{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZRFU35NKLQK7QSV3XEY5VWM5AY","short_pith_number":"pith:ZRFU35NK","schema_version":"1.0","canonical_sha256":"cc4b4df5aa5c15f84abbb931dad99d060547962c9c831257267a1ade1ee5390b","source":{"kind":"arxiv","id":"2203.07454","version":1},"attestation_state":"computed","paper":{"title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander New, Blake Schreurs, Chace Ashcraft, Chigozie S. Ewulum, Eric Q. Nguyen, Erik C. Johnson, Gautam K. Vallabha, Megan M. Baker, Neil M. Fendley","submitted_at":"2022-03-14T19:20:26Z","abstract_excerpt":"Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolving, open-world problems often found in critical application spaces. Reinforcement learning solutions tend to generalize poorly when exposed to new tasks outside of the data distribution they are trained on, prompting an interest in continual learning algorithms. In tandem with research on continual learning algorithms, there is a need for challenge environments, carefully designed experiments, and metrics to assess "},"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":"2203.07454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-14T19:20:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"42a2152bd0441094c59d1d95ad94528b821d5e9488a35c79c63adb50bbbac7ce","abstract_canon_sha256":"b5f8513d38ddd5f52e6c5148fde9dac9127b5712d79fe1cf0a60c74c7651003f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:18.555466Z","signature_b64":"g07Zmq+c5zP9zt6Zl9RywNALNthzcLiqUGRg2QHl+4/H/ajwEZN+Z+t0PjFL2msniN+elcjk6n8051O+GwuxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc4b4df5aa5c15f84abbb931dad99d060547962c9c831257267a1ade1ee5390b","last_reissued_at":"2026-07-05T04:05:18.554995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:18.554995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L2Explorer: A Lifelong Reinforcement Learning Assessment Environment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander New, Blake Schreurs, Chace Ashcraft, Chigozie S. Ewulum, Eric Q. Nguyen, Erik C. Johnson, Gautam K. Vallabha, Megan M. Baker, Neil M. Fendley","submitted_at":"2022-03-14T19:20:26Z","abstract_excerpt":"Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolving, open-world problems often found in critical application spaces. Reinforcement learning solutions tend to generalize poorly when exposed to new tasks outside of the data distribution they are trained on, prompting an interest in continual learning algorithms. In tandem with research on continual learning algorithms, there is a need for challenge environments, carefully designed experiments, and metrics to assess "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07454","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/2203.07454/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":"2203.07454","created_at":"2026-07-05T04:05:18.555059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07454v1","created_at":"2026-07-05T04:05:18.555059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07454","created_at":"2026-07-05T04:05:18.555059+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRFU35NKLQK7","created_at":"2026-07-05T04:05:18.555059+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRFU35NKLQK7QSV3","created_at":"2026-07-05T04:05:18.555059+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRFU35NK","created_at":"2026-07-05T04:05:18.555059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.21872","citing_title":"A Survey of Continual Reinforcement Learning","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY","json":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY.json","graph_json":"https://pith.science/api/pith-number/ZRFU35NKLQK7QSV3XEY5VWM5AY/graph.json","events_json":"https://pith.science/api/pith-number/ZRFU35NKLQK7QSV3XEY5VWM5AY/events.json","paper":"https://pith.science/paper/ZRFU35NK"},"agent_actions":{"view_html":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY","download_json":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY.json","view_paper":"https://pith.science/paper/ZRFU35NK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07454&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRFU35NKLQK7QSV3XEY5VWM5AY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRFU35NKLQK7QSV3XEY5VWM5AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY/action/storage_attestation","attest_author":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY/action/author_attestation","sign_citation":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY/action/citation_signature","submit_replication":"https://pith.science/pith/ZRFU35NKLQK7QSV3XEY5VWM5AY/action/replication_record"}},"created_at":"2026-07-05T04:05:18.555059+00:00","updated_at":"2026-07-05T04:05:18.555059+00:00"}