{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2TRPT4VLWBEDOJ7FJ4OT57ZA3I","short_pith_number":"pith:2TRPT4VL","canonical_record":{"source":{"id":"2203.02481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T18:25:33Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"39a0e858b5ff09e09db83ad7a110365ea311606b75cd2441ee048ffe98b2a8f1","abstract_canon_sha256":"4fa8830b7767fd4bc988f20089afa748d8c36d89295920bde34c14eb25f710d7"},"schema_version":"1.0"},"canonical_sha256":"d4e2f9f2abb0483727e54f1d3eff20da2ecc3d2a5c25f89aaa6202f57a6ccbf8","source":{"kind":"arxiv","id":"2203.02481","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02481","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02481v1","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02481","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"2TRPT4VLWBED","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"2TRPT4VLWBEDOJ7F","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"2TRPT4VL","created_at":"2026-07-05T04:02:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2TRPT4VLWBEDOJ7FJ4OT57ZA3I","target":"record","payload":{"canonical_record":{"source":{"id":"2203.02481","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T18:25:33Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"39a0e858b5ff09e09db83ad7a110365ea311606b75cd2441ee048ffe98b2a8f1","abstract_canon_sha256":"4fa8830b7767fd4bc988f20089afa748d8c36d89295920bde34c14eb25f710d7"},"schema_version":"1.0"},"canonical_sha256":"d4e2f9f2abb0483727e54f1d3eff20da2ecc3d2a5c25f89aaa6202f57a6ccbf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:11.081557Z","signature_b64":"HRXfDr7MKO6kl830/U1e7gB1HbpxivFPJlByHCqKbHYfWUofQwC888nqMGlTOyC87pb/TPDeWhy85YbzT1wTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4e2f9f2abb0483727e54f1d3eff20da2ecc3d2a5c25f89aaa6202f57a6ccbf8","last_reissued_at":"2026-07-05T04:02:11.080958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:11.080958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.02481","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":"2026-07-05T04:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5+jj2zJS+wTvrffBkSj4M2XBSsis+4ishayU6MqgvbKgrJt3LyeNoD8B8FWd7wVkN1ZB250GEZ5Fqgn4jnuhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:53:03.712555Z"},"content_sha256":"3e0298eecfb648c0a2cd5d8ca5fe0b45a3c5ec3b005f31c6f48ee59052d63aeb","schema_version":"1.0","event_id":"sha256:3e0298eecfb648c0a2cd5d8ca5fe0b45a3c5ec3b005f31c6f48ee59052d63aeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2TRPT4VLWBEDOJ7FJ4OT57ZA3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoDIME: Automatic Design of Interesting Multi-Agent Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harri Edwards, Ingmar Kanitscheider","submitted_at":"2022-03-04T18:25:33Z","abstract_excerpt":"Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the difficulties are only exacerbated. One approach is to train a second RL agent, called a teacher, who samples environments that are conducive for the learning of student agents. However, most previous proposals for teacher rewards do not generalize straightforwardly to the multi-agent setting. We examine a set of intrinsic teacher rewards derived from prediction problems that can be applied in multi-agent settings and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02481","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/2203.02481/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5UnMI2xSFQnh4TUoIqCyCvUkcfp6x5hTF0RywYVCzxBGvpO3hQJouRIUcEDVDljlo6gdqyIr81trQs4+xxiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:53:03.713122Z"},"content_sha256":"a5f450e860d3f0f31baada5bb252f1f2a86237d1e3a9143cac4d14955f776a67","schema_version":"1.0","event_id":"sha256:a5f450e860d3f0f31baada5bb252f1f2a86237d1e3a9143cac4d14955f776a67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/bundle.json","state_url":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/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":"2026-08-05T15:53:03Z","links":{"resolver":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I","bundle":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/bundle.json","state":"https://pith.science/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TRPT4VLWBEDOJ7FJ4OT57ZA3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2TRPT4VLWBEDOJ7FJ4OT57ZA3I","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":"4fa8830b7767fd4bc988f20089afa748d8c36d89295920bde34c14eb25f710d7","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T18:25:33Z","title_canon_sha256":"39a0e858b5ff09e09db83ad7a110365ea311606b75cd2441ee048ffe98b2a8f1"},"schema_version":"1.0","source":{"id":"2203.02481","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02481","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02481v1","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02481","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"2TRPT4VLWBED","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"2TRPT4VLWBEDOJ7F","created_at":"2026-07-05T04:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"2TRPT4VL","created_at":"2026-07-05T04:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:a5f450e860d3f0f31baada5bb252f1f2a86237d1e3a9143cac4d14955f776a67","target":"graph","created_at":"2026-07-05T04:02:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.02481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the difficulties are only exacerbated. One approach is to train a second RL agent, called a teacher, who samples environments that are conducive for the learning of student agents. However, most previous proposals for teacher rewards do not generalize straightforwardly to the multi-agent setting. We examine a set of intrinsic teacher rewards derived from prediction problems that can be applied in multi-agent settings and e","authors_text":"Harri Edwards, Ingmar Kanitscheider","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T18:25:33Z","title":"AutoDIME: Automatic Design of Interesting Multi-Agent Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02481","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":"sha256:3e0298eecfb648c0a2cd5d8ca5fe0b45a3c5ec3b005f31c6f48ee59052d63aeb","target":"record","created_at":"2026-07-05T04:02:11Z","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":"4fa8830b7767fd4bc988f20089afa748d8c36d89295920bde34c14eb25f710d7","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-04T18:25:33Z","title_canon_sha256":"39a0e858b5ff09e09db83ad7a110365ea311606b75cd2441ee048ffe98b2a8f1"},"schema_version":"1.0","source":{"id":"2203.02481","kind":"arxiv","version":1}},"canonical_sha256":"d4e2f9f2abb0483727e54f1d3eff20da2ecc3d2a5c25f89aaa6202f57a6ccbf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4e2f9f2abb0483727e54f1d3eff20da2ecc3d2a5c25f89aaa6202f57a6ccbf8","first_computed_at":"2026-07-05T04:02:11.080958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:11.080958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HRXfDr7MKO6kl830/U1e7gB1HbpxivFPJlByHCqKbHYfWUofQwC888nqMGlTOyC87pb/TPDeWhy85YbzT1wTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:11.081557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02481","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e0298eecfb648c0a2cd5d8ca5fe0b45a3c5ec3b005f31c6f48ee59052d63aeb","sha256:a5f450e860d3f0f31baada5bb252f1f2a86237d1e3a9143cac4d14955f776a67"],"state_sha256":"0b31d1efee162311fb562f37f0aa5e2b059fc3a1779b9d6bf13f9d9b7bfe3b5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zygcOjiT9XYZAtroX0cLujCPJZAjWdvE5KnoO2U9sgzah38WvO6YOBo9lB+1db9g/7fLoqhjv2fQ1FdwaMRFDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:53:03.717145Z","bundle_sha256":"63dca1eaee0b495a3e563de7b0d8c4df75f114bd8817773fb942d569aa2f54c7"}}