{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:67DQPA67VBONV7UJWUQ7PLRVQQ","short_pith_number":"pith:67DQPA67","schema_version":"1.0","canonical_sha256":"f7c70783dfa85cdafe89b521f7ae358438dbb7c2381bb4156a2732c4d6fedee0","source":{"kind":"arxiv","id":"2406.14662","version":3},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.14662","created_at":"2026-07-05T10:10:26.838911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14662v3","created_at":"2026-07-05T10:10:26.838911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14662","created_at":"2026-07-05T10:10:26.838911+00:00"},{"alias_kind":"pith_short_12","alias_value":"67DQPA67VBON","created_at":"2026-07-05T10:10:26.838911+00:00"},{"alias_kind":"pith_short_16","alias_value":"67DQPA67VBONV7UJ","created_at":"2026-07-05T10:10:26.838911+00:00"},{"alias_kind":"pith_short_8","alias_value":"67DQPA67","created_at":"2026-07-05T10:10:26.838911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04359","citing_title":"Learning to cooperate with emergent reputation via multi-agent reinforcement learning","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":126,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ","json":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ.json","graph_json":"https://pith.science/api/pith-number/67DQPA67VBONV7UJWUQ7PLRVQQ/graph.json","events_json":"https://pith.science/api/pith-number/67DQPA67VBONV7UJWUQ7PLRVQQ/events.json","paper":"https://pith.science/paper/67DQPA67"},"agent_actions":{"view_html":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ","download_json":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ.json","view_paper":"https://pith.science/paper/67DQPA67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14662&json=true","fetch_graph":"https://pith.science/api/pith-number/67DQPA67VBONV7UJWUQ7PLRVQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/67DQPA67VBONV7UJWUQ7PLRVQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/action/storage_attestation","attest_author":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/action/author_attestation","sign_citation":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/action/citation_signature","submit_replication":"https://pith.science/pith/67DQPA67VBONV7UJWUQ7PLRVQQ/action/replication_record"}},"created_at":"2026-07-05T10:10:26.838911+00:00","updated_at":"2026-07-05T10:10:26.838911+00:00"}