{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DCNVCAKGSX33SCTY6ZWRQNLFVO","short_pith_number":"pith:DCNVCAKG","schema_version":"1.0","canonical_sha256":"189b51014695f7b90a78f66d183565abb5072cc7bda3ad58794c1938838b91e2","source":{"kind":"arxiv","id":"1811.08469","version":3},"attestation_state":"computed","paper":{"title":"Stable Opponent Shaping in Differentiable Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Alistair Letcher, David Balduzzi, Jakob Foerster, Shimon Whiteson, Tim Rockt\\\"aschel","submitted_at":"2018-11-20T20:06:37Z","abstract_excerpt":"A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel -- from GANs and intrinsic curiosity to multi-agent RL. Opponent shaping is a powerful approach to improve learning dynamics in these games, accounting for player influence on others' updates. Learning with Opponent-Learning Awareness (LOLA) is a recent algorithm that exploits this response and leads to cooperation in settings like the Iterated Prisoner's Dilemma. Although experimentally successful, we show that LOLA agents can exhibit 'arrogant' behavio"},"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":"1811.08469","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-11-20T20:06:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"03cffa4d6ebed43016e1345406c3001ad865cc0bba8f2b2946dc468d11f88349","abstract_canon_sha256":"15e315561bcbe050d54ec862cc7c826ecdca26e993c31a81503427035d34c052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:24.869819Z","signature_b64":"n5yVL9ip1LOcFrOvYLuHW2DDYt0VSc40UMTSmNhwiCyumJCvMocMq+6+rmk6VvOu/M6OMBDcaSONgTvVeTi4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"189b51014695f7b90a78f66d183565abb5072cc7bda3ad58794c1938838b91e2","last_reissued_at":"2026-07-05T02:07:24.869444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:24.869444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Opponent Shaping in Differentiable Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Alistair Letcher, David Balduzzi, Jakob Foerster, Shimon Whiteson, Tim Rockt\\\"aschel","submitted_at":"2018-11-20T20:06:37Z","abstract_excerpt":"A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel -- from GANs and intrinsic curiosity to multi-agent RL. Opponent shaping is a powerful approach to improve learning dynamics in these games, accounting for player influence on others' updates. Learning with Opponent-Learning Awareness (LOLA) is a recent algorithm that exploits this response and leads to cooperation in settings like the Iterated Prisoner's Dilemma. Although experimentally successful, we show that LOLA agents can exhibit 'arrogant' behavio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08469","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/1811.08469/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":"1811.08469","created_at":"2026-07-05T02:07:24.869500+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.08469v3","created_at":"2026-07-05T02:07:24.869500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08469","created_at":"2026-07-05T02:07:24.869500+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCNVCAKGSX33","created_at":"2026-07-05T02:07:24.869500+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCNVCAKGSX33SCTY","created_at":"2026-07-05T02:07:24.869500+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCNVCAKG","created_at":"2026-07-05T02:07:24.869500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13806","citing_title":"Min-Max Optimization Requires Exponentially Many Queries","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO","json":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO.json","graph_json":"https://pith.science/api/pith-number/DCNVCAKGSX33SCTY6ZWRQNLFVO/graph.json","events_json":"https://pith.science/api/pith-number/DCNVCAKGSX33SCTY6ZWRQNLFVO/events.json","paper":"https://pith.science/paper/DCNVCAKG"},"agent_actions":{"view_html":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO","download_json":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO.json","view_paper":"https://pith.science/paper/DCNVCAKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.08469&json=true","fetch_graph":"https://pith.science/api/pith-number/DCNVCAKGSX33SCTY6ZWRQNLFVO/graph.json","fetch_events":"https://pith.science/api/pith-number/DCNVCAKGSX33SCTY6ZWRQNLFVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO/action/storage_attestation","attest_author":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO/action/author_attestation","sign_citation":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO/action/citation_signature","submit_replication":"https://pith.science/pith/DCNVCAKGSX33SCTY6ZWRQNLFVO/action/replication_record"}},"created_at":"2026-07-05T02:07:24.869500+00:00","updated_at":"2026-07-05T02:07:24.869500+00:00"}