{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XJGZMNSHNVUSG35PPUAO2JUYIU","short_pith_number":"pith:XJGZMNSH","canonical_record":{"source":{"id":"2505.10330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-15T14:19:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"428df0ff13960eac5b207a8a9962100427878aa585ef9b9686d1aa7797a4a2d0","abstract_canon_sha256":"2240c063a21887686c9d6e8306cb2d66a6bff833f8a601cc0da1bd8a0bfcd417"},"schema_version":"1.0"},"canonical_sha256":"ba4d9636476d69236faf7d00ed2698453c75d34db23bcb60260bf292e6799e12","source":{"kind":"arxiv","id":"2505.10330","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10330","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10330v1","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10330","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"XJGZMNSHNVUS","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"XJGZMNSHNVUSG35P","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"XJGZMNSH","created_at":"2026-07-05T11:03:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XJGZMNSHNVUSG35PPUAO2JUYIU","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-15T14:19:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"428df0ff13960eac5b207a8a9962100427878aa585ef9b9686d1aa7797a4a2d0","abstract_canon_sha256":"2240c063a21887686c9d6e8306cb2d66a6bff833f8a601cc0da1bd8a0bfcd417"},"schema_version":"1.0"},"canonical_sha256":"ba4d9636476d69236faf7d00ed2698453c75d34db23bcb60260bf292e6799e12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:37.022999Z","signature_b64":"BbV6Uo+MwOrY/VeE1fu3elr7SFmjy01DwR74+iFtHhgtHrHCGIqp/21BntoQnnsij5Yt9qUkyVj5mWYBWuwMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba4d9636476d69236faf7d00ed2698453c75d34db23bcb60260bf292e6799e12","last_reissued_at":"2026-07-05T11:03:37.022537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:37.022537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10330","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":"2026-07-05T11:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GyYsmcPHSgKbo8RguzfqvTksxXikwgRYcZDdCbCC2B7H1HZz7HbzvSe2sKEZ00pl+5t5sMkjmy6GM4SamaF1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:59:49.583359Z"},"content_sha256":"0fa473c3aeb3597dd0c7989e31194bf1038ed280385b3639188c06a071b49b14","schema_version":"1.0","event_id":"sha256:0fa473c3aeb3597dd0c7989e31194bf1038ed280385b3639188c06a071b49b14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XJGZMNSHNVUSG35PPUAO2JUYIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Adaptation of Reinforcement Learning Agents to Sudden Environmental Change","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jonathan Clifford Balloch","submitted_at":"2025-05-15T14:19:01Z","abstract_excerpt":"Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in stationary environments, most methods are data intensive and assume a world that does not change between training and test time. As a result, conventional RL methods struggle to adapt when conditions change. This poses a fundamental challenge: how can RL agents efficiently adapt their behavior when encountering novel environmental changes during deployment wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10330","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/2505.10330/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":"2026-07-05T11:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Db/ga32CLzQRdUq6F8ikexNVj0G5bXx5u7LxcVY7nX71sDMhGrjPy/JoaPjP5GaaFTjfgKjAOxlY4p8OqbOGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:59:49.584327Z"},"content_sha256":"f73db959189c2ce29f5bb680fa4c90e941a6cc5eaf8b789bd0b573f6960c5a37","schema_version":"1.0","event_id":"sha256:f73db959189c2ce29f5bb680fa4c90e941a6cc5eaf8b789bd0b573f6960c5a37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJGZMNSHNVUSG35PPUAO2JUYIU/bundle.json","state_url":"https://pith.science/pith/XJGZMNSHNVUSG35PPUAO2JUYIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJGZMNSHNVUSG35PPUAO2JUYIU/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":"2026-08-17T21:59:49Z","links":{"resolver":"https://pith.science/pith/XJGZMNSHNVUSG35PPUAO2JUYIU","bundle":"https://pith.science/pith/XJGZMNSHNVUSG35PPUAO2JUYIU/bundle.json","state":"https://pith.science/pith/XJGZMNSHNVUSG35PPUAO2JUYIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJGZMNSHNVUSG35PPUAO2JUYIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XJGZMNSHNVUSG35PPUAO2JUYIU","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":"2240c063a21887686c9d6e8306cb2d66a6bff833f8a601cc0da1bd8a0bfcd417","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-15T14:19:01Z","title_canon_sha256":"428df0ff13960eac5b207a8a9962100427878aa585ef9b9686d1aa7797a4a2d0"},"schema_version":"1.0","source":{"id":"2505.10330","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10330","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10330v1","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10330","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"XJGZMNSHNVUS","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"XJGZMNSHNVUSG35P","created_at":"2026-07-05T11:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"XJGZMNSH","created_at":"2026-07-05T11:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:f73db959189c2ce29f5bb680fa4c90e941a6cc5eaf8b789bd0b573f6960c5a37","target":"graph","created_at":"2026-07-05T11:03:37Z","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/2505.10330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in stationary environments, most methods are data intensive and assume a world that does not change between training and test time. As a result, conventional RL methods struggle to adapt when conditions change. This poses a fundamental challenge: how can RL agents efficiently adapt their behavior when encountering novel environmental changes during deployment wit","authors_text":"Jonathan Clifford Balloch","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-15T14:19:01Z","title":"Efficient Adaptation of Reinforcement Learning Agents to Sudden Environmental Change"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10330","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":"sha256:0fa473c3aeb3597dd0c7989e31194bf1038ed280385b3639188c06a071b49b14","target":"record","created_at":"2026-07-05T11:03:37Z","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":"2240c063a21887686c9d6e8306cb2d66a6bff833f8a601cc0da1bd8a0bfcd417","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-15T14:19:01Z","title_canon_sha256":"428df0ff13960eac5b207a8a9962100427878aa585ef9b9686d1aa7797a4a2d0"},"schema_version":"1.0","source":{"id":"2505.10330","kind":"arxiv","version":1}},"canonical_sha256":"ba4d9636476d69236faf7d00ed2698453c75d34db23bcb60260bf292e6799e12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba4d9636476d69236faf7d00ed2698453c75d34db23bcb60260bf292e6799e12","first_computed_at":"2026-07-05T11:03:37.022537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:37.022537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BbV6Uo+MwOrY/VeE1fu3elr7SFmjy01DwR74+iFtHhgtHrHCGIqp/21BntoQnnsij5Yt9qUkyVj5mWYBWuwMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:37.022999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10330","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fa473c3aeb3597dd0c7989e31194bf1038ed280385b3639188c06a071b49b14","sha256:f73db959189c2ce29f5bb680fa4c90e941a6cc5eaf8b789bd0b573f6960c5a37"],"state_sha256":"5b73365f35659dc0c255e7e4103440c85a8524b7a8a89838506190280b247ac5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmxeVSn2qK0rP8mIxm9VbdaNPLkzmBXDHPIIZKOq3hcDWE0GT3xSGOpNSgYj2d2F1RuezEyU9qjPCrYYz8ARCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:59:49.591748Z","bundle_sha256":"e9369dd4ab0d19196604b41c864d2f72e253d97531be4558876b28e7091c391a"}}