{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MLI5BR6IQRAR32UQUT4A7Y4UMH","short_pith_number":"pith:MLI5BR6I","canonical_record":{"source":{"id":"2106.06317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T11:31:04Z","cross_cats_sorted":[],"title_canon_sha256":"c10771aeff2e536ae8abc682907f5aa914a4aaa76d4ffb27e9ca099120c3ece4","abstract_canon_sha256":"dd6f6728df5faf60af32f3c06b72078f897889e682ebfbe84a74a844486911de"},"schema_version":"1.0"},"canonical_sha256":"62d1d0c7c884411dea90a4f80fe39461f7baba75999d1adb49391b22e9da7216","source":{"kind":"arxiv","id":"2106.06317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06317","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06317v1","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06317","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"MLI5BR6IQRAR","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"MLI5BR6IQRAR32UQ","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"MLI5BR6I","created_at":"2026-07-05T03:37:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MLI5BR6IQRAR32UQUT4A7Y4UMH","target":"record","payload":{"canonical_record":{"source":{"id":"2106.06317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T11:31:04Z","cross_cats_sorted":[],"title_canon_sha256":"c10771aeff2e536ae8abc682907f5aa914a4aaa76d4ffb27e9ca099120c3ece4","abstract_canon_sha256":"dd6f6728df5faf60af32f3c06b72078f897889e682ebfbe84a74a844486911de"},"schema_version":"1.0"},"canonical_sha256":"62d1d0c7c884411dea90a4f80fe39461f7baba75999d1adb49391b22e9da7216","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:43.368198Z","signature_b64":"k9SUahOcmxmzLDTaAbDe1ULwc7K9yU/ceH/iI5KTngvaX7XyQNqavW1lGXioWq81+Cqp6vJsfwSWz5eGClXnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62d1d0c7c884411dea90a4f80fe39461f7baba75999d1adb49391b22e9da7216","last_reissued_at":"2026-07-05T03:37:43.367666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:43.367666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.06317","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":"2026-07-05T03:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrYcDoeS9t1aALoPd/aWAhb+aPGg2sU9w54jZwYG2GnfpFMpqf8IqgO/RH9Bl1tPcFo+EHhVCBYR9JoBYcGOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:19:30.109022Z"},"content_sha256":"1e2c95b07c17d9342a31504145eab02fd3e6fa8a1244b7545f5f4256ccd12e26","schema_version":"1.0","event_id":"sha256:1e2c95b07c17d9342a31504145eab02fd3e6fa8a1244b7545f5f4256ccd12e26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MLI5BR6IQRAR32UQUT4A7Y4UMH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Risk Adaptation in Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bodo Rosenhahn, Frederik Schubert, Marius Lindauer, Theresa Eimer","submitted_at":"2021-06-11T11:31:04Z","abstract_excerpt":"The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical environments, where errors can lead to high costs or damage. In distributional RL, the risk-sensitivity can be controlled via different distortion measures of the estimated return distribution. However, these distortion functions require an estimate of the risk level, which is difficult to obtain and depends on the current state. In this work, we demonstrate the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06317","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/2106.06317/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":"2026-07-05T03:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eCPjlaHlcSUa4zOy+GEtQwvfDxPk6sXPM7nS+uUwTomj6K82qKm5jJs539WRwHOEWU3G+T+S2ZuYvDmSTnz1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:19:30.109664Z"},"content_sha256":"a94989ba33eda30a0e1cc279178caf1f606df3bf322fa2773c6972a1e39c1e1c","schema_version":"1.0","event_id":"sha256:a94989ba33eda30a0e1cc279178caf1f606df3bf322fa2773c6972a1e39c1e1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLI5BR6IQRAR32UQUT4A7Y4UMH/bundle.json","state_url":"https://pith.science/pith/MLI5BR6IQRAR32UQUT4A7Y4UMH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLI5BR6IQRAR32UQUT4A7Y4UMH/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":"2026-08-06T14:19:30Z","links":{"resolver":"https://pith.science/pith/MLI5BR6IQRAR32UQUT4A7Y4UMH","bundle":"https://pith.science/pith/MLI5BR6IQRAR32UQUT4A7Y4UMH/bundle.json","state":"https://pith.science/pith/MLI5BR6IQRAR32UQUT4A7Y4UMH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLI5BR6IQRAR32UQUT4A7Y4UMH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MLI5BR6IQRAR32UQUT4A7Y4UMH","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":"dd6f6728df5faf60af32f3c06b72078f897889e682ebfbe84a74a844486911de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T11:31:04Z","title_canon_sha256":"c10771aeff2e536ae8abc682907f5aa914a4aaa76d4ffb27e9ca099120c3ece4"},"schema_version":"1.0","source":{"id":"2106.06317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06317","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06317v1","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06317","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"MLI5BR6IQRAR","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"MLI5BR6IQRAR32UQ","created_at":"2026-07-05T03:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"MLI5BR6I","created_at":"2026-07-05T03:37:43Z"}],"graph_snapshots":[{"event_id":"sha256:a94989ba33eda30a0e1cc279178caf1f606df3bf322fa2773c6972a1e39c1e1c","target":"graph","created_at":"2026-07-05T03:37:43Z","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/2106.06317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of Reinforcement Learning (RL) agents in practical applications requires the consideration of suboptimal outcomes, depending on the familiarity of the agent with its environment. This is especially important in safety-critical environments, where errors can lead to high costs or damage. In distributional RL, the risk-sensitivity can be controlled via different distortion measures of the estimated return distribution. However, these distortion functions require an estimate of the risk level, which is difficult to obtain and depends on the current state. In this work, we demonstrate the ","authors_text":"Bodo Rosenhahn, Frederik Schubert, Marius Lindauer, Theresa Eimer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T11:31:04Z","title":"Automatic Risk Adaptation in Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06317","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":"sha256:1e2c95b07c17d9342a31504145eab02fd3e6fa8a1244b7545f5f4256ccd12e26","target":"record","created_at":"2026-07-05T03:37:43Z","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":"dd6f6728df5faf60af32f3c06b72078f897889e682ebfbe84a74a844486911de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-11T11:31:04Z","title_canon_sha256":"c10771aeff2e536ae8abc682907f5aa914a4aaa76d4ffb27e9ca099120c3ece4"},"schema_version":"1.0","source":{"id":"2106.06317","kind":"arxiv","version":1}},"canonical_sha256":"62d1d0c7c884411dea90a4f80fe39461f7baba75999d1adb49391b22e9da7216","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62d1d0c7c884411dea90a4f80fe39461f7baba75999d1adb49391b22e9da7216","first_computed_at":"2026-07-05T03:37:43.367666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:43.367666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k9SUahOcmxmzLDTaAbDe1ULwc7K9yU/ceH/iI5KTngvaX7XyQNqavW1lGXioWq81+Cqp6vJsfwSWz5eGClXnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:43.368198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e2c95b07c17d9342a31504145eab02fd3e6fa8a1244b7545f5f4256ccd12e26","sha256:a94989ba33eda30a0e1cc279178caf1f606df3bf322fa2773c6972a1e39c1e1c"],"state_sha256":"2c9cbc4f3123662933c0c5c786bd6c64d95f302005a407db7e2a85afed201430"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29W+nrf0gtqpMUKsjrlIRzZtS595o3OPo8JedwE2YIICCYxkazMZSaSOSu5wOrXS3QqXNzlyYRIc4/YyMfxZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:19:30.113251Z","bundle_sha256":"571ffb4e89b2dde60cdc6ab7eda719f8521e16636a7d154e844aa007b0d899f2"}}