{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:66KEWDSDICSEUIJYOKIIHPIZVD","short_pith_number":"pith:66KEWDSD","schema_version":"1.0","canonical_sha256":"f7944b0e4340a44a2138729083bd19a8e76403a08612ae61b80c8e3d92ddf573","source":{"kind":"arxiv","id":"2206.04122","version":2},"attestation_state":"computed","paper":{"title":"ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.GT","authors_text":"Gabriele Farina, Marc Lanctot, Stephen McAleer, Tuomas Sandholm","submitted_at":"2022-06-08T18:43:45Z","abstract_excerpt":"Recent techniques for approximating Nash equilibria in very large games leverage neural networks to learn approximately optimal policies (strategies). One promising line of research uses neural networks to approximate counterfactual regret minimization (CFR) or its modern variants. DREAM, the only current CFR-based neural method that is model free and therefore scalable to very large games, trains a neural network on an estimated regret target that can have extremely high variance due to an importance sampling term inherited from Monte Carlo CFR (MCCFR). In this paper we propose an unbiased mo"},"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":"2206.04122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-06-08T18:43:45Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"f995a2b9453e95a158a278a1d6095888cba1630f8dcd603accea5c25449f397d","abstract_canon_sha256":"635d64c916766ea07ee442c29d68e29429121cb6703bba95cb45605ce1a82777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:06.204884Z","signature_b64":"vTjF/6T1nFNnPzFUQc9og9UQ8yyJvLFNu2ujv+PLYRZco9cKdhmBHCxlnXAlHuOOtnHXOeC+1Jd9GRlZqZ4MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7944b0e4340a44a2138729083bd19a8e76403a08612ae61b80c8e3d92ddf573","last_reissued_at":"2026-07-05T05:05:06.204479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:06.204479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.GT","authors_text":"Gabriele Farina, Marc Lanctot, Stephen McAleer, Tuomas Sandholm","submitted_at":"2022-06-08T18:43:45Z","abstract_excerpt":"Recent techniques for approximating Nash equilibria in very large games leverage neural networks to learn approximately optimal policies (strategies). One promising line of research uses neural networks to approximate counterfactual regret minimization (CFR) or its modern variants. DREAM, the only current CFR-based neural method that is model free and therefore scalable to very large games, trains a neural network on an estimated regret target that can have extremely high variance due to an importance sampling term inherited from Monte Carlo CFR (MCCFR). In this paper we propose an unbiased mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04122","kind":"arxiv","version":2},"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/2206.04122/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":"2206.04122","created_at":"2026-07-05T05:05:06.204535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04122v2","created_at":"2026-07-05T05:05:06.204535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04122","created_at":"2026-07-05T05:05:06.204535+00:00"},{"alias_kind":"pith_short_12","alias_value":"66KEWDSDICSE","created_at":"2026-07-05T05:05:06.204535+00:00"},{"alias_kind":"pith_short_16","alias_value":"66KEWDSDICSEUIJY","created_at":"2026-07-05T05:05:06.204535+00:00"},{"alias_kind":"pith_short_8","alias_value":"66KEWDSD","created_at":"2026-07-05T05:05:06.204535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29457","citing_title":"How Much Due Diligence Before You Bid? Learning in Intractable Takeover Auctions","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16087","citing_title":"The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD","json":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD.json","graph_json":"https://pith.science/api/pith-number/66KEWDSDICSEUIJYOKIIHPIZVD/graph.json","events_json":"https://pith.science/api/pith-number/66KEWDSDICSEUIJYOKIIHPIZVD/events.json","paper":"https://pith.science/paper/66KEWDSD"},"agent_actions":{"view_html":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD","download_json":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD.json","view_paper":"https://pith.science/paper/66KEWDSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04122&json=true","fetch_graph":"https://pith.science/api/pith-number/66KEWDSDICSEUIJYOKIIHPIZVD/graph.json","fetch_events":"https://pith.science/api/pith-number/66KEWDSDICSEUIJYOKIIHPIZVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD/action/storage_attestation","attest_author":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD/action/author_attestation","sign_citation":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD/action/citation_signature","submit_replication":"https://pith.science/pith/66KEWDSDICSEUIJYOKIIHPIZVD/action/replication_record"}},"created_at":"2026-07-05T05:05:06.204535+00:00","updated_at":"2026-07-05T05:05:06.204535+00:00"}