{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GMXDK37AWBZDGRE75TENHB7FAQ","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":"3d047492160e8c8ca797d2680128ce4ef3d2ebc3b44bae13591332213dbd8e41","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T13:40:11Z","title_canon_sha256":"5d2d1f7907d639651dd29c323e92bc2eb4241d4a07cfb57dc0ed3d9906b16b29"},"schema_version":"1.0","source":{"id":"2402.06402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06402","created_at":"2026-07-05T07:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06402v1","created_at":"2026-07-05T07:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06402","created_at":"2026-07-05T07:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"GMXDK37AWBZD","created_at":"2026-07-05T07:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"GMXDK37AWBZDGRE7","created_at":"2026-07-05T07:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"GMXDK37A","created_at":"2026-07-05T07:43:23Z"}],"graph_snapshots":[{"event_id":"sha256:59d8cb873f29ba4357cd3f2bce3b862ee43347b8d8b7e9b7f1fb7182d633c299","target":"graph","created_at":"2026-07-05T07:43:23Z","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/2402.06402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Hierarchical Transformers for Meta-Reinforcement Learning (HTrMRL), a powerful online meta-reinforcement learning approach. HTrMRL aims to address the challenge of enabling reinforcement learning agents to perform effectively in previously unseen tasks. We demonstrate how past episodes serve as a rich source of information, which our model effectively distills and applies to new contexts. Our learned algorithm is capable of outperforming the previous state-of-the-art and provides more efficient meta-training while significantly improving generalization capabilities. Experimental r","authors_text":"Andr\\'e Biedenkapp, Gresa Shala, Josif Grabocka","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T13:40:11Z","title":"Hierarchical Transformers are Efficient Meta-Reinforcement Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06402","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:e7e4ced21050bcf621fdeb3f4ad38f3ca42c2e6c25c8e1562df3b84bc6c11b2e","target":"record","created_at":"2026-07-05T07:43:23Z","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":"3d047492160e8c8ca797d2680128ce4ef3d2ebc3b44bae13591332213dbd8e41","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-09T13:40:11Z","title_canon_sha256":"5d2d1f7907d639651dd29c323e92bc2eb4241d4a07cfb57dc0ed3d9906b16b29"},"schema_version":"1.0","source":{"id":"2402.06402","kind":"arxiv","version":1}},"canonical_sha256":"332e356fe0b07233449fecc8d387e5042b833753e84c3de51719ddd9b744adae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"332e356fe0b07233449fecc8d387e5042b833753e84c3de51719ddd9b744adae","first_computed_at":"2026-07-05T07:43:23.737754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:23.737754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z4lGiEZYN1Ff/qdelq9T4KzP670ci5vPam3Ik0w0JLglt9QtZK5EbSCh9c/xKaf+7Z0XGOfoklGkDNro4JVwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:23.738164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7e4ced21050bcf621fdeb3f4ad38f3ca42c2e6c25c8e1562df3b84bc6c11b2e","sha256:59d8cb873f29ba4357cd3f2bce3b862ee43347b8d8b7e9b7f1fb7182d633c299"],"state_sha256":"cfae628130403a5eb12e41ffed1fe8187d014d1ab4ee008b428f03f9d2b81b1e"}