{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NMPZT3KRJW3G3K3AODQ37R276C","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":"a0a60cc353bfb7952ed5ab16cfb0f95377ddf728c9b9b5cdb70d96485cc00112","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T22:25:40Z","title_canon_sha256":"8f077477958f93b5acb5bf23ba2a8331f5dea18d1d581c75159734afc1476eb2"},"schema_version":"1.0","source":{"id":"2411.11188","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11188","created_at":"2026-07-05T09:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11188v1","created_at":"2026-07-05T09:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11188","created_at":"2026-07-05T09:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"NMPZT3KRJW3G","created_at":"2026-07-05T09:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"NMPZT3KRJW3G3K3A","created_at":"2026-07-05T09:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"NMPZT3KR","created_at":"2026-07-05T09:36:52Z"}],"graph_snapshots":[{"event_id":"sha256:605c2eee76781aded25daac7b70b4bb01182b7b5d46d49e482792769342af217","target":"graph","created_at":"2026-07-05T09:36:52Z","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/2411.11188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models trained on diverse datasets unlock generalization by in-context learning. Reinforcement Learning (RL) policies can achieve a similar effect by meta-learning within the memory of a sequence model. However, meta-RL research primarily focuses on adapting to minor variations of a single task. It is difficult to scale towards more general behavior without confronting challenges in multi-task optimization, and few solutions are compatible with meta-RL's goal of learning from large training sets of unlabeled tasks. To address this challenge, we revisit the idea that multi-task RL is b","authors_text":"Amy Zhang, Daniel Adebi, Jake Grigsby, Justin Sasek, Samyak Parajuli, Yuke Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T22:25:40Z","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11188","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":"sha256:92979d89d121b768d334a1d2f7c4ff07a3307ef62417fb90a73c2d407b5e5f82","target":"record","created_at":"2026-07-05T09:36:52Z","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":"a0a60cc353bfb7952ed5ab16cfb0f95377ddf728c9b9b5cdb70d96485cc00112","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-17T22:25:40Z","title_canon_sha256":"8f077477958f93b5acb5bf23ba2a8331f5dea18d1d581c75159734afc1476eb2"},"schema_version":"1.0","source":{"id":"2411.11188","kind":"arxiv","version":1}},"canonical_sha256":"6b1f99ed514db66dab6070e1bfc75ff09a99f158412806a1ce8e4032c49654ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b1f99ed514db66dab6070e1bfc75ff09a99f158412806a1ce8e4032c49654ff","first_computed_at":"2026-07-05T09:36:52.739038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:52.739038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAFMIq2tIaLMLjxoGtI8BpV433FIUcACHN4lWwlwmd8V89OwEIWp/tv0P5pL1I+kqAsFvWOGTLEQEPX/iS0vAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:52.739522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11188","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92979d89d121b768d334a1d2f7c4ff07a3307ef62417fb90a73c2d407b5e5f82","sha256:605c2eee76781aded25daac7b70b4bb01182b7b5d46d49e482792769342af217"],"state_sha256":"ba6eba1948f75fe8188db657375da06d21929fd22e4e9d8c37c4bcc5869615b3"}