{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NPLNJJLSEF7SXWTUYD54X5ZXFF","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":"0f7f8eb5360a136bb17ae0151205088a38bf1dabc63919bc7153c5aeb76b24fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T17:57:49Z","title_canon_sha256":"e8511c400467c7c35dcc8495c9d073da266e30f69e495dc855a0c82b9a5a4ee4"},"schema_version":"1.0","source":{"id":"2210.14215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14215","created_at":"2026-07-05T05:10:27Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14215v1","created_at":"2026-07-05T05:10:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14215","created_at":"2026-07-05T05:10:27Z"},{"alias_kind":"pith_short_12","alias_value":"NPLNJJLSEF7S","created_at":"2026-07-05T05:10:27Z"},{"alias_kind":"pith_short_16","alias_value":"NPLNJJLSEF7SXWTU","created_at":"2026-07-05T05:10:27Z"},{"alias_kind":"pith_short_8","alias_value":"NPLNJJLS","created_at":"2026-07-05T05:10:27Z"}],"graph_snapshots":[{"event_id":"sha256:1231eeac700cb54f2760850d00beaf23c0d6248ee707c4eac5e14fa019059844","target":"graph","created_at":"2026-07-05T05:10:27Z","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/2210.14215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to reinforcement learn as an across-episode sequential prediction problem. A dataset of learning histories is generated by a source RL algorithm, and then a causal transformer is trained by autoregressively predicting actions given their preceding learning histories as context. Unlike sequential policy prediction architectures that distill post-learning or expert sequ","authors_text":"Angelos Filos, DJ Strouse, Emilio Parisotto, Ethan Brooks, Himanshu Sahni, Junhyuk Oh, Luyu Wang, Maxime Gazeau, Michael Laskin, Richie Steigerwald, Satinder Singh, Stephen Spencer, Steven Hansen, Volodymyr Mnih","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T17:57:49Z","title":"In-context Reinforcement Learning with Algorithm Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14215","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":"sha256:34852e932cea1208f18d738c5dfa930e4d8fd0823c7e36c64d2ed46ffa4d4d2a","target":"record","created_at":"2026-07-05T05:10:27Z","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":"0f7f8eb5360a136bb17ae0151205088a38bf1dabc63919bc7153c5aeb76b24fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-25T17:57:49Z","title_canon_sha256":"e8511c400467c7c35dcc8495c9d073da266e30f69e495dc855a0c82b9a5a4ee4"},"schema_version":"1.0","source":{"id":"2210.14215","kind":"arxiv","version":1}},"canonical_sha256":"6bd6d4a572217f2bda74c0fbcbf737295077a0a2fa751dfd67be81189995a040","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bd6d4a572217f2bda74c0fbcbf737295077a0a2fa751dfd67be81189995a040","first_computed_at":"2026-07-05T05:10:27.534150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:27.534150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bml2Pjf/6zyUf+S08EYvqucSHyTYeHjNfm7ioliKJkw5m3FIkKtWi014Nec5NbUcFILXjgdzTFJkCftzorzOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:27.534646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34852e932cea1208f18d738c5dfa930e4d8fd0823c7e36c64d2ed46ffa4d4d2a","sha256:1231eeac700cb54f2760850d00beaf23c0d6248ee707c4eac5e14fa019059844"],"state_sha256":"61f344ae5ec90c8e4a03be24a60ab087d5ba46d9d6e8af2abd770a39c7fbe924"}