{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JEOGDZJZZAS43WPKY75KNEQGOL","short_pith_number":"pith:JEOGDZJZ","canonical_record":{"source":{"id":"2301.08025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-19T11:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"d07eb8c9a6ab997e141bef1d34a0192e4b9ac2bc7036b13fbc2cca2c09689727","abstract_canon_sha256":"9c217faecab358fd76b38d10f918aaa240a2c9104278e6e35cc8034615e3e0f5"},"schema_version":"1.0"},"canonical_sha256":"491c61e539c825cdd9eac7faa6920672f454f4a351b9448affa4db7b08343214","source":{"kind":"arxiv","id":"2301.08025","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08025","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08025v2","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08025","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"pith_short_12","alias_value":"JEOGDZJZZAS4","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"pith_short_16","alias_value":"JEOGDZJZZAS43WPK","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"pith_short_8","alias_value":"JEOGDZJZ","created_at":"2026-07-05T06:52:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JEOGDZJZZAS43WPKY75KNEQGOL","target":"record","payload":{"canonical_record":{"source":{"id":"2301.08025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-19T11:55:47Z","cross_cats_sorted":[],"title_canon_sha256":"d07eb8c9a6ab997e141bef1d34a0192e4b9ac2bc7036b13fbc2cca2c09689727","abstract_canon_sha256":"9c217faecab358fd76b38d10f918aaa240a2c9104278e6e35cc8034615e3e0f5"},"schema_version":"1.0"},"canonical_sha256":"491c61e539c825cdd9eac7faa6920672f454f4a351b9448affa4db7b08343214","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:01.926732Z","signature_b64":"a+Xue0eMCfw7q3Sub1dfJgU/op1mjYl8tSG/2gd0PGRaJI+sxAt4RUJs3PudkvYTCVFpo1LCgCr7GnFT0KUaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"491c61e539c825cdd9eac7faa6920672f454f4a351b9448affa4db7b08343214","last_reissued_at":"2026-07-05T06:52:01.926279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:01.926279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.08025","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:52:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2CafHlxAIk5Dg4ZMsXgQWo7H6abn5UQsIgXTanHfFCES1u2feVFvh5mcQVLh+rIDpfkqmiS1I6xjBbiJ8ErBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:40:08.293987Z"},"content_sha256":"e4df03c9de3ffe33d298a0363a31315e0c3b0424a31f7a419b9d345eda858728","schema_version":"1.0","event_id":"sha256:e4df03c9de3ffe33d298a0363a31315e0c3b0424a31f7a419b9d345eda858728"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JEOGDZJZZAS43WPKY75KNEQGOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization through Diversity: Improving Unsupervised Environment Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dexun Li, Pradeep Varakantham, Wenjun Li","submitted_at":"2023-01-19T11:55:47Z","abstract_excerpt":"Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in the environment (e.g., positions of obstacles in the maze, size of the board) can severely affect the effectiveness of the policy learned by the agent. To that end, existing work has proposed training RL agents on an adaptive curriculum of environments (generated automatically) to improve performance on out-of-distribution (OOD) test scenarios. Specifically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08025","kind":"arxiv","version":2},"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/2301.08025/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":"2026-07-05T06:52:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DcygdQOKiyo7I5ZYnHbkFsldOVU17lJrPzg3yMdYvZ/QLcIcqHJbJxHpozaTM0qXwvnYVozbjYqGAySuQ4FDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:40:08.294490Z"},"content_sha256":"25339e906cac3e049d1344f57a4717f30d39fb2e6d03500df236319123a9eb4a","schema_version":"1.0","event_id":"sha256:25339e906cac3e049d1344f57a4717f30d39fb2e6d03500df236319123a9eb4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEOGDZJZZAS43WPKY75KNEQGOL/bundle.json","state_url":"https://pith.science/pith/JEOGDZJZZAS43WPKY75KNEQGOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEOGDZJZZAS43WPKY75KNEQGOL/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":"2026-08-09T22:40:08Z","links":{"resolver":"https://pith.science/pith/JEOGDZJZZAS43WPKY75KNEQGOL","bundle":"https://pith.science/pith/JEOGDZJZZAS43WPKY75KNEQGOL/bundle.json","state":"https://pith.science/pith/JEOGDZJZZAS43WPKY75KNEQGOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEOGDZJZZAS43WPKY75KNEQGOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JEOGDZJZZAS43WPKY75KNEQGOL","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":"9c217faecab358fd76b38d10f918aaa240a2c9104278e6e35cc8034615e3e0f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-19T11:55:47Z","title_canon_sha256":"d07eb8c9a6ab997e141bef1d34a0192e4b9ac2bc7036b13fbc2cca2c09689727"},"schema_version":"1.0","source":{"id":"2301.08025","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08025","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08025v2","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08025","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"pith_short_12","alias_value":"JEOGDZJZZAS4","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"pith_short_16","alias_value":"JEOGDZJZZAS43WPK","created_at":"2026-07-05T06:52:01Z"},{"alias_kind":"pith_short_8","alias_value":"JEOGDZJZ","created_at":"2026-07-05T06:52:01Z"}],"graph_snapshots":[{"event_id":"sha256:25339e906cac3e049d1344f57a4717f30d39fb2e6d03500df236319123a9eb4a","target":"graph","created_at":"2026-07-05T06:52:01Z","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/2301.08025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agent decision making using Reinforcement Learning (RL) heavily relies on either a model or simulator of the environment (e.g., moving in an 8x8 maze with three rooms, playing Chess on an 8x8 board). Due to this dependence, small changes in the environment (e.g., positions of obstacles in the maze, size of the board) can severely affect the effectiveness of the policy learned by the agent. To that end, existing work has proposed training RL agents on an adaptive curriculum of environments (generated automatically) to improve performance on out-of-distribution (OOD) test scenarios. Specifically","authors_text":"Dexun Li, Pradeep Varakantham, Wenjun Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-19T11:55:47Z","title":"Generalization through Diversity: Improving Unsupervised Environment Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08025","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:e4df03c9de3ffe33d298a0363a31315e0c3b0424a31f7a419b9d345eda858728","target":"record","created_at":"2026-07-05T06:52:01Z","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":"9c217faecab358fd76b38d10f918aaa240a2c9104278e6e35cc8034615e3e0f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-01-19T11:55:47Z","title_canon_sha256":"d07eb8c9a6ab997e141bef1d34a0192e4b9ac2bc7036b13fbc2cca2c09689727"},"schema_version":"1.0","source":{"id":"2301.08025","kind":"arxiv","version":2}},"canonical_sha256":"491c61e539c825cdd9eac7faa6920672f454f4a351b9448affa4db7b08343214","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"491c61e539c825cdd9eac7faa6920672f454f4a351b9448affa4db7b08343214","first_computed_at":"2026-07-05T06:52:01.926279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:01.926279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a+Xue0eMCfw7q3Sub1dfJgU/op1mjYl8tSG/2gd0PGRaJI+sxAt4RUJs3PudkvYTCVFpo1LCgCr7GnFT0KUaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:01.926732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.08025","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4df03c9de3ffe33d298a0363a31315e0c3b0424a31f7a419b9d345eda858728","sha256:25339e906cac3e049d1344f57a4717f30d39fb2e6d03500df236319123a9eb4a"],"state_sha256":"824e93f0e06e33bfa334f1fac92a34e11f13b19ea7b740e29d3b43894aef2deb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EO/Swefy9e4i5W5uII0BZqHl6J+btrQ014ft5BNsojxhslG0QJEiHHm0XhrWkA4iy0pLxaQGVnK8Dp3ESjYlDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:40:08.298290Z","bundle_sha256":"2a9e536b3f10abffe0070c499dc87abbbb0f2fdac7ba09969867ebb09b689957"}}