom","submitted_at":"2022-11-20T02:48:01Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10851","kind":"arxiv","version":4},"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/2211.10851/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":"2211.10851","created_at":"2026-07-05T07:12:47.371764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.10851v4","created_at":"2026-07-05T07:12:47.371764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10851","created_at":"2026-07-05T07:12:47.371764+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILWPYN5GN4UG","created_at":"2026-07-05T07:12:47.371764+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILWPYN5GN4UGUOJ6","created_at":"2026-07-05T07:12:47.371764+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILWPYN5G","created_at":"2026-07-05T07:12:47.371764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22255","citing_title":"Agent-centric learning: from external reward maximization to internal knowledge curation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R","json":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R.json","graph_json":"https://pith.science/api/pith-number/ILWPYN5GN4UGUOJ6FA3TTRUY5R/graph.json","events_json":"https://pith.science/api/pith-number/ILWPYN5GN4UGUOJ6FA3TTRUY5R/events.json","paper":"https://pith.science/paper/ILWPYN5G"},"agent_actions":{"view_html":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R","download_json":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R.json","view_paper":"https://pith.science/paper/ILWPYN5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.10851&json=true","fetch_graph":"https://pith.science/api/pith-number/ILWPYN5GN4UGUOJ6FA3TTRUY5R/graph.json","fetch_events":"https://pith.science/api/pith-number/ILWPYN5GN4UGUOJ6FA3TTRUY5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R/action/storage_attestation","attest_author":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R/action/author_attestation","sign_citation":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R/action/citation_signature","submit_replication":"https://pith.science/pith/ILWPYN5GN4UGUOJ6FA3TTRUY5R/action/replication_record"}},"created_at":"2026-07-05T07:12:47.371764+00:00","updated_at":"2026-07-05T07:12:47.371764+00:00"}