{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AX36ZOOGYDUQLBKPRYZDPIYTS4","short_pith_number":"pith:AX36ZOOG","canonical_record":{"source":{"id":"2408.10215","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T09:28:12Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"6b3a01eeaebc4e5d8997c70597f219a98a7741e17c01c964c52337a9d30da1c6","abstract_canon_sha256":"b5a3ff14122d818109aeeadc4a51424f0300e7adc512cf3943ac69565d14ce61"},"schema_version":"1.0"},"canonical_sha256":"05f7ecb9c6c0e905854f8e3237a313972a5cd2040b84e374cff752c3e20e8d05","source":{"kind":"arxiv","id":"2408.10215","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10215","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10215v2","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10215","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"AX36ZOOGYDUQ","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"AX36ZOOGYDUQLBKP","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"AX36ZOOG","created_at":"2026-07-05T09:54:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AX36ZOOGYDUQLBKPRYZDPIYTS4","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10215","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T09:28:12Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"6b3a01eeaebc4e5d8997c70597f219a98a7741e17c01c964c52337a9d30da1c6","abstract_canon_sha256":"b5a3ff14122d818109aeeadc4a51424f0300e7adc512cf3943ac69565d14ce61"},"schema_version":"1.0"},"canonical_sha256":"05f7ecb9c6c0e905854f8e3237a313972a5cd2040b84e374cff752c3e20e8d05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:46.409014Z","signature_b64":"wrSKYpDCeqg0DKpVD2/NKwviZsEt5HURCUetf1U6J3v0wuIO+qhD7C4xhRY6nS2wQdZ35PTUYfly+F+dqXOoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f7ecb9c6c0e905854f8e3237a313972a5cd2040b84e374cff752c3e20e8d05","last_reissued_at":"2026-07-05T09:54:46.408530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:46.408530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10215","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":"2026-07-05T09:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PICOqbuQly/2cATdxFQRivTugioWT/1VxMlZtCTi4Yro6nRsjWVNjdITJvrz3tUjCCqOGDAN/yotF559K7GZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:24:22.357750Z"},"content_sha256":"82d27032e2c6fdb8e27db3caff85f0b010eb2fb35687dd139ee883f4bee45a44","schema_version":"1.0","event_id":"sha256:82d27032e2c6fdb8e27db3caff85f0b010eb2fb35687dd139ee883f4bee45a44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AX36ZOOGYDUQLBKPRYZDPIYTS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Jnadi, Hadi Salloum, Mostafa Mostafa, Pavel Osinenko, Sinan Ibrahim","submitted_at":"2024-07-22T09:28:12Z","abstract_excerpt":"The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward engineering and reward shaping in enhancing the efficiency and effectiveness of reinforcement learning algorithms. Reward engineering involves designing reward functions that accurately reflect the desired outcomes, while reward shaping provides additional feedback to guide the learning process, accelerating convergence to optimal policies. Despite significant adva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10215","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/2408.10215/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":"2026-07-05T09:54:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xSxGM/SCqdPLHZa0fKfxn/ukrgabcLRUb+TtPJDaQop8w/j52y5db0EFEIE/lPueSboFNor1EsmuIa/Wu7nECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:24:22.358129Z"},"content_sha256":"f796cd96900523d7cc0ad734bf4feadec67a16bc7a22750fd913f3d255974089","schema_version":"1.0","event_id":"sha256:f796cd96900523d7cc0ad734bf4feadec67a16bc7a22750fd913f3d255974089"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AX36ZOOGYDUQLBKPRYZDPIYTS4/bundle.json","state_url":"https://pith.science/pith/AX36ZOOGYDUQLBKPRYZDPIYTS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AX36ZOOGYDUQLBKPRYZDPIYTS4/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":"2026-08-13T13:24:22Z","links":{"resolver":"https://pith.science/pith/AX36ZOOGYDUQLBKPRYZDPIYTS4","bundle":"https://pith.science/pith/AX36ZOOGYDUQLBKPRYZDPIYTS4/bundle.json","state":"https://pith.science/pith/AX36ZOOGYDUQLBKPRYZDPIYTS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AX36ZOOGYDUQLBKPRYZDPIYTS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AX36ZOOGYDUQLBKPRYZDPIYTS4","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":"b5a3ff14122d818109aeeadc4a51424f0300e7adc512cf3943ac69565d14ce61","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T09:28:12Z","title_canon_sha256":"6b3a01eeaebc4e5d8997c70597f219a98a7741e17c01c964c52337a9d30da1c6"},"schema_version":"1.0","source":{"id":"2408.10215","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10215","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10215v2","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10215","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"AX36ZOOGYDUQ","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"AX36ZOOGYDUQLBKP","created_at":"2026-07-05T09:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"AX36ZOOG","created_at":"2026-07-05T09:54:46Z"}],"graph_snapshots":[{"event_id":"sha256:f796cd96900523d7cc0ad734bf4feadec67a16bc7a22750fd913f3d255974089","target":"graph","created_at":"2026-07-05T09:54:46Z","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/2408.10215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward engineering and reward shaping in enhancing the efficiency and effectiveness of reinforcement learning algorithms. Reward engineering involves designing reward functions that accurately reflect the desired outcomes, while reward shaping provides additional feedback to guide the learning process, accelerating convergence to optimal policies. Despite significant adva","authors_text":"Ali Jnadi, Hadi Salloum, Mostafa Mostafa, Pavel Osinenko, Sinan Ibrahim","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T09:28:12Z","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10215","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":"sha256:82d27032e2c6fdb8e27db3caff85f0b010eb2fb35687dd139ee883f4bee45a44","target":"record","created_at":"2026-07-05T09:54:46Z","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":"b5a3ff14122d818109aeeadc4a51424f0300e7adc512cf3943ac69565d14ce61","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T09:28:12Z","title_canon_sha256":"6b3a01eeaebc4e5d8997c70597f219a98a7741e17c01c964c52337a9d30da1c6"},"schema_version":"1.0","source":{"id":"2408.10215","kind":"arxiv","version":2}},"canonical_sha256":"05f7ecb9c6c0e905854f8e3237a313972a5cd2040b84e374cff752c3e20e8d05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05f7ecb9c6c0e905854f8e3237a313972a5cd2040b84e374cff752c3e20e8d05","first_computed_at":"2026-07-05T09:54:46.408530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:46.408530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wrSKYpDCeqg0DKpVD2/NKwviZsEt5HURCUetf1U6J3v0wuIO+qhD7C4xhRY6nS2wQdZ35PTUYfly+F+dqXOoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:46.409014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10215","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82d27032e2c6fdb8e27db3caff85f0b010eb2fb35687dd139ee883f4bee45a44","sha256:f796cd96900523d7cc0ad734bf4feadec67a16bc7a22750fd913f3d255974089"],"state_sha256":"2fc2feb5ba4c974c3f2a01b017678124a7a05242076dfde90001b61495baf606"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"za93pa4SIzGTg5CO9QgqG0SPJGci5jhPrBoDnSNIYpxrc+htmNHJOv7yTyCjv2Sox27EvS4DvVa35xN92yz0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:24:22.360786Z","bundle_sha256":"f9a9018c348bb7e83c3ce0262312a84d146ecca09125a945571d163bc85dfb00"}}