{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6SDQDYVJPI3ECH7XHIBODNTJRY","short_pith_number":"pith:6SDQDYVJ","schema_version":"1.0","canonical_sha256":"f48701e2a97a36411ff73a02e1b6698e33e94ce6f9515e932c04aa834ae58c51","source":{"kind":"arxiv","id":"2505.23445","version":2},"attestation_state":"computed","paper":{"title":"The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Adrien Majka, El-Mahdi El-Mhamdi","submitted_at":"2025-05-29T13:42:05Z","abstract_excerpt":"Goodhart's law is a famous adage in policy-making that states that ``When a measure becomes a target, it ceases to be a good measure''. As machine learning models and the optimisation capacity to train them grow, growing empirical evidence reinforced the belief in the validity of this law without however being formalised. Recently, a few attempts were made to formalise Goodhart's law, either by categorising variants of it, or by looking at how optimising a proxy metric affects the optimisation of an intended goal. In this work, we alleviate the simplifying independence assumption, made in prev"},"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":"2505.23445","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-29T13:42:05Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"56cb11645889e6463b9758ec088ca55709c3d5dfaccbd9528ce6c6c29a125ecd","abstract_canon_sha256":"0b19ebcd749773736cffd11c50265f13b1fe62cdcf27536baca09a297c5a4adc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:35.292612Z","signature_b64":"Jc0GEMLB7wKXZgNWwnH+zuXboH7vg4ybCNkIzxJkQmhqeGkwFWGhB9832FjFnn389rgQfAao4FXxA4X8AIJuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f48701e2a97a36411ff73a02e1b6698e33e94ce6f9515e932c04aa834ae58c51","last_reissued_at":"2026-07-05T12:04:35.292107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:35.292107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Adrien Majka, El-Mahdi El-Mhamdi","submitted_at":"2025-05-29T13:42:05Z","abstract_excerpt":"Goodhart's law is a famous adage in policy-making that states that ``When a measure becomes a target, it ceases to be a good measure''. As machine learning models and the optimisation capacity to train them grow, growing empirical evidence reinforced the belief in the validity of this law without however being formalised. Recently, a few attempts were made to formalise Goodhart's law, either by categorising variants of it, or by looking at how optimising a proxy metric affects the optimisation of an intended goal. In this work, we alleviate the simplifying independence assumption, made in prev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23445","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/2505.23445/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":"2505.23445","created_at":"2026-07-05T12:04:35.292162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23445v2","created_at":"2026-07-05T12:04:35.292162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23445","created_at":"2026-07-05T12:04:35.292162+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SDQDYVJPI3E","created_at":"2026-07-05T12:04:35.292162+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SDQDYVJPI3ECH7X","created_at":"2026-07-05T12:04:35.292162+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SDQDYVJ","created_at":"2026-07-05T12:04:35.292162+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/6SDQDYVJPI3ECH7XHIBODNTJRY","json":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY.json","graph_json":"https://pith.science/api/pith-number/6SDQDYVJPI3ECH7XHIBODNTJRY/graph.json","events_json":"https://pith.science/api/pith-number/6SDQDYVJPI3ECH7XHIBODNTJRY/events.json","paper":"https://pith.science/paper/6SDQDYVJ"},"agent_actions":{"view_html":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY","download_json":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY.json","view_paper":"https://pith.science/paper/6SDQDYVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23445&json=true","fetch_graph":"https://pith.science/api/pith-number/6SDQDYVJPI3ECH7XHIBODNTJRY/graph.json","fetch_events":"https://pith.science/api/pith-number/6SDQDYVJPI3ECH7XHIBODNTJRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY/action/storage_attestation","attest_author":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY/action/author_attestation","sign_citation":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY/action/citation_signature","submit_replication":"https://pith.science/pith/6SDQDYVJPI3ECH7XHIBODNTJRY/action/replication_record"}},"created_at":"2026-07-05T12:04:35.292162+00:00","updated_at":"2026-07-05T12:04:35.292162+00:00"}