{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DQ2JX6PSHRORJYCSRUBHIHTVBO","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":"83715846f9e0f5c3ae56fd3df593ae31655f6f4407e4ebb5ed3f969ea9dcf2e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T13:19:26Z","title_canon_sha256":"6199824ae15e555cb61804a3b36389a1e9c7299024cf1ddf0fe698e775b9f3fd"},"schema_version":"1.0","source":{"id":"2406.12589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12589","created_at":"2026-07-05T08:33:48Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12589v1","created_at":"2026-07-05T08:33:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12589","created_at":"2026-07-05T08:33:48Z"},{"alias_kind":"pith_short_12","alias_value":"DQ2JX6PSHROR","created_at":"2026-07-05T08:33:48Z"},{"alias_kind":"pith_short_16","alias_value":"DQ2JX6PSHRORJYCS","created_at":"2026-07-05T08:33:48Z"},{"alias_kind":"pith_short_8","alias_value":"DQ2JX6PS","created_at":"2026-07-05T08:33:48Z"}],"graph_snapshots":[{"event_id":"sha256:cdb1c9dcdde2b504e0f156d82b70f663164c341def49f5d37a52c0c22005b22d","target":"graph","created_at":"2026-07-05T08:33:48Z","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/2406.12589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents are commonly trained and evaluated in the same environment. In contrast, humans often train in a specialized environment before being evaluated, such as studying a book before taking an exam. The potential of such specialized training environments is still vastly underexplored, despite their capacity to dramatically speed up training.\n  The framework of synthetic environments takes a first step in this direction by meta-learning neural network-based Markov decision processes (MDPs). The initial approach was limited to toy problems and produced environments th","authors_text":"Andrei Lupu, Chris Lu, Henning Sprekeler, Jakob N. Foerster, Jarek Liesen, Robert T. Lange","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T13:19:26Z","title":"Discovering Minimal Reinforcement Learning Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12589","kind":"arxiv","version":1},"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:a0264b2f2ec9b09215597c1866d47d1922fd51fba08a11b8874d0d3bf8ebd5fa","target":"record","created_at":"2026-07-05T08:33:48Z","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":"83715846f9e0f5c3ae56fd3df593ae31655f6f4407e4ebb5ed3f969ea9dcf2e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T13:19:26Z","title_canon_sha256":"6199824ae15e555cb61804a3b36389a1e9c7299024cf1ddf0fe698e775b9f3fd"},"schema_version":"1.0","source":{"id":"2406.12589","kind":"arxiv","version":1}},"canonical_sha256":"1c349bf9f23c5d14e0528d02741e750bbf1576432f117fd49c5e1bec7dcda8e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c349bf9f23c5d14e0528d02741e750bbf1576432f117fd49c5e1bec7dcda8e3","first_computed_at":"2026-07-05T08:33:48.432584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:48.432584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Czy1Qqj0LBABlWN1XNqK2oo/+qSJ4gM3YCuBqHTZIu3Lm+zQPDIO61Oh5VOV3y30/Ti85cXLZLWd1ItJqYfYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:48.433066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0264b2f2ec9b09215597c1866d47d1922fd51fba08a11b8874d0d3bf8ebd5fa","sha256:cdb1c9dcdde2b504e0f156d82b70f663164c341def49f5d37a52c0c22005b22d"],"state_sha256":"8eef64d9ff7512bc997171805c31674367394299b233060452baff917aee8ce8"}