{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CVIQCQIYEB32HWCJXMQ6S54DXU","short_pith_number":"pith:CVIQCQIY","canonical_record":{"source":{"id":"2502.07978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T21:52:19Z","cross_cats_sorted":[],"title_canon_sha256":"73066347c6132f9a45b82ce6050c8c91b42ea9ad283f466a3c7a7be099e70ffd","abstract_canon_sha256":"9065d3049b3c70dad84f3209613e490534de89dda2f46bdf9492d97cea0e4c57"},"schema_version":"1.0"},"canonical_sha256":"15510141182077a3d849bb21e97783bd1ebb4b45b6318dd141c52b53c9484ef3","source":{"kind":"arxiv","id":"2502.07978","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07978","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07978v1","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07978","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"CVIQCQIYEB32","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"CVIQCQIYEB32HWCJ","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"CVIQCQIY","created_at":"2026-07-05T10:13:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CVIQCQIYEB32HWCJXMQ6S54DXU","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T21:52:19Z","cross_cats_sorted":[],"title_canon_sha256":"73066347c6132f9a45b82ce6050c8c91b42ea9ad283f466a3c7a7be099e70ffd","abstract_canon_sha256":"9065d3049b3c70dad84f3209613e490534de89dda2f46bdf9492d97cea0e4c57"},"schema_version":"1.0"},"canonical_sha256":"15510141182077a3d849bb21e97783bd1ebb4b45b6318dd141c52b53c9484ef3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:13.093300Z","signature_b64":"qEZdnU01/9c+o8iBmhzq8VRWnxFkDQJgghTGbSIw5adBIrOm6cpxUJW3nwSEnaxLGxPT7Y/JVGJkS+/O+wRwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15510141182077a3d849bb21e97783bd1ebb4b45b6318dd141c52b53c9484ef3","last_reissued_at":"2026-07-05T10:13:13.092805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:13.092805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07978","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Az/o7AICh2Y9mv9i5Pf5f/6/+amCc4l2O6blfy3ZSyojr30s2eVfSh/6xnKtenRHsV2LQlXXm+Qdll7RzlArAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:43:59.395927Z"},"content_sha256":"3b422928af5c43a4f916691b9dc241c55b2515f0d4c8dd713b4646caff734b7f","schema_version":"1.0","event_id":"sha256:3b422928af5c43a4f916691b9dc241c55b2515f0d4c8dd713b4646caff734b7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CVIQCQIYEB32HWCJXMQ6S54DXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of In-Context Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Moeini, Ethan Blaser, Jacob Beck, Jiuqi Wang, Rohan Chandra, Shangtong Zhang, Shimon Whiteson","submitted_at":"2025-02-11T21:52:19Z","abstract_excerpt":"Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning on additional context such as their action-observation histories. This paper surveys work on such behavior, known as in-context reinforcement learning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07978","kind":"arxiv","version":1},"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/2502.07978/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":"2026-07-05T10:13:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oME8r0Hw0UmyfwdF3yyqURz9CY7jYaZ2AgFJelH42KN+IZqemjDuqiVDZjmlYsj4ro7FVUc0ZEbnIv+iApgxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:43:59.396735Z"},"content_sha256":"f8a4f8fece8c4555e928c0c3d2f48f25d02151c4670150928b3e1d381c1a6c58","schema_version":"1.0","event_id":"sha256:f8a4f8fece8c4555e928c0c3d2f48f25d02151c4670150928b3e1d381c1a6c58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CVIQCQIYEB32HWCJXMQ6S54DXU/bundle.json","state_url":"https://pith.science/pith/CVIQCQIYEB32HWCJXMQ6S54DXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CVIQCQIYEB32HWCJXMQ6S54DXU/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":"2026-08-07T08:43:59Z","links":{"resolver":"https://pith.science/pith/CVIQCQIYEB32HWCJXMQ6S54DXU","bundle":"https://pith.science/pith/CVIQCQIYEB32HWCJXMQ6S54DXU/bundle.json","state":"https://pith.science/pith/CVIQCQIYEB32HWCJXMQ6S54DXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CVIQCQIYEB32HWCJXMQ6S54DXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CVIQCQIYEB32HWCJXMQ6S54DXU","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":"9065d3049b3c70dad84f3209613e490534de89dda2f46bdf9492d97cea0e4c57","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T21:52:19Z","title_canon_sha256":"73066347c6132f9a45b82ce6050c8c91b42ea9ad283f466a3c7a7be099e70ffd"},"schema_version":"1.0","source":{"id":"2502.07978","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07978","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07978v1","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07978","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"pith_short_12","alias_value":"CVIQCQIYEB32","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"pith_short_16","alias_value":"CVIQCQIYEB32HWCJ","created_at":"2026-07-05T10:13:13Z"},{"alias_kind":"pith_short_8","alias_value":"CVIQCQIY","created_at":"2026-07-05T10:13:13Z"}],"graph_snapshots":[{"event_id":"sha256:f8a4f8fece8c4555e928c0c3d2f48f25d02151c4670150928b3e1d381c1a6c58","target":"graph","created_at":"2026-07-05T10:13:13Z","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/2502.07978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by simply conditioning on additional context such as their action-observation histories. This paper surveys work on such behavior, known as in-context reinforcement learning.","authors_text":"Amir Moeini, Ethan Blaser, Jacob Beck, Jiuqi Wang, Rohan Chandra, Shangtong Zhang, Shimon Whiteson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T21:52:19Z","title":"A Survey of In-Context Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07978","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":"sha256:3b422928af5c43a4f916691b9dc241c55b2515f0d4c8dd713b4646caff734b7f","target":"record","created_at":"2026-07-05T10:13:13Z","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":"9065d3049b3c70dad84f3209613e490534de89dda2f46bdf9492d97cea0e4c57","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T21:52:19Z","title_canon_sha256":"73066347c6132f9a45b82ce6050c8c91b42ea9ad283f466a3c7a7be099e70ffd"},"schema_version":"1.0","source":{"id":"2502.07978","kind":"arxiv","version":1}},"canonical_sha256":"15510141182077a3d849bb21e97783bd1ebb4b45b6318dd141c52b53c9484ef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15510141182077a3d849bb21e97783bd1ebb4b45b6318dd141c52b53c9484ef3","first_computed_at":"2026-07-05T10:13:13.092805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:13.092805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qEZdnU01/9c+o8iBmhzq8VRWnxFkDQJgghTGbSIw5adBIrOm6cpxUJW3nwSEnaxLGxPT7Y/JVGJkS+/O+wRwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:13.093300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07978","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b422928af5c43a4f916691b9dc241c55b2515f0d4c8dd713b4646caff734b7f","sha256:f8a4f8fece8c4555e928c0c3d2f48f25d02151c4670150928b3e1d381c1a6c58"],"state_sha256":"d81d5ddb102502036b62a6b5c93553b13f2710c7919378c28c3f60bcb63494fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOhmlZ+Qi1ZrJIdtJ1n9hqbVA5M7xySN1BVb0awfIvLkbXDPY18PHBWyiPqFwmWMbRYljdGYebU+Qu9dwcauCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:43:59.402389Z","bundle_sha256":"4870c04650f3a66f48ba630e5de275c2fbce6ef2e6760d83f8280b77b3f01227"}}