{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CUPCHA3FHFKIZQXAIJPEYKKS3D","short_pith_number":"pith:CUPCHA3F","schema_version":"1.0","canonical_sha256":"151e23836539548cc2e0425e4c2952d8e348966457534591294c7ef9c2adb261","source":{"kind":"arxiv","id":"2011.01010","version":2},"attestation_state":"computed","paper":{"title":"Causal Campbell-Goodhart's law and Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","econ.GN","q-fin.EC"],"primary_cat":"cs.LG","authors_text":"Hal Ashton","submitted_at":"2020-11-02T14:42:20Z","abstract_excerpt":"Campbell-Goodhart's law relates to the causal inference error whereby decision-making agents aim to influence variables which are correlated to their goal objective but do not reliably cause it. This is a well known error in Economics and Political Science but not widely labelled in Artificial Intelligence research. Through a simple example, we show how off-the-shelf deep Reinforcement Learning (RL) algorithms are not necessarily immune to this cognitive error. The off-policy learning method is tricked, whilst the on-policy method is not. The practical implication is that naive application of "},"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":"2011.01010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-02T14:42:20Z","cross_cats_sorted":["cs.AI","econ.GN","q-fin.EC"],"title_canon_sha256":"21050c58558ae0841c9b1e47c67395de1505a7a77d4e105beb6bc0cff54e4007","abstract_canon_sha256":"960d73c4346b79c09e2e2832db337089a66e26718090f3b9281f0b65e5b66dad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:15.891590Z","signature_b64":"or/FSdn44yC+dtJKSK6ZXcILwlmt3cgReb8tt6klOsR+yqG4UL3o4ZGnqygfKRwsy2a8VCIqvZyjU8f0D/syBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"151e23836539548cc2e0425e4c2952d8e348966457534591294c7ef9c2adb261","last_reissued_at":"2026-07-05T02:16:15.891081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:15.891081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Campbell-Goodhart's law and Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","econ.GN","q-fin.EC"],"primary_cat":"cs.LG","authors_text":"Hal Ashton","submitted_at":"2020-11-02T14:42:20Z","abstract_excerpt":"Campbell-Goodhart's law relates to the causal inference error whereby decision-making agents aim to influence variables which are correlated to their goal objective but do not reliably cause it. This is a well known error in Economics and Political Science but not widely labelled in Artificial Intelligence research. Through a simple example, we show how off-the-shelf deep Reinforcement Learning (RL) algorithms are not necessarily immune to this cognitive error. The off-policy learning method is tricked, whilst the on-policy method is not. The practical implication is that naive application of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01010","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/2011.01010/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":"2011.01010","created_at":"2026-07-05T02:16:15.891141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01010v2","created_at":"2026-07-05T02:16:15.891141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01010","created_at":"2026-07-05T02:16:15.891141+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUPCHA3FHFKI","created_at":"2026-07-05T02:16:15.891141+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUPCHA3FHFKIZQXA","created_at":"2026-07-05T02:16:15.891141+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUPCHA3F","created_at":"2026-07-05T02:16:15.891141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08805","citing_title":"Building Better Environments for Autonomous Cyber Defence","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D","json":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D.json","graph_json":"https://pith.science/api/pith-number/CUPCHA3FHFKIZQXAIJPEYKKS3D/graph.json","events_json":"https://pith.science/api/pith-number/CUPCHA3FHFKIZQXAIJPEYKKS3D/events.json","paper":"https://pith.science/paper/CUPCHA3F"},"agent_actions":{"view_html":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D","download_json":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D.json","view_paper":"https://pith.science/paper/CUPCHA3F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01010&json=true","fetch_graph":"https://pith.science/api/pith-number/CUPCHA3FHFKIZQXAIJPEYKKS3D/graph.json","fetch_events":"https://pith.science/api/pith-number/CUPCHA3FHFKIZQXAIJPEYKKS3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D/action/storage_attestation","attest_author":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D/action/author_attestation","sign_citation":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D/action/citation_signature","submit_replication":"https://pith.science/pith/CUPCHA3FHFKIZQXAIJPEYKKS3D/action/replication_record"}},"created_at":"2026-07-05T02:16:15.891141+00:00","updated_at":"2026-07-05T02:16:15.891141+00:00"}