{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CDX67MILDFNYFANQQNQMZPMLTH","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":"7be11b2e6179eb04dc66160ea6d0e7e8f331e3d935b0463f1a9056dee9d7cb8c","cross_cats_sorted":["cs.AI","cs.CL","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T14:12:56Z","title_canon_sha256":"c28ae30c5f54bd2ba5b6b629bbed96398211963bdb71b8e246ce5e874a0d2641"},"schema_version":"1.0","source":{"id":"2006.13760","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13760","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13760v2","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13760","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_12","alias_value":"CDX67MILDFNY","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_16","alias_value":"CDX67MILDFNYFANQ","created_at":"2026-07-05T01:55:29Z"},{"alias_kind":"pith_short_8","alias_value":"CDX67MIL","created_at":"2026-07-05T01:55:29Z"}],"graph_snapshots":[{"event_id":"sha256:03623a5a4c95cd2e62f09dfd22c17a5f327acef687209c5e2f0b548af03ee42f","target":"graph","created_at":"2026-07-05T01:55:29Z","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/2006.13760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the development of challenging environments that test the limits of current methods. While existing RL environments are either sufficiently complex or based on fast simulation, they are rarely both. Here, we present the NetHack Learning Environment (NLE), a scalable, procedurally generated, stochastic, rich, and challenging environment for RL research based on the popular single-player terminal-based roguelike game, NetHack. We argue that NetHack is sufficiently complex to drive long-term research on problems such as exp","authors_text":"Alexander H. Miller, Edward Grefenstette, Heinrich K\\\"uttler, Marco Selvatici, Nantas Nardelli, Roberta Raileanu, Tim Rockt\\\"aschel","cross_cats":["cs.AI","cs.CL","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T14:12:56Z","title":"The NetHack Learning Environment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13760","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:d961afec39d04fb99088d4084165339b15e00cf5b807819ce2050bf213fac87d","target":"record","created_at":"2026-07-05T01:55:29Z","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":"7be11b2e6179eb04dc66160ea6d0e7e8f331e3d935b0463f1a9056dee9d7cb8c","cross_cats_sorted":["cs.AI","cs.CL","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T14:12:56Z","title_canon_sha256":"c28ae30c5f54bd2ba5b6b629bbed96398211963bdb71b8e246ce5e874a0d2641"},"schema_version":"1.0","source":{"id":"2006.13760","kind":"arxiv","version":2}},"canonical_sha256":"10efefb10b195b8281b08360ccbd8b99d3198b2747c0cb894448ce96d7a096e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10efefb10b195b8281b08360ccbd8b99d3198b2747c0cb894448ce96d7a096e9","first_computed_at":"2026-07-05T01:55:29.114787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:29.114787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iTEn1aZ/tTUsHyNKR+4YySdbL8ZbsjzYDhLJumaFdyqXbhnMBlYARhKlGaaUk7aIlPHINVcewN+00BVpTqUwCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:29.115120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13760","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d961afec39d04fb99088d4084165339b15e00cf5b807819ce2050bf213fac87d","sha256:03623a5a4c95cd2e62f09dfd22c17a5f327acef687209c5e2f0b548af03ee42f"],"state_sha256":"01224d13bda3c406a719fb6b18c5dad95a7b3fdfa9cea2c50d6d5722cde70613"}