{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KKZLH6AMIGMUULYHJYITR5ABDV","short_pith_number":"pith:KKZLH6AM","canonical_record":{"source":{"id":"2210.03821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T21:18:22Z","cross_cats_sorted":[],"title_canon_sha256":"699c585e1358654017679f7662bd2b0e61df20043246d219dc9c36bb1b3c75c8","abstract_canon_sha256":"3e580121a31783ebebb8df47066f51d870e452ea6791ef3558cf58271a0fec5d"},"schema_version":"1.0"},"canonical_sha256":"52b2b3f80c41994a2f074e1138f4011d7a5d9c980f1c9f8505034067cd69bdc7","source":{"kind":"arxiv","id":"2210.03821","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03821","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03821v2","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03821","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"KKZLH6AMIGMU","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"pith_short_16","alias_value":"KKZLH6AMIGMUULYH","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"pith_short_8","alias_value":"KKZLH6AM","created_at":"2026-07-05T06:40:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KKZLH6AMIGMUULYHJYITR5ABDV","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T21:18:22Z","cross_cats_sorted":[],"title_canon_sha256":"699c585e1358654017679f7662bd2b0e61df20043246d219dc9c36bb1b3c75c8","abstract_canon_sha256":"3e580121a31783ebebb8df47066f51d870e452ea6791ef3558cf58271a0fec5d"},"schema_version":"1.0"},"canonical_sha256":"52b2b3f80c41994a2f074e1138f4011d7a5d9c980f1c9f8505034067cd69bdc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:29.614583Z","signature_b64":"tm05/YnWvrLK/FdWXu8+1o7LgG3zSVxjrNJc70iqc66F+ojC8dwiAbdsInpNySGZ8fUc8BNiM/RHUIRqLGZRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b2b3f80c41994a2f074e1138f4011d7a5d9c980f1c9f8505034067cd69bdc7","last_reissued_at":"2026-07-05T06:40:29.614088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:29.614088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03821","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxYDLIQQSHFO7F8CjKeYUIRvwHCIM3CeQuNp5gowode+1t97cffP0qoMaaNm0H6T/HGgiWlAvD8Jfy4cTyACDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:58:29.017412Z"},"content_sha256":"7df1f432c9e946fb84f2c3d8006acf3d32bf7c89292cace6e47870a1e015d234","schema_version":"1.0","event_id":"sha256:7df1f432c9e946fb84f2c3d8006acf3d32bf7c89292cace6e47870a1e015d234"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KKZLH6AMIGMUULYHJYITR5ABDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models can Implement Policy Iteration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ethan Brooks, Logan Walls, Richard L. Lewis, Satinder Singh","submitted_at":"2022-10-07T21:18:22Z","abstract_excerpt":"This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement Learning (RL), in-context, using foundation models. While the application of foundation models to RL has received considerable attention, most approaches rely on either (1) the curation of expert demonstrations (either through manual design or task-specific pretraining) or (2) adaptation to the task of interest using gradient methods (either fine-tuning or training of adapter layers). Both of these techniques have drawbacks. Collecting demonstrations is labor-intensive, and algorithms that rely on them do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03821","kind":"arxiv","version":2},"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/2210.03821/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OoR9Nt2y8eEvh3Fuc46bjHY55QJZOJgYyBtKqZZ5z62oq4bcIdh52A3Bgd4H7/pCrifirm991PJW4StumNGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:58:29.017807Z"},"content_sha256":"98b8eb14b022b186233916a000f336b49bb6ab220cf69fc5474591af9ab8e839","schema_version":"1.0","event_id":"sha256:98b8eb14b022b186233916a000f336b49bb6ab220cf69fc5474591af9ab8e839"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKZLH6AMIGMUULYHJYITR5ABDV/bundle.json","state_url":"https://pith.science/pith/KKZLH6AMIGMUULYHJYITR5ABDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKZLH6AMIGMUULYHJYITR5ABDV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T09:58:29Z","links":{"resolver":"https://pith.science/pith/KKZLH6AMIGMUULYHJYITR5ABDV","bundle":"https://pith.science/pith/KKZLH6AMIGMUULYHJYITR5ABDV/bundle.json","state":"https://pith.science/pith/KKZLH6AMIGMUULYHJYITR5ABDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKZLH6AMIGMUULYHJYITR5ABDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KKZLH6AMIGMUULYHJYITR5ABDV","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":"3e580121a31783ebebb8df47066f51d870e452ea6791ef3558cf58271a0fec5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T21:18:22Z","title_canon_sha256":"699c585e1358654017679f7662bd2b0e61df20043246d219dc9c36bb1b3c75c8"},"schema_version":"1.0","source":{"id":"2210.03821","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03821","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03821v2","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03821","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"KKZLH6AMIGMU","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"pith_short_16","alias_value":"KKZLH6AMIGMUULYH","created_at":"2026-07-05T06:40:29Z"},{"alias_kind":"pith_short_8","alias_value":"KKZLH6AM","created_at":"2026-07-05T06:40:29Z"}],"graph_snapshots":[{"event_id":"sha256:98b8eb14b022b186233916a000f336b49bb6ab220cf69fc5474591af9ab8e839","target":"graph","created_at":"2026-07-05T06:40:29Z","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/2210.03821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement Learning (RL), in-context, using foundation models. While the application of foundation models to RL has received considerable attention, most approaches rely on either (1) the curation of expert demonstrations (either through manual design or task-specific pretraining) or (2) adaptation to the task of interest using gradient methods (either fine-tuning or training of adapter layers). Both of these techniques have drawbacks. Collecting demonstrations is labor-intensive, and algorithms that rely on them do","authors_text":"Ethan Brooks, Logan Walls, Richard L. Lewis, Satinder Singh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T21:18:22Z","title":"Large Language Models can Implement Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03821","kind":"arxiv","version":2},"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":"sha256:7df1f432c9e946fb84f2c3d8006acf3d32bf7c89292cace6e47870a1e015d234","target":"record","created_at":"2026-07-05T06:40:29Z","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":"3e580121a31783ebebb8df47066f51d870e452ea6791ef3558cf58271a0fec5d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T21:18:22Z","title_canon_sha256":"699c585e1358654017679f7662bd2b0e61df20043246d219dc9c36bb1b3c75c8"},"schema_version":"1.0","source":{"id":"2210.03821","kind":"arxiv","version":2}},"canonical_sha256":"52b2b3f80c41994a2f074e1138f4011d7a5d9c980f1c9f8505034067cd69bdc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52b2b3f80c41994a2f074e1138f4011d7a5d9c980f1c9f8505034067cd69bdc7","first_computed_at":"2026-07-05T06:40:29.614088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:29.614088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tm05/YnWvrLK/FdWXu8+1o7LgG3zSVxjrNJc70iqc66F+ojC8dwiAbdsInpNySGZ8fUc8BNiM/RHUIRqLGZRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:29.614583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03821","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7df1f432c9e946fb84f2c3d8006acf3d32bf7c89292cace6e47870a1e015d234","sha256:98b8eb14b022b186233916a000f336b49bb6ab220cf69fc5474591af9ab8e839"],"state_sha256":"e7b0b2473ce2d616ae2b0ffa2a0297e9efbe9d91db5b937ba319e2d511809838"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTf9d3OcPyOGkwrCs1VyLAVjgrRWSjwByWpDuGYiWM/jATEO+MI2VY13aCyi7wizXzVpLRHvwzUViDbZaPjEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:58:29.021900Z","bundle_sha256":"0e9a4500380b21e7a58ab237ade9757e7b86bfecb0fb158fa433153cb87bf347"}}