{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JWAFCZSEBMIFUW4Y7ZS3ZH6TST","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":"94139ee34686e8d902b4a5cb462ed76d14efbd4b269ed8c4f446b0d510e29a43","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-26T17:58:50Z","title_canon_sha256":"df8f95ad9314113c76fe26118132ac6668422e6dec9863d8f3e774e11251d310"},"schema_version":"1.0","source":{"id":"2306.14892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14892","created_at":"2026-07-05T06:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14892v1","created_at":"2026-07-05T06:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14892","created_at":"2026-07-05T06:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"JWAFCZSEBMIF","created_at":"2026-07-05T06:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"JWAFCZSEBMIFUW4Y","created_at":"2026-07-05T06:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"JWAFCZSE","created_at":"2026-07-05T06:24:41Z"}],"graph_snapshots":[{"event_id":"sha256:d324492d16d535d4e4b903fb1d17c7343743537bd95c28fec95b38e9043fb9dd","target":"graph","created_at":"2026-07-05T06:24:41Z","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/2306.14892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large transformer models trained on diverse datasets have shown a remarkable ability to learn in-context, achieving high few-shot performance on tasks they were not explicitly trained to solve. In this paper, we study the in-context learning capabilities of transformers in decision-making problems, i.e., reinforcement learning (RL) for bandits and Markov decision processes. To do so, we introduce and study Decision-Pretrained Transformer (DPT), a supervised pretraining method where the transformer predicts an optimal action given a query state and an in-context dataset of interactions, across ","authors_text":"Aldo Pacchiano, Annie Xie, Chelsea Finn, Emma Brunskill, Jonathan N. Lee, Ofir Nachum, Yash Chandak","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-26T17:58:50Z","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14892","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:d97a90909ae0e29eca38928aed38e974f02099d5e11bf9354fae62f3741e51c9","target":"record","created_at":"2026-07-05T06:24:41Z","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":"94139ee34686e8d902b4a5cb462ed76d14efbd4b269ed8c4f446b0d510e29a43","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-26T17:58:50Z","title_canon_sha256":"df8f95ad9314113c76fe26118132ac6668422e6dec9863d8f3e774e11251d310"},"schema_version":"1.0","source":{"id":"2306.14892","kind":"arxiv","version":1}},"canonical_sha256":"4d805166440b105a5b98fe65bc9fd394e67abe32b6284c7eeb1a9f26a04d6feb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d805166440b105a5b98fe65bc9fd394e67abe32b6284c7eeb1a9f26a04d6feb","first_computed_at":"2026-07-05T06:24:41.809294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:41.809294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mc+cNPDxVn8xayBfv2Vw3XVuLzWkp8FYTZHYIIX1mSUOGZSAvSy5EFwM+Vv60QHR5vckcVLYt06wT/+UgSEgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:41.809670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d97a90909ae0e29eca38928aed38e974f02099d5e11bf9354fae62f3741e51c9","sha256:d324492d16d535d4e4b903fb1d17c7343743537bd95c28fec95b38e9043fb9dd"],"state_sha256":"6c4ea80098c6dbc3a47d71141d9a86ad9779accd3856a4435db00c62eeca346f"}