{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZGWO7XPCELBORZMX2QJPYMEU6L","short_pith_number":"pith:ZGWO7XPC","canonical_record":{"source":{"id":"2406.11240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T06:10:37Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"c48f8412548c89f2ac8572590e8bbdd65e6681e5428eabc855b78de57e003567","abstract_canon_sha256":"f4c63eff0533c522a6ef368f58c713187df4a59f5d8d54003be6089ab3001d7d"},"schema_version":"1.0"},"canonical_sha256":"c9acefdde222c2e8e597d412fc3094f2ee1084173d4fa1168cf3f550c8b59c43","source":{"kind":"arxiv","id":"2406.11240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11240","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11240v1","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11240","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZGWO7XPCELBO","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZGWO7XPCELBORZMX","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZGWO7XPC","created_at":"2026-07-05T08:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZGWO7XPCELBORZMX2QJPYMEU6L","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T06:10:37Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"c48f8412548c89f2ac8572590e8bbdd65e6681e5428eabc855b78de57e003567","abstract_canon_sha256":"f4c63eff0533c522a6ef368f58c713187df4a59f5d8d54003be6089ab3001d7d"},"schema_version":"1.0"},"canonical_sha256":"c9acefdde222c2e8e597d412fc3094f2ee1084173d4fa1168cf3f550c8b59c43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:50.639635Z","signature_b64":"xO+XT5W9g3bZMHe7d5XWuBk3ldcCU30NKzY4MKXQF2l+IrfChFH1QaW6vLcqhommmBbbnwm2T1M0dm2xHtjZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9acefdde222c2e8e597d412fc3094f2ee1084173d4fa1168cf3f550c8b59c43","last_reissued_at":"2026-07-05T08:32:50.639079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:50.639079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11240","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":"2026-07-05T08:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmMV4FA/Rz228EKemFL1kJVgQQjw4no2gutwBQjKS7IZu0182fOCzwGfy3mr2g9I1XJaZmN/FCqjnrurucMkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:23:54.177816Z"},"content_sha256":"adaa2ff460382f49af1228e4cde1c0fee0f4cb29ca76cd70cb31753445b2209d","schema_version":"1.0","event_id":"sha256:adaa2ff460382f49af1228e4cde1c0fee0f4cb29ca76cd70cb31753445b2209d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZGWO7XPCELBORZMX2QJPYMEU6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Benefits of Power Regularization in Cooperative Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Michael Dennis, Michelle Li","submitted_at":"2024-06-17T06:10:37Z","abstract_excerpt":"Cooperative Multi-Agent Reinforcement Learning (MARL) algorithms, trained only to optimize task reward, can lead to a concentration of power where the failure or adversarial intent of a single agent could decimate the reward of every agent in the system. In the context of teams of people, it is often useful to explicitly consider how power is distributed to ensure no person becomes a single point of failure. Here, we argue that explicitly regularizing the concentration of power in cooperative RL systems can result in systems which are more robust to single agent failure, adversarial attacks, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11240","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/2406.11240/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":"2026-07-05T08:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPfYIS5NmMKw2Igay+jKRWneBMWEjhBDdYKRIEwQw59lDE9CjWb9mkB6+AXV1q1srUkwdpF7hP6UXWGaHwwPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:23:54.178304Z"},"content_sha256":"5e06546aadb67a38da75557f1e68cce99ea7f7bc261ffec10e91994710a48473","schema_version":"1.0","event_id":"sha256:5e06546aadb67a38da75557f1e68cce99ea7f7bc261ffec10e91994710a48473"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZGWO7XPCELBORZMX2QJPYMEU6L/bundle.json","state_url":"https://pith.science/pith/ZGWO7XPCELBORZMX2QJPYMEU6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZGWO7XPCELBORZMX2QJPYMEU6L/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":"2026-08-19T00:23:54Z","links":{"resolver":"https://pith.science/pith/ZGWO7XPCELBORZMX2QJPYMEU6L","bundle":"https://pith.science/pith/ZGWO7XPCELBORZMX2QJPYMEU6L/bundle.json","state":"https://pith.science/pith/ZGWO7XPCELBORZMX2QJPYMEU6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZGWO7XPCELBORZMX2QJPYMEU6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZGWO7XPCELBORZMX2QJPYMEU6L","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":"f4c63eff0533c522a6ef368f58c713187df4a59f5d8d54003be6089ab3001d7d","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T06:10:37Z","title_canon_sha256":"c48f8412548c89f2ac8572590e8bbdd65e6681e5428eabc855b78de57e003567"},"schema_version":"1.0","source":{"id":"2406.11240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11240","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11240v1","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11240","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZGWO7XPCELBO","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZGWO7XPCELBORZMX","created_at":"2026-07-05T08:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZGWO7XPC","created_at":"2026-07-05T08:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:5e06546aadb67a38da75557f1e68cce99ea7f7bc261ffec10e91994710a48473","target":"graph","created_at":"2026-07-05T08:32:50Z","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/2406.11240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative Multi-Agent Reinforcement Learning (MARL) algorithms, trained only to optimize task reward, can lead to a concentration of power where the failure or adversarial intent of a single agent could decimate the reward of every agent in the system. In the context of teams of people, it is often useful to explicitly consider how power is distributed to ensure no person becomes a single point of failure. Here, we argue that explicitly regularizing the concentration of power in cooperative RL systems can result in systems which are more robust to single agent failure, adversarial attacks, a","authors_text":"Michael Dennis, Michelle Li","cross_cats":["cs.AI","cs.GT","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T06:10:37Z","title":"The Benefits of Power Regularization in Cooperative Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11240","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:adaa2ff460382f49af1228e4cde1c0fee0f4cb29ca76cd70cb31753445b2209d","target":"record","created_at":"2026-07-05T08:32:50Z","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":"f4c63eff0533c522a6ef368f58c713187df4a59f5d8d54003be6089ab3001d7d","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-17T06:10:37Z","title_canon_sha256":"c48f8412548c89f2ac8572590e8bbdd65e6681e5428eabc855b78de57e003567"},"schema_version":"1.0","source":{"id":"2406.11240","kind":"arxiv","version":1}},"canonical_sha256":"c9acefdde222c2e8e597d412fc3094f2ee1084173d4fa1168cf3f550c8b59c43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9acefdde222c2e8e597d412fc3094f2ee1084173d4fa1168cf3f550c8b59c43","first_computed_at":"2026-07-05T08:32:50.639079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:50.639079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xO+XT5W9g3bZMHe7d5XWuBk3ldcCU30NKzY4MKXQF2l+IrfChFH1QaW6vLcqhommmBbbnwm2T1M0dm2xHtjZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:50.639635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adaa2ff460382f49af1228e4cde1c0fee0f4cb29ca76cd70cb31753445b2209d","sha256:5e06546aadb67a38da75557f1e68cce99ea7f7bc261ffec10e91994710a48473"],"state_sha256":"7c1cb0fb5335b2ccccd5b5a31b75e6b76056e85c81628f15f3ed0c8ed2bfd332"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DW3hOPZKfM2SHC5fvhao2+L8QyaU6Fqry0av691frMwbzqS3gKWDMqeow7Jqbwi+8jXBc2RegmJy4EN6wFlMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:23:54.181779Z","bundle_sha256":"a8499344137b554258b49c41d9d39a13b51b3c103145f885418bda433043a6c7"}}