{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GF4HQZO52VNI4K7LOPPBYFE5OG","short_pith_number":"pith:GF4HQZO5","schema_version":"1.0","canonical_sha256":"31787865ddd55a8e2beb73de1c149d71b66e4d6736f209efa78ee7a6590e0a8c","source":{"kind":"arxiv","id":"2402.08393","version":1},"attestation_state":"computed","paper":{"title":"NfgTransformer: Equivariant Representation Learning for Normal-form Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Georgios Piliouras, Ian Gemp, Luke Marris, Nicolas Heess, Siqi Liu","submitted_at":"2024-02-13T11:38:52Z","abstract_excerpt":"Normal-form games (NFGs) are the fundamental model of strategic interaction. We study their representation using neural networks. We describe the inherent equivariance of NFGs -- any permutation of strategies describes an equivalent game -- as well as the challenges this poses for representation learning. We then propose the NfgTransformer architecture that leverages this equivariance, leading to state-of-the-art performance in a range of game-theoretic tasks including equilibrium-solving, deviation gain estimation and ranking, with a common approach to NFG representation. We show that the res"},"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":"2402.08393","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-02-13T11:38:52Z","cross_cats_sorted":[],"title_canon_sha256":"d40a0bd3e7ef390667eccb2635b86d075039f5e1089dd02f4b3b728f567e73e2","abstract_canon_sha256":"8ce469942870d33e830d352a1cf85bc4ca5e52422a198738789fed2701f39def"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:32.004449Z","signature_b64":"93wL0aEaFma4D88ZNlWy9PqJwAH2QTeoYDlkaAJQcR3GpAzpQsAUdMRLneruxQPMKrDbCKI47hxzLMqFFpOfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31787865ddd55a8e2beb73de1c149d71b66e4d6736f209efa78ee7a6590e0a8c","last_reissued_at":"2026-07-05T07:44:32.004021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:32.004021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NfgTransformer: Equivariant Representation Learning for Normal-form Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Georgios Piliouras, Ian Gemp, Luke Marris, Nicolas Heess, Siqi Liu","submitted_at":"2024-02-13T11:38:52Z","abstract_excerpt":"Normal-form games (NFGs) are the fundamental model of strategic interaction. We study their representation using neural networks. We describe the inherent equivariance of NFGs -- any permutation of strategies describes an equivalent game -- as well as the challenges this poses for representation learning. We then propose the NfgTransformer architecture that leverages this equivariance, leading to state-of-the-art performance in a range of game-theoretic tasks including equilibrium-solving, deviation gain estimation and ranking, with a common approach to NFG representation. We show that the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08393","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/2402.08393/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":"2402.08393","created_at":"2026-07-05T07:44:32.004078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08393v1","created_at":"2026-07-05T07:44:32.004078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08393","created_at":"2026-07-05T07:44:32.004078+00:00"},{"alias_kind":"pith_short_12","alias_value":"GF4HQZO52VNI","created_at":"2026-07-05T07:44:32.004078+00:00"},{"alias_kind":"pith_short_16","alias_value":"GF4HQZO52VNI4K7L","created_at":"2026-07-05T07:44:32.004078+00:00"},{"alias_kind":"pith_short_8","alias_value":"GF4HQZO5","created_at":"2026-07-05T07:44:32.004078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG","json":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG.json","graph_json":"https://pith.science/api/pith-number/GF4HQZO52VNI4K7LOPPBYFE5OG/graph.json","events_json":"https://pith.science/api/pith-number/GF4HQZO52VNI4K7LOPPBYFE5OG/events.json","paper":"https://pith.science/paper/GF4HQZO5"},"agent_actions":{"view_html":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG","download_json":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG.json","view_paper":"https://pith.science/paper/GF4HQZO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08393&json=true","fetch_graph":"https://pith.science/api/pith-number/GF4HQZO52VNI4K7LOPPBYFE5OG/graph.json","fetch_events":"https://pith.science/api/pith-number/GF4HQZO52VNI4K7LOPPBYFE5OG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG/action/storage_attestation","attest_author":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG/action/author_attestation","sign_citation":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG/action/citation_signature","submit_replication":"https://pith.science/pith/GF4HQZO52VNI4K7LOPPBYFE5OG/action/replication_record"}},"created_at":"2026-07-05T07:44:32.004078+00:00","updated_at":"2026-07-05T07:44:32.004078+00:00"}