{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PD4RE53BMUCRZGGSPKFXXRLXOZ","short_pith_number":"pith:PD4RE53B","schema_version":"1.0","canonical_sha256":"78f912776165051c98d27a8b7bc577766a8409a02b16f8a45b67c3d8d9159cd0","source":{"kind":"arxiv","id":"2508.11874","version":2},"attestation_state":"computed","paper":{"title":"Discovering Expert-Level Nash Equilibrium Algorithms with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DS","cs.LO","cs.PL"],"primary_cat":"cs.GT","authors_text":"Dongchen Li, Hanyu Li, Xiaotie Deng","submitted_at":"2025-08-16T02:18:43Z","abstract_excerpt":"Designing polynomial-time algorithms for approximate Nash equilibria (ANE) with provable worst-case guarantees is a fundamental open problem in algorithmic game theory. While large language models (LLMs) can generate candidate algorithms at scale, certifying worst-case guarantees requires formal analysis over all game instances -- a task for which no automated system previously existed. Here, we present LegoNE, a framework encoding expert proof strategies into a symbolic language that automatically compiles any candidate algorithm into a finite optimization problem certifying its worst-case gu"},"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":"2508.11874","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.GT","submitted_at":"2025-08-16T02:18:43Z","cross_cats_sorted":["cs.AI","cs.DS","cs.LO","cs.PL"],"title_canon_sha256":"91dbcbef9223ead65a4e47fed1615ab38a78b626fc202d1ae32e451de8f840ec","abstract_canon_sha256":"cd56e3a6ded53379ff6b999dc1b88f0b5f13b80e9c702b96e249faa28e90a98f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:06.582223Z","signature_b64":"UoT8xYSO0MmigdvzcfvjC7NpJfTqhe/i63yacFiRx5mrxz4rnlst1Qsxjob/WP0CeI4DKMNa28so+xq1cO5aAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f912776165051c98d27a8b7bc577766a8409a02b16f8a45b67c3d8d9159cd0","last_reissued_at":"2026-06-09T02:07:06.581284Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:06.581284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Expert-Level Nash Equilibrium Algorithms with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DS","cs.LO","cs.PL"],"primary_cat":"cs.GT","authors_text":"Dongchen Li, Hanyu Li, Xiaotie Deng","submitted_at":"2025-08-16T02:18:43Z","abstract_excerpt":"Designing polynomial-time algorithms for approximate Nash equilibria (ANE) with provable worst-case guarantees is a fundamental open problem in algorithmic game theory. While large language models (LLMs) can generate candidate algorithms at scale, certifying worst-case guarantees requires formal analysis over all game instances -- a task for which no automated system previously existed. Here, we present LegoNE, a framework encoding expert proof strategies into a symbolic language that automatically compiles any candidate algorithm into a finite optimization problem certifying its worst-case gu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11874","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/2508.11874/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":"2508.11874","created_at":"2026-06-09T02:07:06.581374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11874v2","created_at":"2026-06-09T02:07:06.581374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11874","created_at":"2026-06-09T02:07:06.581374+00:00"},{"alias_kind":"pith_short_12","alias_value":"PD4RE53BMUCR","created_at":"2026-06-09T02:07:06.581374+00:00"},{"alias_kind":"pith_short_16","alias_value":"PD4RE53BMUCRZGGS","created_at":"2026-06-09T02:07:06.581374+00:00"},{"alias_kind":"pith_short_8","alias_value":"PD4RE53B","created_at":"2026-06-09T02:07:06.581374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16379","citing_title":"An Information-Theoretic Criterion for Efficient Data Synthesis","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ","json":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ.json","graph_json":"https://pith.science/api/pith-number/PD4RE53BMUCRZGGSPKFXXRLXOZ/graph.json","events_json":"https://pith.science/api/pith-number/PD4RE53BMUCRZGGSPKFXXRLXOZ/events.json","paper":"https://pith.science/paper/PD4RE53B"},"agent_actions":{"view_html":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ","download_json":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ.json","view_paper":"https://pith.science/paper/PD4RE53B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11874&json=true","fetch_graph":"https://pith.science/api/pith-number/PD4RE53BMUCRZGGSPKFXXRLXOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PD4RE53BMUCRZGGSPKFXXRLXOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ/action/storage_attestation","attest_author":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ/action/author_attestation","sign_citation":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ/action/citation_signature","submit_replication":"https://pith.science/pith/PD4RE53BMUCRZGGSPKFXXRLXOZ/action/replication_record"}},"created_at":"2026-06-09T02:07:06.581374+00:00","updated_at":"2026-06-09T02:07:06.581374+00:00"}