{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FU3UN3TP2ZCGKBEHQTXSDWPCMC","short_pith_number":"pith:FU3UN3TP","schema_version":"1.0","canonical_sha256":"2d3746ee6fd64465048784ef21d9e260800b1117dae78f468d77f41c7ae4e804","source":{"kind":"arxiv","id":"2412.07165","version":2},"attestation_state":"computed","paper":{"title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Jacob Adkins, Michael Bowling","submitted_at":"2024-12-10T03:55:18Z","abstract_excerpt":"The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achieve state-of-the-art performance reported in the literature. We currently lack a scalable and widely accepted approach to characterizing these complex interactions. This work proposes a new empirical methodology for studying, comparing, and quantifying the sensitivity of an algorithm's performance to "},"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":"2412.07165","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T03:55:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ecf3cc39329e6dacb3a62749f0422d5568b804c52af4dfc8d21a4d53d974b4ce","abstract_canon_sha256":"b8b516cc5fea26cb2837c3abeaa5ba93efa18bf640642c3998e66843bbd8ac16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:13.277398Z","signature_b64":"D+b33LkgWBz+Y/1gCtSDzv5cOKv37ibWJjLNWehhtpVeb4fQFijCsMsgA9sd5jwv8hi1u8Gn3FcCRPwNbHt8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d3746ee6fd64465048784ef21d9e260800b1117dae78f468d77f41c7ae4e804","last_reissued_at":"2026-07-05T10:09:13.276856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:13.276856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Jacob Adkins, Michael Bowling","submitted_at":"2024-12-10T03:55:18Z","abstract_excerpt":"The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achieve state-of-the-art performance reported in the literature. We currently lack a scalable and widely accepted approach to characterizing these complex interactions. This work proposes a new empirical methodology for studying, comparing, and quantifying the sensitivity of an algorithm's performance to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07165","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/2412.07165/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":"2412.07165","created_at":"2026-07-05T10:09:13.276919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07165v2","created_at":"2026-07-05T10:09:13.276919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07165","created_at":"2026-07-05T10:09:13.276919+00:00"},{"alias_kind":"pith_short_12","alias_value":"FU3UN3TP2ZCG","created_at":"2026-07-05T10:09:13.276919+00:00"},{"alias_kind":"pith_short_16","alias_value":"FU3UN3TP2ZCGKBEH","created_at":"2026-07-05T10:09:13.276919+00:00"},{"alias_kind":"pith_short_8","alias_value":"FU3UN3TP","created_at":"2026-07-05T10:09:13.276919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01567","citing_title":"Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC","json":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC.json","graph_json":"https://pith.science/api/pith-number/FU3UN3TP2ZCGKBEHQTXSDWPCMC/graph.json","events_json":"https://pith.science/api/pith-number/FU3UN3TP2ZCGKBEHQTXSDWPCMC/events.json","paper":"https://pith.science/paper/FU3UN3TP"},"agent_actions":{"view_html":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC","download_json":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC.json","view_paper":"https://pith.science/paper/FU3UN3TP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07165&json=true","fetch_graph":"https://pith.science/api/pith-number/FU3UN3TP2ZCGKBEHQTXSDWPCMC/graph.json","fetch_events":"https://pith.science/api/pith-number/FU3UN3TP2ZCGKBEHQTXSDWPCMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC/action/storage_attestation","attest_author":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC/action/author_attestation","sign_citation":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC/action/citation_signature","submit_replication":"https://pith.science/pith/FU3UN3TP2ZCGKBEHQTXSDWPCMC/action/replication_record"}},"created_at":"2026-07-05T10:09:13.276919+00:00","updated_at":"2026-07-05T10:09:13.276919+00:00"}