{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7EXCTHOIFG66BZEAPI2ELN3V4G","short_pith_number":"pith:7EXCTHOI","schema_version":"1.0","canonical_sha256":"f92e299dc829bde0e4807a3445b775e1b869b93c3b54a6eb233361aa1d628723","source":{"kind":"arxiv","id":"2303.03376","version":1},"attestation_state":"computed","paper":{"title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Akbir Khan, Jack Parker-Holder, Jakob Foerster, Michael Dennis, Mikayel Samvelyan, Minqi Jiang, Roberta Raileanu, Tim Rockt\\\"aschel","submitted_at":"2023-03-06T18:57:41Z","abstract_excerpt":"Open-ended learning methods that automatically generate a curriculum of increasingly challenging tasks serve as a promising avenue toward generally capable reinforcement learning agents. Existing methods adapt curricula independently over either environment parameters (in single-agent settings) or co-player policies (in multi-agent settings). However, the strengths and weaknesses of co-players can manifest themselves differently depending on environmental features. It is thus crucial to consider the dependency between the environment and co-player when shaping a curriculum in multi-agent domai"},"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":"2303.03376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-06T18:57:41Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"ae178ca584a19be2dfb9175c18a98aa3ed818a788a0a623a16111dbf7c0fcfb7","abstract_canon_sha256":"f90fbaeb0df9714af8053b4b5b14ef68e8c72b8d08a76136cf0146a259d8ff5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:28.925931Z","signature_b64":"vJMwXbGYZVs76fL66vA3Lo2Uvz0tOYHg5Jttfuzw4QaZs/ucfOgwHqhxsuIYo2qyHbjx06KTzeLtofqAzlK8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92e299dc829bde0e4807a3445b775e1b869b93c3b54a6eb233361aa1d628723","last_reissued_at":"2026-07-05T05:48:28.925470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:28.925470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Akbir Khan, Jack Parker-Holder, Jakob Foerster, Michael Dennis, Mikayel Samvelyan, Minqi Jiang, Roberta Raileanu, Tim Rockt\\\"aschel","submitted_at":"2023-03-06T18:57:41Z","abstract_excerpt":"Open-ended learning methods that automatically generate a curriculum of increasingly challenging tasks serve as a promising avenue toward generally capable reinforcement learning agents. Existing methods adapt curricula independently over either environment parameters (in single-agent settings) or co-player policies (in multi-agent settings). However, the strengths and weaknesses of co-players can manifest themselves differently depending on environmental features. It is thus crucial to consider the dependency between the environment and co-player when shaping a curriculum in multi-agent domai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03376","kind":"arxiv","version":1},"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/2303.03376/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":"2303.03376","created_at":"2026-07-05T05:48:28.925529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03376v1","created_at":"2026-07-05T05:48:28.925529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03376","created_at":"2026-07-05T05:48:28.925529+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EXCTHOIFG66","created_at":"2026-07-05T05:48:28.925529+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EXCTHOIFG66BZEA","created_at":"2026-07-05T05:48:28.925529+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EXCTHOI","created_at":"2026-07-05T05:48:28.925529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":282,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09423","citing_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01358","citing_title":"PACE: Parameter Change for Unsupervised Environment Design","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G","json":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G.json","graph_json":"https://pith.science/api/pith-number/7EXCTHOIFG66BZEAPI2ELN3V4G/graph.json","events_json":"https://pith.science/api/pith-number/7EXCTHOIFG66BZEAPI2ELN3V4G/events.json","paper":"https://pith.science/paper/7EXCTHOI"},"agent_actions":{"view_html":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G","download_json":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G.json","view_paper":"https://pith.science/paper/7EXCTHOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03376&json=true","fetch_graph":"https://pith.science/api/pith-number/7EXCTHOIFG66BZEAPI2ELN3V4G/graph.json","fetch_events":"https://pith.science/api/pith-number/7EXCTHOIFG66BZEAPI2ELN3V4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G/action/storage_attestation","attest_author":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G/action/author_attestation","sign_citation":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G/action/citation_signature","submit_replication":"https://pith.science/pith/7EXCTHOIFG66BZEAPI2ELN3V4G/action/replication_record"}},"created_at":"2026-07-05T05:48:28.925529+00:00","updated_at":"2026-07-05T05:48:28.925529+00:00"}