{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4ARQQ6AQYLXOYL3CDHULDKW4PM","short_pith_number":"pith:4ARQQ6AQ","canonical_record":{"source":{"id":"2507.18867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T00:59:10Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1e137f7c0ca371ece423e979a53305eea883cb24eec58aa4ecb57d59b591dfa0","abstract_canon_sha256":"2b90c7a6e1772838f25ad9778b5045567d87b2374e67570ad81b786534aa42ca"},"schema_version":"1.0"},"canonical_sha256":"e023087810c2eeec2f6219e8b1aadc7b3a0d4af006e75069d486dd917adb3ce3","source":{"kind":"arxiv","id":"2507.18867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18867","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18867v1","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18867","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"pith_short_12","alias_value":"4ARQQ6AQYLXO","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"pith_short_16","alias_value":"4ARQQ6AQYLXOYL3C","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"pith_short_8","alias_value":"4ARQQ6AQ","created_at":"2026-07-05T11:42:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4ARQQ6AQYLXOYL3CDHULDKW4PM","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T00:59:10Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1e137f7c0ca371ece423e979a53305eea883cb24eec58aa4ecb57d59b591dfa0","abstract_canon_sha256":"2b90c7a6e1772838f25ad9778b5045567d87b2374e67570ad81b786534aa42ca"},"schema_version":"1.0"},"canonical_sha256":"e023087810c2eeec2f6219e8b1aadc7b3a0d4af006e75069d486dd917adb3ce3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:59.882063Z","signature_b64":"Y8Zh3cu/o5uWCw/TJ7uaN5r3ReajpDWlRDK9Ghp+o0f2HQBDrVU8aJfN0N1cAYLkg+NPQwcSL43uHKVCnxR1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e023087810c2eeec2f6219e8b1aadc7b3a0d4af006e75069d486dd917adb3ce3","last_reissued_at":"2026-07-05T11:42:59.881593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:59.881593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18867","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":"2026-07-05T11:42:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K+smQgAVBHKjylbLxcoqu6vCVmt9npJ/nRMRh39YUtUZ9A47c/aHJiHYhiOnLMWMgGvSrVDlYGNsxuAxRHRHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:01:15.924055Z"},"content_sha256":"d6d03092877427bd2c512fc0a200a13c7eae34a34700d8239e53daf7c9a28a1e","schema_version":"1.0","event_id":"sha256:d6d03092877427bd2c512fc0a200a13c7eae34a34700d8239e53daf7c9a28a1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4ARQQ6AQYLXOYL3CDHULDKW4PM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Chunlin Chen, Xiao Yin, Xuefei Wu, Yuanyang Zhu","submitted_at":"2025-07-25T00:59:10Z","abstract_excerpt":"Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense individual rewards to guide the agents toward efficient exploration. However, individual rewards generally rely on manually engineered shaping-reward functions that lack high-order intelligence, thus it behaves ineffectively than humans regarding learning and generalization in complex problems. To tackle these issues, we combine the above two paradigms and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18867","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/2507.18867/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":"2026-07-05T11:42:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVndXzDSllQt5W9GYptNnFYL007vTwCH+YSH+ko2zMPtqGFBkr/CUpe+L+nTSKflYDIDmEFBFFyNM9uadTBqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T10:01:15.924740Z"},"content_sha256":"4babb2a9f4953b2e1942194593df71d4e543c5edff2dfbd0c039db43e01de07d","schema_version":"1.0","event_id":"sha256:4babb2a9f4953b2e1942194593df71d4e543c5edff2dfbd0c039db43e01de07d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/bundle.json","state_url":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/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":"2026-08-21T10:01:15Z","links":{"resolver":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM","bundle":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/bundle.json","state":"https://pith.science/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ARQQ6AQYLXOYL3CDHULDKW4PM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ARQQ6AQYLXOYL3CDHULDKW4PM","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":"2b90c7a6e1772838f25ad9778b5045567d87b2374e67570ad81b786534aa42ca","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T00:59:10Z","title_canon_sha256":"1e137f7c0ca371ece423e979a53305eea883cb24eec58aa4ecb57d59b591dfa0"},"schema_version":"1.0","source":{"id":"2507.18867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18867","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18867v1","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18867","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"pith_short_12","alias_value":"4ARQQ6AQYLXO","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"pith_short_16","alias_value":"4ARQQ6AQYLXOYL3C","created_at":"2026-07-05T11:42:59Z"},{"alias_kind":"pith_short_8","alias_value":"4ARQQ6AQ","created_at":"2026-07-05T11:42:59Z"}],"graph_snapshots":[{"event_id":"sha256:4babb2a9f4953b2e1942194593df71d4e543c5edff2dfbd0c039db43e01de07d","target":"graph","created_at":"2026-07-05T11:42:59Z","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/2507.18867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient exploration in multi-agent reinforcement learning (MARL) is a challenging problem when receiving only a team reward, especially in environments with sparse rewards. A powerful method to mitigate this issue involves crafting dense individual rewards to guide the agents toward efficient exploration. However, individual rewards generally rely on manually engineered shaping-reward functions that lack high-order intelligence, thus it behaves ineffectively than humans regarding learning and generalization in complex problems. To tackle these issues, we combine the above two paradigms and p","authors_text":"Chunlin Chen, Xiao Yin, Xuefei Wu, Yuanyang Zhu","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T00:59:10Z","title":"Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18867","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:d6d03092877427bd2c512fc0a200a13c7eae34a34700d8239e53daf7c9a28a1e","target":"record","created_at":"2026-07-05T11:42:59Z","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":"2b90c7a6e1772838f25ad9778b5045567d87b2374e67570ad81b786534aa42ca","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-25T00:59:10Z","title_canon_sha256":"1e137f7c0ca371ece423e979a53305eea883cb24eec58aa4ecb57d59b591dfa0"},"schema_version":"1.0","source":{"id":"2507.18867","kind":"arxiv","version":1}},"canonical_sha256":"e023087810c2eeec2f6219e8b1aadc7b3a0d4af006e75069d486dd917adb3ce3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e023087810c2eeec2f6219e8b1aadc7b3a0d4af006e75069d486dd917adb3ce3","first_computed_at":"2026-07-05T11:42:59.881593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:59.881593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y8Zh3cu/o5uWCw/TJ7uaN5r3ReajpDWlRDK9Ghp+o0f2HQBDrVU8aJfN0N1cAYLkg+NPQwcSL43uHKVCnxR1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:59.882063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6d03092877427bd2c512fc0a200a13c7eae34a34700d8239e53daf7c9a28a1e","sha256:4babb2a9f4953b2e1942194593df71d4e543c5edff2dfbd0c039db43e01de07d"],"state_sha256":"e06d59990fc27b0641a269ffa4ad6a20b164e335b40c646aa7ed1240282f5f55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JLiEZFE3LnuNRc2E+8CqA5u0egZ0teivuTJ37YnmpoBkOQbrVm0lb3rvwX6DDu+UL59VAdYzRWd2AGEWleTCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T10:01:15.929960Z","bundle_sha256":"e51526018f6b9fb1ce67c51d8f1db8f280ced450a23e6434e1bb51496a41c906"}}