{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AP452UIROEWPGHXY2KZBWCUPRQ","short_pith_number":"pith:AP452UIR","canonical_record":{"source":{"id":"1806.01780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-05T16:21:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dae165f9acd788b2d01bc380c896f57d5095fb656c5b24e0b98f092e9582b220","abstract_canon_sha256":"910c7ea1e31e76ab1476b888f1384394d644914775b7b6e179ef385c36b1ddb9"},"schema_version":"1.0"},"canonical_sha256":"03f9dd5111712cf31ef8d2b21b0a8f8c03b7b462291a6c495b6eaa099ab9238b","source":{"kind":"arxiv","id":"1806.01780","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01780","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01780v1","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01780","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"AP452UIROEWP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AP452UIROEWPGHXY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AP452UIR","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AP452UIROEWPGHXY2KZBWCUPRQ","target":"record","payload":{"canonical_record":{"source":{"id":"1806.01780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-05T16:21:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dae165f9acd788b2d01bc380c896f57d5095fb656c5b24e0b98f092e9582b220","abstract_canon_sha256":"910c7ea1e31e76ab1476b888f1384394d644914775b7b6e179ef385c36b1ddb9"},"schema_version":"1.0"},"canonical_sha256":"03f9dd5111712cf31ef8d2b21b0a8f8c03b7b462291a6c495b6eaa099ab9238b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:11.856530Z","signature_b64":"Ef035LyScgi8byrQYRkdZKA+DbmLKl5iT3QJa1Mlbg+V4Dhd6C+746+72oZT0oMfMRW8O/uhjJma9C3TbYAfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03f9dd5111712cf31ef8d2b21b0a8f8c03b7b462291a6c495b6eaa099ab9238b","last_reissued_at":"2026-05-18T00:14:11.856052Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:11.856052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.01780","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YukdsICmhHAUAdJwZCPEImHXmr86pu6fsj+PGN9PM7OmgVW7gjZ2UKpbRPHj5IZEKV6OjLKdpjoUMnG2i4LaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:06:23.617442Z"},"content_sha256":"d3e27b30e33e3d04e70309f51b4fdc6f9297ae7000e62da94bd15cc40ae01f93","schema_version":"1.0","event_id":"sha256:d3e27b30e33e3d04e70309f51b4fdc6f9297ae7000e62da94bd15cc40ae01f93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AP452UIROEWPGHXY2KZBWCUPRQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mix&Match - Agent Curricula for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Leonard Hasenclever, Max Jaderberg, Nicolas Heess, Razvan Pascanu, Siddhant M. Jayakumar, Simon Osindero, Wojciech Marian Czarnecki, Yee Whye Teh","submitted_at":"2018-06-05T16:21:25Z","abstract_excerpt":"We introduce Mix&Match (M&M) - a training framework designed to facilitate rapid and effective learning in RL agents, especially those that would be too slow or too challenging to train otherwise. The key innovation is a procedure that allows us to automatically form a curriculum over agents. Through such a curriculum we can progressively train more complex agents by, effectively, bootstrapping from solutions found by simpler agents. In contradistinction to typical curriculum learning approaches, we do not gradually modify the tasks or environments presented, but instead use a process to gradu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01780","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iDIQ+LC6upW1I+Ej4GiUULoX6VPUdVXAsquiCb+rLW2HLO4U/Wl5/3Qmjbz0+d37o1MtQ76dt0fJVznE9L8SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:06:23.618159Z"},"content_sha256":"21b7c71ce1dc3f76af453a5c18d522d451c4af25d1aef7e248cde76ba43b4d01","schema_version":"1.0","event_id":"sha256:21b7c71ce1dc3f76af453a5c18d522d451c4af25d1aef7e248cde76ba43b4d01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AP452UIROEWPGHXY2KZBWCUPRQ/bundle.json","state_url":"https://pith.science/pith/AP452UIROEWPGHXY2KZBWCUPRQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AP452UIROEWPGHXY2KZBWCUPRQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T10:06:23Z","links":{"resolver":"https://pith.science/pith/AP452UIROEWPGHXY2KZBWCUPRQ","bundle":"https://pith.science/pith/AP452UIROEWPGHXY2KZBWCUPRQ/bundle.json","state":"https://pith.science/pith/AP452UIROEWPGHXY2KZBWCUPRQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AP452UIROEWPGHXY2KZBWCUPRQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AP452UIROEWPGHXY2KZBWCUPRQ","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":"910c7ea1e31e76ab1476b888f1384394d644914775b7b6e179ef385c36b1ddb9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-05T16:21:25Z","title_canon_sha256":"dae165f9acd788b2d01bc380c896f57d5095fb656c5b24e0b98f092e9582b220"},"schema_version":"1.0","source":{"id":"1806.01780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01780","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01780v1","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01780","created_at":"2026-05-18T00:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"AP452UIROEWP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AP452UIROEWPGHXY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AP452UIR","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:21b7c71ce1dc3f76af453a5c18d522d451c4af25d1aef7e248cde76ba43b4d01","target":"graph","created_at":"2026-05-18T00:14:11Z","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"},"paper":{"abstract_excerpt":"We introduce Mix&Match (M&M) - a training framework designed to facilitate rapid and effective learning in RL agents, especially those that would be too slow or too challenging to train otherwise. The key innovation is a procedure that allows us to automatically form a curriculum over agents. Through such a curriculum we can progressively train more complex agents by, effectively, bootstrapping from solutions found by simpler agents. In contradistinction to typical curriculum learning approaches, we do not gradually modify the tasks or environments presented, but instead use a process to gradu","authors_text":"Leonard Hasenclever, Max Jaderberg, Nicolas Heess, Razvan Pascanu, Siddhant M. Jayakumar, Simon Osindero, Wojciech Marian Czarnecki, Yee Whye Teh","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-05T16:21:25Z","title":"Mix&Match - Agent Curricula for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01780","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:d3e27b30e33e3d04e70309f51b4fdc6f9297ae7000e62da94bd15cc40ae01f93","target":"record","created_at":"2026-05-18T00:14:11Z","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":"910c7ea1e31e76ab1476b888f1384394d644914775b7b6e179ef385c36b1ddb9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-05T16:21:25Z","title_canon_sha256":"dae165f9acd788b2d01bc380c896f57d5095fb656c5b24e0b98f092e9582b220"},"schema_version":"1.0","source":{"id":"1806.01780","kind":"arxiv","version":1}},"canonical_sha256":"03f9dd5111712cf31ef8d2b21b0a8f8c03b7b462291a6c495b6eaa099ab9238b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03f9dd5111712cf31ef8d2b21b0a8f8c03b7b462291a6c495b6eaa099ab9238b","first_computed_at":"2026-05-18T00:14:11.856052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:11.856052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ef035LyScgi8byrQYRkdZKA+DbmLKl5iT3QJa1Mlbg+V4Dhd6C+746+72oZT0oMfMRW8O/uhjJma9C3TbYAfCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:11.856530Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.01780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3e27b30e33e3d04e70309f51b4fdc6f9297ae7000e62da94bd15cc40ae01f93","sha256:21b7c71ce1dc3f76af453a5c18d522d451c4af25d1aef7e248cde76ba43b4d01"],"state_sha256":"cdee93b3ae4f24fc0731b19c7903538f3fb1d1dfb920b450e4e4cd00cdfa8aef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uq5xQiMOaC8NeLER0FJmM9LKQ91Sy5MOxVllIclhhIcGKZDnNkiyEi0y+dFuf3GZpYdoghCDcpWwsZeGdjIpBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T10:06:23.621889Z","bundle_sha256":"a713d1bd4a324374853cf32a012c9e2c3bab0759ea671883eeef7cd9520e3f33"}}