{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DMP6OYWQU4PB4H2MBIVNRNZRZF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"696eb1938a29e66e1eb5f9aa2fe1b86dcf3a5f64305a356bd3e3415829bb3dc6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-04T14:09:00Z","title_canon_sha256":"dc4799f128304c798ca229238e41f1a530bfea2dc1ba1fbdf9cba17881c155db"},"schema_version":"1.0","source":{"id":"2502.02332","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02332","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02332v2","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02332","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"DMP6OYWQU4PB","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_16","alias_value":"DMP6OYWQU4PB4H2M","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_8","alias_value":"DMP6OYWQ","created_at":"2026-07-05T10:47:57Z"}],"graph_snapshots":[{"event_id":"sha256:c75792658020222905ab56ef20da7a9826cb3a5e101e7d139ea400d8c49ee891","target":"graph","created_at":"2026-07-05T10:47:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.02332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study task selection to enhance sample efficiency in model-agnostic meta-reinforcement learning (MAML-RL). Traditional meta-RL typically assumes that all available tasks are equally important, which can lead to task redundancy when they share significant similarities. To address this, we propose a coreset-based task selection approach that selects a weighted subset of tasks based on how diverse they are in gradient space, prioritizing the most informative and diverse tasks. Such task selection reduces the number of samples needed to find an $\\epsilon$-close stationary solution by a factor o","authors_text":"Donglin Zhan, James Anderson, Leonardo F. Toso","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-04T14:09:00Z","title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02332","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1477f0b4e31e577cdc0656ffcf57dc02b242e34be39788bea17176e795f2ef24","target":"record","created_at":"2026-07-05T10:47:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"696eb1938a29e66e1eb5f9aa2fe1b86dcf3a5f64305a356bd3e3415829bb3dc6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-04T14:09:00Z","title_canon_sha256":"dc4799f128304c798ca229238e41f1a530bfea2dc1ba1fbdf9cba17881c155db"},"schema_version":"1.0","source":{"id":"2502.02332","kind":"arxiv","version":2}},"canonical_sha256":"1b1fe762d0a71e1e1f4c0a2ad8b731c969050af8cd48a5369d30abdf2a2b4d5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b1fe762d0a71e1e1f4c0a2ad8b731c969050af8cd48a5369d30abdf2a2b4d5c","first_computed_at":"2026-07-05T10:47:57.225627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:57.225627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bjMeQz+DetVF96ODoK4kXDR5JYSezHmsT9JO2Is/uB1tFU2dn0cxKw+5z5guu0wi1FZNKoW9NOT0/sQ5oqVuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:57.226131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02332","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1477f0b4e31e577cdc0656ffcf57dc02b242e34be39788bea17176e795f2ef24","sha256:c75792658020222905ab56ef20da7a9826cb3a5e101e7d139ea400d8c49ee891"],"state_sha256":"f9c56610be018d56448ca1f19d8d25aee3be54bad4224b357e2b43be742e0be7"}