{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XKCFFKPBUEEKBUB6UUMPIEMJ57","short_pith_number":"pith:XKCFFKPB","canonical_record":{"source":{"id":"2103.09159","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-16T15:56:57Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"cca190eade985719442fb86266c33819fc8c7bb825318a411516f881747a1357","abstract_canon_sha256":"ea9b082562a89b9ea9a6dc29b94444d4600e0173d7a93d8016249f5c8df48dc4"},"schema_version":"1.0"},"canonical_sha256":"ba8452a9e1a108a0d03ea518f41189efe16965c1454d42166d7f170e96ecffad","source":{"kind":"arxiv","id":"2103.09159","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09159","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09159v5","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09159","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"XKCFFKPBUEEK","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"pith_short_16","alias_value":"XKCFFKPBUEEKBUB6","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"pith_short_8","alias_value":"XKCFFKPB","created_at":"2026-07-05T05:38:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XKCFFKPBUEEKBUB6UUMPIEMJ57","target":"record","payload":{"canonical_record":{"source":{"id":"2103.09159","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-16T15:56:57Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"cca190eade985719442fb86266c33819fc8c7bb825318a411516f881747a1357","abstract_canon_sha256":"ea9b082562a89b9ea9a6dc29b94444d4600e0173d7a93d8016249f5c8df48dc4"},"schema_version":"1.0"},"canonical_sha256":"ba8452a9e1a108a0d03ea518f41189efe16965c1454d42166d7f170e96ecffad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:59.997626Z","signature_b64":"+tzP96WGnNk6QvPRIKf4JCgF1asYsMt5BCQv++GEqKCVzOCEfBGpq6MC4DLYyOROvUPHJWS0yz/TLAw0RVKrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba8452a9e1a108a0d03ea518f41189efe16965c1454d42166d7f170e96ecffad","last_reissued_at":"2026-07-05T05:38:59.997151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:59.997151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.09159","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+CJc1+9EvJ+WdFtce88pKsB08nMDfgw/cBTCqNZ9Gxrluxs8sk5LDcmBIwklU1DMn6lrlmNv4a5Kik6NG4eRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:48:15.385482Z"},"content_sha256":"ea4d1ca422bae252a7151c45167408bb1d3b82f8012d61e0d06e956c95cc9164","schema_version":"1.0","event_id":"sha256:ea4d1ca422bae252a7151c45167408bb1d3b82f8012d61e0d06e956c95cc9164"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XKCFFKPBUEEKBUB6UUMPIEMJ57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Shape Rewards using a Game of Two Partners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"David Mguni, Feifei Tong, Hui Chen, Jiangcheng Zhu, Jianhong Wang, Jun Wang, Matthew Taylor, Nicolas Perez-Nieves, Taher Jafferjee, Tianpei Yang, Wenbin Song, Yaodong Yang","submitted_at":"2021-03-16T15:56:57Z","abstract_excerpt":"Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is time-consuming and error-prone. It also requires domain knowledge which runs contrary to the goal of autonomous learning. We introduce Reinforcement Learning Optimising Shaping Algorithm (ROSA), an automated reward shaping framework in which the shaping-reward function is constructed in a Markov game between two agents. A reward-shaping agent (Shaper) uses switchi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09159","kind":"arxiv","version":5},"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/2103.09159/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":"2026-07-05T05:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdow9nPF97ZRPMsMYlrNTfzjZ8w3E4HPmn8u0YcfjF/k36CR6m2a4vR5FQL+2iayBckGsqBQRBuCak0G5KmWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:48:15.385874Z"},"content_sha256":"a0850bfd63c5dcc85f0b667eaf196d753629a94a0ea558a535bcf3ee79c52a54","schema_version":"1.0","event_id":"sha256:a0850bfd63c5dcc85f0b667eaf196d753629a94a0ea558a535bcf3ee79c52a54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKCFFKPBUEEKBUB6UUMPIEMJ57/bundle.json","state_url":"https://pith.science/pith/XKCFFKPBUEEKBUB6UUMPIEMJ57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKCFFKPBUEEKBUB6UUMPIEMJ57/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":"2026-07-09T04:48:15Z","links":{"resolver":"https://pith.science/pith/XKCFFKPBUEEKBUB6UUMPIEMJ57","bundle":"https://pith.science/pith/XKCFFKPBUEEKBUB6UUMPIEMJ57/bundle.json","state":"https://pith.science/pith/XKCFFKPBUEEKBUB6UUMPIEMJ57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKCFFKPBUEEKBUB6UUMPIEMJ57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XKCFFKPBUEEKBUB6UUMPIEMJ57","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":"ea9b082562a89b9ea9a6dc29b94444d4600e0173d7a93d8016249f5c8df48dc4","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-16T15:56:57Z","title_canon_sha256":"cca190eade985719442fb86266c33819fc8c7bb825318a411516f881747a1357"},"schema_version":"1.0","source":{"id":"2103.09159","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09159","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09159v5","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09159","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"XKCFFKPBUEEK","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"pith_short_16","alias_value":"XKCFFKPBUEEKBUB6","created_at":"2026-07-05T05:38:59Z"},{"alias_kind":"pith_short_8","alias_value":"XKCFFKPB","created_at":"2026-07-05T05:38:59Z"}],"graph_snapshots":[{"event_id":"sha256:a0850bfd63c5dcc85f0b667eaf196d753629a94a0ea558a535bcf3ee79c52a54","target":"graph","created_at":"2026-07-05T05:38:59Z","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/2103.09159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is time-consuming and error-prone. It also requires domain knowledge which runs contrary to the goal of autonomous learning. We introduce Reinforcement Learning Optimising Shaping Algorithm (ROSA), an automated reward shaping framework in which the shaping-reward function is constructed in a Markov game between two agents. A reward-shaping agent (Shaper) uses switchi","authors_text":"David Mguni, Feifei Tong, Hui Chen, Jiangcheng Zhu, Jianhong Wang, Jun Wang, Matthew Taylor, Nicolas Perez-Nieves, Taher Jafferjee, Tianpei Yang, Wenbin Song, Yaodong Yang","cross_cats":["cs.AI","cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-16T15:56:57Z","title":"Learning to Shape Rewards using a Game of Two Partners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09159","kind":"arxiv","version":5},"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:ea4d1ca422bae252a7151c45167408bb1d3b82f8012d61e0d06e956c95cc9164","target":"record","created_at":"2026-07-05T05:38:59Z","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":"ea9b082562a89b9ea9a6dc29b94444d4600e0173d7a93d8016249f5c8df48dc4","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-16T15:56:57Z","title_canon_sha256":"cca190eade985719442fb86266c33819fc8c7bb825318a411516f881747a1357"},"schema_version":"1.0","source":{"id":"2103.09159","kind":"arxiv","version":5}},"canonical_sha256":"ba8452a9e1a108a0d03ea518f41189efe16965c1454d42166d7f170e96ecffad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba8452a9e1a108a0d03ea518f41189efe16965c1454d42166d7f170e96ecffad","first_computed_at":"2026-07-05T05:38:59.997151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:59.997151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+tzP96WGnNk6QvPRIKf4JCgF1asYsMt5BCQv++GEqKCVzOCEfBGpq6MC4DLYyOROvUPHJWS0yz/TLAw0RVKrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:59.997626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.09159","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea4d1ca422bae252a7151c45167408bb1d3b82f8012d61e0d06e956c95cc9164","sha256:a0850bfd63c5dcc85f0b667eaf196d753629a94a0ea558a535bcf3ee79c52a54"],"state_sha256":"1de43b8ff03e5c994fd78476496839b29c5bc3c0de2372db15335008fdaa6873"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mzeb7vUx0WApCHvUZP3pPTGyLRTHR3f5LgJgopgqUajJrO4WypwmX9gtX9UlLjwjupiQXrgRafIkDIDr5MWGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:48:15.388391Z","bundle_sha256":"7d48bb65737e741109e09fbb22ce65873bc65f110840237b8f03de2a66a33678"}}