{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2LH5DOFVNXRTP2OZG6PLEJK3ZA","short_pith_number":"pith:2LH5DOFV","schema_version":"1.0","canonical_sha256":"d2cfd1b8b56de337e9d9379eb2255bc803c6530447a64b499a35ae776b081089","source":{"kind":"arxiv","id":"2408.15099","version":3},"attestation_state":"computed","paper":{"title":"No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexander Rutherford, Bruno Lacerda, Jakob Foerster, Michael Beukman, Nick Hawes, Timon Willi","submitted_at":"2024-08-27T14:31:54Z","abstract_excerpt":"What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks. This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics. Surprisingly, despite methods aiming to maximise regret in theory, the practical approximations do not correlate with regret but with su"},"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":"2408.15099","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T14:31:54Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"1e99a5f03c6d7591910fa764a4963e2179e3e1a582b678053a5626f8a84b72fd","abstract_canon_sha256":"2ae7098971d28fa4e25b74a014dfbf8b951b4b08506dea4781bafaea0bc4d3b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:13.488092Z","signature_b64":"rjtg1CNYYow5FWUqG2WOqNX9tA2kAmTqZd1C/VQ2tCmn8cWv6B+pjBtZucx39+TSKspFfbxBU7jqgGSmWR1QBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2cfd1b8b56de337e9d9379eb2255bc803c6530447a64b499a35ae776b081089","last_reissued_at":"2026-07-05T09:28:13.487604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:13.487604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexander Rutherford, Bruno Lacerda, Jakob Foerster, Michael Beukman, Nick Hawes, Timon Willi","submitted_at":"2024-08-27T14:31:54Z","abstract_excerpt":"What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks. This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics. Surprisingly, despite methods aiming to maximise regret in theory, the practical approximations do not correlate with regret but with su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15099","kind":"arxiv","version":3},"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/2408.15099/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":"2408.15099","created_at":"2026-07-05T09:28:13.487660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15099v3","created_at":"2026-07-05T09:28:13.487660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15099","created_at":"2026-07-05T09:28:13.487660+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LH5DOFVNXRT","created_at":"2026-07-05T09:28:13.487660+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LH5DOFVNXRTP2OZ","created_at":"2026-07-05T09:28:13.487660+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LH5DOFV","created_at":"2026-07-05T09:28:13.487660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.12272","citing_title":"Learning to Reason at the Frontier of Learnability","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA","json":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA.json","graph_json":"https://pith.science/api/pith-number/2LH5DOFVNXRTP2OZG6PLEJK3ZA/graph.json","events_json":"https://pith.science/api/pith-number/2LH5DOFVNXRTP2OZG6PLEJK3ZA/events.json","paper":"https://pith.science/paper/2LH5DOFV"},"agent_actions":{"view_html":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA","download_json":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA.json","view_paper":"https://pith.science/paper/2LH5DOFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15099&json=true","fetch_graph":"https://pith.science/api/pith-number/2LH5DOFVNXRTP2OZG6PLEJK3ZA/graph.json","fetch_events":"https://pith.science/api/pith-number/2LH5DOFVNXRTP2OZG6PLEJK3ZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA/action/storage_attestation","attest_author":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA/action/author_attestation","sign_citation":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA/action/citation_signature","submit_replication":"https://pith.science/pith/2LH5DOFVNXRTP2OZG6PLEJK3ZA/action/replication_record"}},"created_at":"2026-07-05T09:28:13.487660+00:00","updated_at":"2026-07-05T09:28:13.487660+00:00"}