{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:67DQPA67VBONV7UJWUQ7PLRVQQ","short_pith_number":"pith:67DQPA67","canonical_record":{"source":{"id":"2406.14662","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T18:30:09Z","cross_cats_sorted":[],"title_canon_sha256":"a9f4614e103b995462f47bea57f9313561b4e1906693b2cc39de34f370e4e1c2","abstract_canon_sha256":"b7cede5db7ae6c6b1c5c31b9a2cea561e71789a30828a4c0203d2a7389c6e22f"},"schema_version":"1.0"},"canonical_sha256":"f7c70783dfa85cdafe89b521f7ae358438dbb7c2381bb4156a2732c4d6fedee0","source":{"kind":"arxiv","id":"2406.14662","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14662","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14662v3","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14662","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"pith_short_12","alias_value":"67DQPA67VBON","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"pith_short_16","alias_value":"67DQPA67VBONV7UJ","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"pith_short_8","alias_value":"67DQPA67","created_at":"2026-07-05T10:10:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:67DQPA67VBONV7UJWUQ7PLRVQQ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14662","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T18:30:09Z","cross_cats_sorted":[],"title_canon_sha256":"a9f4614e103b995462f47bea57f9313561b4e1906693b2cc39de34f370e4e1c2","abstract_canon_sha256":"b7cede5db7ae6c6b1c5c31b9a2cea561e71789a30828a4c0203d2a7389c6e22f"},"schema_version":"1.0"},"canonical_sha256":"f7c70783dfa85cdafe89b521f7ae358438dbb7c2381bb4156a2732c4d6fedee0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:26.839290Z","signature_b64":"e1apIR8I2ALOeH8B+yWjpOYg+BeEUpka1PDcICe+lKEYxumXn5W1ODRE8VDGrE3XXBsjr2WoTemdoUCHVjZsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7c70783dfa85cdafe89b521f7ae358438dbb7c2381bb4156a2732c4d6fedee0","last_reissued_at":"2026-07-05T10:10:26.838856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:26.838856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14662","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:10:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4u8anwa8554ZOFQ+uqVso0OZlaAce3aK/YrergvskDSiiUKV7r72z0TvBxScAk2slZtxPmNtjn52Bg0VUhY+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:22.566210Z"},"content_sha256":"d3743c8666ff5344186412eab7e094bc7008c806e86d8bcb574724f605deaea3","schema_version":"1.0","event_id":"sha256:d3743c8666ff5344186412eab7e094bc7008c806e86d8bcb574724f605deaea3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:67DQPA67VBONV7UJWUQ7PLRVQQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advantage Alignment Algorithms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Gauthier Gidel, Juan Agustin Duque, Milad Aghajohari, Razvan Ciuca, Tianyu Zhang, Tim Cooijmans","submitted_at":"2024-06-20T18:30:09Z","abstract_excerpt":"Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts, particularly in general-sum games where naive reinforcement learning agents empirically converge to Pareto-suboptimal Nash equilibria. To address this issue, opponent shaping has emerged as a paradigm for finding socially beneficial equilibria in general-sum games. In this work, we introduce Advantage Alignment, a family of algorithms derived from first prin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14662","kind":"arxiv","version":3},"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/2406.14662/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":"2026-07-05T10:10:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMHh4Hfmjl8jvj8sWYRKr2dyynN8ozFTsOYOu2lCt9mmLIjdSI3wMnL6hlY6JAOXw/zLXvd3askrqmr0RmXyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:22.567123Z"},"content_sha256":"ee685420d6ed183d88e7b203367802385b8066af9da0a1d027aa755330e6326a","schema_version":"1.0","event_id":"sha256:ee685420d6ed183d88e7b203367802385b8066af9da0a1d027aa755330e6326a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/bundle.json","state_url":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/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":"2026-08-08T13:12:22Z","links":{"resolver":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ","bundle":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/bundle.json","state":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:67DQPA67VBONV7UJWUQ7PLRVQQ","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":"b7cede5db7ae6c6b1c5c31b9a2cea561e71789a30828a4c0203d2a7389c6e22f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T18:30:09Z","title_canon_sha256":"a9f4614e103b995462f47bea57f9313561b4e1906693b2cc39de34f370e4e1c2"},"schema_version":"1.0","source":{"id":"2406.14662","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14662","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14662v3","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14662","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"pith_short_12","alias_value":"67DQPA67VBON","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"pith_short_16","alias_value":"67DQPA67VBONV7UJ","created_at":"2026-07-05T10:10:26Z"},{"alias_kind":"pith_short_8","alias_value":"67DQPA67","created_at":"2026-07-05T10:10:26Z"}],"graph_snapshots":[{"event_id":"sha256:ee685420d6ed183d88e7b203367802385b8066af9da0a1d027aa755330e6326a","target":"graph","created_at":"2026-07-05T10:10:26Z","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/2406.14662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts, particularly in general-sum games where naive reinforcement learning agents empirically converge to Pareto-suboptimal Nash equilibria. To address this issue, opponent shaping has emerged as a paradigm for finding socially beneficial equilibria in general-sum games. In this work, we introduce Advantage Alignment, a family of algorithms derived from first prin","authors_text":"Aaron Courville, Gauthier Gidel, Juan Agustin Duque, Milad Aghajohari, Razvan Ciuca, Tianyu Zhang, Tim Cooijmans","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T18:30:09Z","title":"Advantage Alignment Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14662","kind":"arxiv","version":3},"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:d3743c8666ff5344186412eab7e094bc7008c806e86d8bcb574724f605deaea3","target":"record","created_at":"2026-07-05T10:10:26Z","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":"b7cede5db7ae6c6b1c5c31b9a2cea561e71789a30828a4c0203d2a7389c6e22f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T18:30:09Z","title_canon_sha256":"a9f4614e103b995462f47bea57f9313561b4e1906693b2cc39de34f370e4e1c2"},"schema_version":"1.0","source":{"id":"2406.14662","kind":"arxiv","version":3}},"canonical_sha256":"f7c70783dfa85cdafe89b521f7ae358438dbb7c2381bb4156a2732c4d6fedee0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7c70783dfa85cdafe89b521f7ae358438dbb7c2381bb4156a2732c4d6fedee0","first_computed_at":"2026-07-05T10:10:26.838856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:26.838856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e1apIR8I2ALOeH8B+yWjpOYg+BeEUpka1PDcICe+lKEYxumXn5W1ODRE8VDGrE3XXBsjr2WoTemdoUCHVjZsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:26.839290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14662","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3743c8666ff5344186412eab7e094bc7008c806e86d8bcb574724f605deaea3","sha256:ee685420d6ed183d88e7b203367802385b8066af9da0a1d027aa755330e6326a"],"state_sha256":"20393089604b419ff830d0283fb7af522331a828d35a316bbf394e2504a7384a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EhxXz5KfWWbOttfcOVglxIXDN/IwNbhbIHdOKvGeVEEtjZR4VUfKejtURHo7dDl2KggjMi3+TMqH5XNCKbLOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:12:22.571748Z","bundle_sha256":"a31eba008c15b75cf860af8c6dd475b2eba7ed22ac8413a0cccc38d9e366c31f"}}