{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YSFC2RUEAESIBIOQTTPH3LRJMO","short_pith_number":"pith:YSFC2RUE","schema_version":"1.0","canonical_sha256":"c48a2d4684012480a1d09cde7dae2963b1f80cc7e26ce7784148f7195c1702ba","source":{"kind":"arxiv","id":"2401.14483","version":4},"attestation_state":"computed","paper":{"title":"Evaluation Metrics as Averaged Outcomes of Fair Gambles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rabanus Derr, Robert C. Williamson","submitted_at":"2024-01-25T19:36:11Z","abstract_excerpt":"In the current practices of machine learning, the evaluation of forecasts has become a cornerstone of scientific progress. A multitude of evaluation metrics have been suggested and used to qualify \"good\" forecasts. What do those metrics share? How are they related? In this work, we use a protocol borrowed from game-theoretic probability to show that a large part of evaluation metrics can be viewed as averaged outcomes of fair gambles. Intuitively, a fair gambler is one which a forecaster would expect to fail. Hence, the gambler's ability to gain disproves the quality of the forecast. Standard "},"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":"2401.14483","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-25T19:36:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7a58b0044b42a04a3ff8f57895e2d13b30a76fa0148205089b8238b2ec644027","abstract_canon_sha256":"f1422896a73d4b28606b2792ce3bcbad79abc38fdf72474b8d9f13a26054ef58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:55.197916Z","signature_b64":"QhhX45jzAjICL+WCXjNr+7Yqu6NJGgPbKWvc+bLxot/S69t2BIJHFIcNqIJX7K6SsfMClfJjExnOrxpl5nCNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c48a2d4684012480a1d09cde7dae2963b1f80cc7e26ce7784148f7195c1702ba","last_reissued_at":"2026-06-24T01:14:55.197423Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:55.197423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation Metrics as Averaged Outcomes of Fair Gambles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rabanus Derr, Robert C. Williamson","submitted_at":"2024-01-25T19:36:11Z","abstract_excerpt":"In the current practices of machine learning, the evaluation of forecasts has become a cornerstone of scientific progress. A multitude of evaluation metrics have been suggested and used to qualify \"good\" forecasts. What do those metrics share? How are they related? In this work, we use a protocol borrowed from game-theoretic probability to show that a large part of evaluation metrics can be viewed as averaged outcomes of fair gambles. Intuitively, a fair gambler is one which a forecaster would expect to fail. Hence, the gambler's ability to gain disproves the quality of the forecast. Standard "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14483","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/2401.14483/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":"2401.14483","created_at":"2026-06-24T01:14:55.197482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14483v4","created_at":"2026-06-24T01:14:55.197482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14483","created_at":"2026-06-24T01:14:55.197482+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSFC2RUEAESI","created_at":"2026-06-24T01:14:55.197482+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSFC2RUEAESIBIOQ","created_at":"2026-06-24T01:14:55.197482+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSFC2RUE","created_at":"2026-06-24T01:14:55.197482+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/YSFC2RUEAESIBIOQTTPH3LRJMO","json":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO.json","graph_json":"https://pith.science/api/pith-number/YSFC2RUEAESIBIOQTTPH3LRJMO/graph.json","events_json":"https://pith.science/api/pith-number/YSFC2RUEAESIBIOQTTPH3LRJMO/events.json","paper":"https://pith.science/paper/YSFC2RUE"},"agent_actions":{"view_html":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO","download_json":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO.json","view_paper":"https://pith.science/paper/YSFC2RUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14483&json=true","fetch_graph":"https://pith.science/api/pith-number/YSFC2RUEAESIBIOQTTPH3LRJMO/graph.json","fetch_events":"https://pith.science/api/pith-number/YSFC2RUEAESIBIOQTTPH3LRJMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO/action/storage_attestation","attest_author":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO/action/author_attestation","sign_citation":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO/action/citation_signature","submit_replication":"https://pith.science/pith/YSFC2RUEAESIBIOQTTPH3LRJMO/action/replication_record"}},"created_at":"2026-06-24T01:14:55.197482+00:00","updated_at":"2026-06-24T01:14:55.197482+00:00"}