{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WRM4S3QWAZ7RNOA4EGYPMXFSA5","short_pith_number":"pith:WRM4S3QW","schema_version":"1.0","canonical_sha256":"b459c96e16067f16b81c21b0f65cb20760bca0ab8989419bf49929be11156e98","source":{"kind":"arxiv","id":"2206.04199","version":3},"attestation_state":"computed","paper":{"title":"Deep Surrogate Assisted Generation of Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Bryon Tjanaka, Matthew C. Fontaine, Stefanos Nikolaidis, Varun Bhatt","submitted_at":"2022-06-09T00:14:03Z","abstract_excerpt":"Recent progress in reinforcement learning (RL) has started producing generally capable agents that can solve a distribution of complex environments. These agents are typically tested on fixed, human-authored environments. On the other hand, quality diversity (QD) optimization has been proven to be an effective component of environment generation algorithms, which can generate collections of high-quality environments that are diverse in the resulting agent behaviors. However, these algorithms require potentially expensive simulations of agents on newly generated environments. We propose Deep 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":"2206.04199","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-06-09T00:14:03Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"8d2856f6940a20ffc520542bb35cf5c188f0c0df39805a65123b395a83e75487","abstract_canon_sha256":"e1e1df852b78eb5c2d0a3764997e56513aa8ddcdb7392c80ada64ab737703423"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:48.259723Z","signature_b64":"6eg35ahWKQa0u3bDAir326n8tX0WI+Ujzmu2vyPG6STnzDJlDSsANB5zUnlzI6pgVh5YI4f3qrwgxim8TA9NAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b459c96e16067f16b81c21b0f65cb20760bca0ab8989419bf49929be11156e98","last_reissued_at":"2026-07-05T05:05:48.259239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:48.259239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Surrogate Assisted Generation of Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Bryon Tjanaka, Matthew C. Fontaine, Stefanos Nikolaidis, Varun Bhatt","submitted_at":"2022-06-09T00:14:03Z","abstract_excerpt":"Recent progress in reinforcement learning (RL) has started producing generally capable agents that can solve a distribution of complex environments. These agents are typically tested on fixed, human-authored environments. On the other hand, quality diversity (QD) optimization has been proven to be an effective component of environment generation algorithms, which can generate collections of high-quality environments that are diverse in the resulting agent behaviors. However, these algorithms require potentially expensive simulations of agents on newly generated environments. We propose Deep Su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04199","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/2206.04199/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":"2206.04199","created_at":"2026-07-05T05:05:48.259295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04199v3","created_at":"2026-07-05T05:05:48.259295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04199","created_at":"2026-07-05T05:05:48.259295+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRM4S3QWAZ7R","created_at":"2026-07-05T05:05:48.259295+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRM4S3QWAZ7RNOA4","created_at":"2026-07-05T05:05:48.259295+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRM4S3QW","created_at":"2026-07-05T05:05:48.259295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07029","citing_title":"Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5","json":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5.json","graph_json":"https://pith.science/api/pith-number/WRM4S3QWAZ7RNOA4EGYPMXFSA5/graph.json","events_json":"https://pith.science/api/pith-number/WRM4S3QWAZ7RNOA4EGYPMXFSA5/events.json","paper":"https://pith.science/paper/WRM4S3QW"},"agent_actions":{"view_html":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5","download_json":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5.json","view_paper":"https://pith.science/paper/WRM4S3QW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04199&json=true","fetch_graph":"https://pith.science/api/pith-number/WRM4S3QWAZ7RNOA4EGYPMXFSA5/graph.json","fetch_events":"https://pith.science/api/pith-number/WRM4S3QWAZ7RNOA4EGYPMXFSA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5/action/storage_attestation","attest_author":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5/action/author_attestation","sign_citation":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5/action/citation_signature","submit_replication":"https://pith.science/pith/WRM4S3QWAZ7RNOA4EGYPMXFSA5/action/replication_record"}},"created_at":"2026-07-05T05:05:48.259295+00:00","updated_at":"2026-07-05T05:05:48.259295+00:00"}