{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N2TLFFQE5SDAJYMQFGY27UDZWZ","short_pith_number":"pith:N2TLFFQE","schema_version":"1.0","canonical_sha256":"6ea6b29604ec8604e19029b1afd079b671838ec20f99111af9c1de96cf86e121","source":{"kind":"arxiv","id":"2212.10420","version":2},"attestation_state":"computed","paper":{"title":"Settling the Reward Hypothesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"cs.AI","authors_text":"David Abel, John D. Martin, Michael Bowling, Will Dabney","submitted_at":"2022-12-20T16:55:33Z","abstract_excerpt":"The reward hypothesis posits that, \"all of what we mean by goals and purposes can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward).\" We aim to fully settle this hypothesis. This will not conclude with a simple affirmation or refutation, but rather specify completely the implicit requirements on goals and purposes under which the hypothesis holds."},"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":"2212.10420","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-12-20T16:55:33Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"736a7145d97174b38f76a91e9e5532654c7015e467455179acaa68f23d891118","abstract_canon_sha256":"7035e38efc3a3dec94a66332dbd2aa265915515e7c9073b71078f8edd7feaea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:21.351468Z","signature_b64":"w/ZzyawcURyqZ4rfEg+vM7pNxplWPma0/eQKRx6ACEB1fs8Sr/VVYzm6U1OYukeiWmyOkUFDA/FEBHGy3CxzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ea6b29604ec8604e19029b1afd079b671838ec20f99111af9c1de96cf86e121","last_reissued_at":"2026-07-05T06:51:21.350844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:21.350844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Settling the Reward Hypothesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"cs.AI","authors_text":"David Abel, John D. Martin, Michael Bowling, Will Dabney","submitted_at":"2022-12-20T16:55:33Z","abstract_excerpt":"The reward hypothesis posits that, \"all of what we mean by goals and purposes can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward).\" We aim to fully settle this hypothesis. This will not conclude with a simple affirmation or refutation, but rather specify completely the implicit requirements on goals and purposes under which the hypothesis holds."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10420","kind":"arxiv","version":2},"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/2212.10420/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":"2212.10420","created_at":"2026-07-05T06:51:21.350918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10420v2","created_at":"2026-07-05T06:51:21.350918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10420","created_at":"2026-07-05T06:51:21.350918+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2TLFFQE5SDA","created_at":"2026-07-05T06:51:21.350918+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2TLFFQE5SDAJYMQ","created_at":"2026-07-05T06:51:21.350918+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2TLFFQE","created_at":"2026-07-05T06:51:21.350918+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/N2TLFFQE5SDAJYMQFGY27UDZWZ","json":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ.json","graph_json":"https://pith.science/api/pith-number/N2TLFFQE5SDAJYMQFGY27UDZWZ/graph.json","events_json":"https://pith.science/api/pith-number/N2TLFFQE5SDAJYMQFGY27UDZWZ/events.json","paper":"https://pith.science/paper/N2TLFFQE"},"agent_actions":{"view_html":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ","download_json":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ.json","view_paper":"https://pith.science/paper/N2TLFFQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10420&json=true","fetch_graph":"https://pith.science/api/pith-number/N2TLFFQE5SDAJYMQFGY27UDZWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/N2TLFFQE5SDAJYMQFGY27UDZWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ/action/storage_attestation","attest_author":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ/action/author_attestation","sign_citation":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ/action/citation_signature","submit_replication":"https://pith.science/pith/N2TLFFQE5SDAJYMQFGY27UDZWZ/action/replication_record"}},"created_at":"2026-07-05T06:51:21.350918+00:00","updated_at":"2026-07-05T06:51:21.350918+00:00"}