{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:327AZAHVZILCZOSMCVOA3BCL7S","short_pith_number":"pith:327AZAHV","canonical_record":{"source":{"id":"2402.01361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:29:18Z","cross_cats_sorted":[],"title_canon_sha256":"a48e6f05e7db7f0b0994b1afaf89c2100c8f73f5358094578a04e5c41039013c","abstract_canon_sha256":"a4f82ab98267fac5e025ce1e206ed71dd0c7895c7246dd47a656ec77efe7780a"},"schema_version":"1.0"},"canonical_sha256":"debe0c80f5ca162cba4c155c0d844bfc9b2ec8e0221c5629266727a903b1e978","source":{"kind":"arxiv","id":"2402.01361","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01361","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01361v2","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01361","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"327AZAHVZILC","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"327AZAHVZILCZOSM","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"327AZAHV","created_at":"2026-07-05T10:18:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:327AZAHVZILCZOSMCVOA3BCL7S","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:29:18Z","cross_cats_sorted":[],"title_canon_sha256":"a48e6f05e7db7f0b0994b1afaf89c2100c8f73f5358094578a04e5c41039013c","abstract_canon_sha256":"a4f82ab98267fac5e025ce1e206ed71dd0c7895c7246dd47a656ec77efe7780a"},"schema_version":"1.0"},"canonical_sha256":"debe0c80f5ca162cba4c155c0d844bfc9b2ec8e0221c5629266727a903b1e978","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:34.776533Z","signature_b64":"uPOYiHJIeqvLKPv60omUsBYWYBK4Wl0/yruQ96HcoThkeFhcsn0ZeNs1oiX1aZbnThZj/+2GFNhccPcsrBLoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"debe0c80f5ca162cba4c155c0d844bfc9b2ec8e0221c5629266727a903b1e978","last_reissued_at":"2026-07-05T10:18:34.776087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:34.776087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01361","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":"2026-07-05T10:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fF1MKsJD2Hw5WK8pNUkN2vy7+tSSUFY0xaxfhLyt6Kd3aHYzH4V8vO7TYkkAqHPugTdMTh5jwNjdwN0LXB9yBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:09:49.954825Z"},"content_sha256":"9ee2a76eed3336e1f136512fd895852c1f377524d5f6c91df2341a11fe6f098f","schema_version":"1.0","event_id":"sha256:9ee2a76eed3336e1f136512fd895852c1f377524d5f6c91df2341a11fe6f098f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:327AZAHVZILCZOSMCVOA3BCL7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To the Max: Reinventing Reward in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Grigorii Veviurko, Mathijs de Weerdt, Wendelin B\\\"ohmer","submitted_at":"2024-02-02T12:29:18Z","abstract_excerpt":"In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the task efficiently. Choosing a good reward function is hence an extremely important yet challenging problem. In this paper, we explore an alternative approach for using rewards for learning. We introduce \\textit{max-reward RL}, where an agent optimizes the maximum rather than the cumulative reward. Unlike earlier works, our approach works for deterministic an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01361","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/2402.01361/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":"2026-07-05T10:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pxcu1ox6WOWhovu6HbX4MKYRdInbF5YZ+xg2OPM7BK8HXf0no9BJfvpoMUf8QwpEOWfRg40l3i2kDPl5SmSFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:09:49.955229Z"},"content_sha256":"aa545cd5880294d2f27e357d15dd2c72ae50f21639657dbda294e2619d7a8bf4","schema_version":"1.0","event_id":"sha256:aa545cd5880294d2f27e357d15dd2c72ae50f21639657dbda294e2619d7a8bf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/bundle.json","state_url":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/327AZAHVZILCZOSMCVOA3BCL7S/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":"2026-07-06T23:09:49Z","links":{"resolver":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S","bundle":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/bundle.json","state":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/327AZAHVZILCZOSMCVOA3BCL7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:327AZAHVZILCZOSMCVOA3BCL7S","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":"a4f82ab98267fac5e025ce1e206ed71dd0c7895c7246dd47a656ec77efe7780a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:29:18Z","title_canon_sha256":"a48e6f05e7db7f0b0994b1afaf89c2100c8f73f5358094578a04e5c41039013c"},"schema_version":"1.0","source":{"id":"2402.01361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01361","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01361v2","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01361","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"327AZAHVZILC","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"327AZAHVZILCZOSM","created_at":"2026-07-05T10:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"327AZAHV","created_at":"2026-07-05T10:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:aa545cd5880294d2f27e357d15dd2c72ae50f21639657dbda294e2619d7a8bf4","target":"graph","created_at":"2026-07-05T10:18:34Z","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/2402.01361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the task efficiently. Choosing a good reward function is hence an extremely important yet challenging problem. In this paper, we explore an alternative approach for using rewards for learning. We introduce \\textit{max-reward RL}, where an agent optimizes the maximum rather than the cumulative reward. Unlike earlier works, our approach works for deterministic an","authors_text":"Grigorii Veviurko, Mathijs de Weerdt, Wendelin B\\\"ohmer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:29:18Z","title":"To the Max: Reinventing Reward in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01361","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":"sha256:9ee2a76eed3336e1f136512fd895852c1f377524d5f6c91df2341a11fe6f098f","target":"record","created_at":"2026-07-05T10:18:34Z","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":"a4f82ab98267fac5e025ce1e206ed71dd0c7895c7246dd47a656ec77efe7780a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:29:18Z","title_canon_sha256":"a48e6f05e7db7f0b0994b1afaf89c2100c8f73f5358094578a04e5c41039013c"},"schema_version":"1.0","source":{"id":"2402.01361","kind":"arxiv","version":2}},"canonical_sha256":"debe0c80f5ca162cba4c155c0d844bfc9b2ec8e0221c5629266727a903b1e978","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"debe0c80f5ca162cba4c155c0d844bfc9b2ec8e0221c5629266727a903b1e978","first_computed_at":"2026-07-05T10:18:34.776087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:34.776087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uPOYiHJIeqvLKPv60omUsBYWYBK4Wl0/yruQ96HcoThkeFhcsn0ZeNs1oiX1aZbnThZj/+2GFNhccPcsrBLoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:34.776533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ee2a76eed3336e1f136512fd895852c1f377524d5f6c91df2341a11fe6f098f","sha256:aa545cd5880294d2f27e357d15dd2c72ae50f21639657dbda294e2619d7a8bf4"],"state_sha256":"fe51934b270c99c23f5be0d471619e67bd2a409c5c6a31a4de9b5feddada2ee2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1B8ZbYjLpFGVFwav02/8IssX5drTO4hiRewGWI+EjuteIsrzSF0Z4m1otOU9cb8D0qm6Ld+mBiwD7zIHCAyADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:09:49.957201Z","bundle_sha256":"7de7d4717e29e21798802bd617a008fdae931638405c1f85cb248fc9c02524e2"}}