{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:J2J5BGQ4TZV7LZ5SDCC4JEUFAM","short_pith_number":"pith:J2J5BGQ4","canonical_record":{"source":{"id":"2212.10876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-21T09:38:18Z","cross_cats_sorted":[],"title_canon_sha256":"4b4e5a19c0231676ad07b1e6667c1161942f621a0217e261d4a43345007d8228","abstract_canon_sha256":"6ca4d4a9af11ea341edfbde19c8f7b7bb4a2d70cffb3d7b4350669843a74319d"},"schema_version":"1.0"},"canonical_sha256":"4e93d09a1c9e6bf5e7b21885c49285031884ce0037f5724010ed6f5cdc52e9e7","source":{"kind":"arxiv","id":"2212.10876","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10876","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10876v1","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10876","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"J2J5BGQ4TZV7","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"J2J5BGQ4TZV7LZ5S","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"J2J5BGQ4","created_at":"2026-07-05T05:27:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:J2J5BGQ4TZV7LZ5SDCC4JEUFAM","target":"record","payload":{"canonical_record":{"source":{"id":"2212.10876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-21T09:38:18Z","cross_cats_sorted":[],"title_canon_sha256":"4b4e5a19c0231676ad07b1e6667c1161942f621a0217e261d4a43345007d8228","abstract_canon_sha256":"6ca4d4a9af11ea341edfbde19c8f7b7bb4a2d70cffb3d7b4350669843a74319d"},"schema_version":"1.0"},"canonical_sha256":"4e93d09a1c9e6bf5e7b21885c49285031884ce0037f5724010ed6f5cdc52e9e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:23.889027Z","signature_b64":"Naapb7NMDVS27H8PRqPIymuwOtKdH4l0Ep5hJkH1Z0PCiP25VaKfCH3TxOysMUwlSD+KMoMJwuWQCEWJj512CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e93d09a1c9e6bf5e7b21885c49285031884ce0037f5724010ed6f5cdc52e9e7","last_reissued_at":"2026-07-05T05:27:23.888605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:23.888605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.10876","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":"2026-07-05T05:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/gDt8l5KaRM1pdvXGoBOiFmp7IFibG4vbQTMGHLY3UEkNcWLqamKKcMQ3cDOAfoZv6D7Ak3A1Uwd+8GskvANAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:51:15.101303Z"},"content_sha256":"39e2f392a96b8e0d0f66e93c6e00852697bdd8000c980e4340325c8622bc5774","schema_version":"1.0","event_id":"sha256:39e2f392a96b8e0d0f66e93c6e00852697bdd8000c980e4340325c8622bc5774"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:J2J5BGQ4TZV7LZ5SDCC4JEUFAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyperparameters in Contextual RL are Highly Situational","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carolin Benjamins, Marius Lindauer, Theresa Eimer","submitted_at":"2022-12-21T09:38:18Z","abstract_excerpt":"Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparameters found by automatic hyperparameter optimization (HPO) methods are not only dependent on the problem at hand, but even on how well the state describes the environment dynamics. Specifically, we show that agents in contextual RL require different hyperparameters if they are shown how environmental"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10876","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/2212.10876/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":"2026-07-05T05:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fdcyRXQB4o3lAVNWFRLk8JW7r4MEBian+y5t+981/GdflL0PXf9PREBMZMCP6qYP+E31NdGu74BBSG8CbJWmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:51:15.102017Z"},"content_sha256":"26ba564069b49e71c3a18dc8f624077f8e62aeb0a98e38c2173da2326757e4e1","schema_version":"1.0","event_id":"sha256:26ba564069b49e71c3a18dc8f624077f8e62aeb0a98e38c2173da2326757e4e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2J5BGQ4TZV7LZ5SDCC4JEUFAM/bundle.json","state_url":"https://pith.science/pith/J2J5BGQ4TZV7LZ5SDCC4JEUFAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2J5BGQ4TZV7LZ5SDCC4JEUFAM/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":"2026-08-03T15:51:15Z","links":{"resolver":"https://pith.science/pith/J2J5BGQ4TZV7LZ5SDCC4JEUFAM","bundle":"https://pith.science/pith/J2J5BGQ4TZV7LZ5SDCC4JEUFAM/bundle.json","state":"https://pith.science/pith/J2J5BGQ4TZV7LZ5SDCC4JEUFAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2J5BGQ4TZV7LZ5SDCC4JEUFAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J2J5BGQ4TZV7LZ5SDCC4JEUFAM","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":"6ca4d4a9af11ea341edfbde19c8f7b7bb4a2d70cffb3d7b4350669843a74319d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-21T09:38:18Z","title_canon_sha256":"4b4e5a19c0231676ad07b1e6667c1161942f621a0217e261d4a43345007d8228"},"schema_version":"1.0","source":{"id":"2212.10876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10876","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10876v1","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10876","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"J2J5BGQ4TZV7","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"J2J5BGQ4TZV7LZ5S","created_at":"2026-07-05T05:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"J2J5BGQ4","created_at":"2026-07-05T05:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:26ba564069b49e71c3a18dc8f624077f8e62aeb0a98e38c2173da2326757e4e1","target":"graph","created_at":"2026-07-05T05:27:23Z","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/2212.10876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although Reinforcement Learning (RL) has shown impressive results in games and simulation, real-world application of RL suffers from its instability under changing environment conditions and hyperparameters. We give a first impression of the extent of this instability by showing that the hyperparameters found by automatic hyperparameter optimization (HPO) methods are not only dependent on the problem at hand, but even on how well the state describes the environment dynamics. Specifically, we show that agents in contextual RL require different hyperparameters if they are shown how environmental","authors_text":"Carolin Benjamins, Marius Lindauer, Theresa Eimer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-21T09:38:18Z","title":"Hyperparameters in Contextual RL are Highly Situational"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10876","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":"sha256:39e2f392a96b8e0d0f66e93c6e00852697bdd8000c980e4340325c8622bc5774","target":"record","created_at":"2026-07-05T05:27:23Z","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":"6ca4d4a9af11ea341edfbde19c8f7b7bb4a2d70cffb3d7b4350669843a74319d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-21T09:38:18Z","title_canon_sha256":"4b4e5a19c0231676ad07b1e6667c1161942f621a0217e261d4a43345007d8228"},"schema_version":"1.0","source":{"id":"2212.10876","kind":"arxiv","version":1}},"canonical_sha256":"4e93d09a1c9e6bf5e7b21885c49285031884ce0037f5724010ed6f5cdc52e9e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e93d09a1c9e6bf5e7b21885c49285031884ce0037f5724010ed6f5cdc52e9e7","first_computed_at":"2026-07-05T05:27:23.888605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:23.888605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Naapb7NMDVS27H8PRqPIymuwOtKdH4l0Ep5hJkH1Z0PCiP25VaKfCH3TxOysMUwlSD+KMoMJwuWQCEWJj512CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:23.889027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39e2f392a96b8e0d0f66e93c6e00852697bdd8000c980e4340325c8622bc5774","sha256:26ba564069b49e71c3a18dc8f624077f8e62aeb0a98e38c2173da2326757e4e1"],"state_sha256":"d328166c8caf3b779364ab12f0c8d4a76fafc7101d8468abf42534228bf3edc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYrkn/FYNDGjPgLCH5RxejNLEc/bqzehKKdWuL+CQn54NpFY82GM8DBDTPxK5bYc4mQvw0aSOMcsekzzD7GtCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:51:15.106062Z","bundle_sha256":"1603f295981f71588559f771ff0a5efb795c3e4b942dccc0c2937de634678e37"}}