{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OF3MLSQ5EH7VNVTL6YPNOGMR66","short_pith_number":"pith:OF3MLSQ5","schema_version":"1.0","canonical_sha256":"7176c5ca1d21ff56d66bf61ed71991f796084b69e75bfd62451ec916f21df273","source":{"kind":"arxiv","id":"2605.29371","version":1},"attestation_state":"computed","paper":{"title":"Kernel-based potential mean-field games with unbiased random Fourier $U$-statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Yumiharu Nakano","submitted_at":"2026-05-28T05:15:25Z","abstract_excerpt":"We study the subclass of potential mean-field games in which the running interaction cost and the terminal target cost are both expressed through reproducing-kernel maximum mean discrepancy (MMD) penalties, and develop a computational framework that exploits this kernel structure. Both costs are estimated from finite-sample empirical distributions using a random Fourier U-statistic representation that is unbiased and has linear cost in the batch size. The drift of the controlled diffusion is parametrized by a neural network and trained via stochastic gradient descent. For this subclass we prov"},"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":"2605.29371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-28T05:15:25Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","stat.ML"],"title_canon_sha256":"b7d7726198c8174621ae901cb59ec6c3f0ea4f394a836e0f9c6a2911aea5e4ba","abstract_canon_sha256":"585f7f446b325d6007eea20ee3b9de14d13dc7b8229fb015575f4448e9ce2ad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:35.760150Z","signature_b64":"oRpdUzspxrMEpRFlVp68KTrIUE3Fd61RM3DAb28IREifulDpDbY1FeqFnz/X4EVvBCaoTCL6W4UZZsHhux4LBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7176c5ca1d21ff56d66bf61ed71991f796084b69e75bfd62451ec916f21df273","last_reissued_at":"2026-05-29T01:05:35.759474Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:35.759474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernel-based potential mean-field games with unbiased random Fourier $U$-statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","stat.ML"],"primary_cat":"math.OC","authors_text":"Yumiharu Nakano","submitted_at":"2026-05-28T05:15:25Z","abstract_excerpt":"We study the subclass of potential mean-field games in which the running interaction cost and the terminal target cost are both expressed through reproducing-kernel maximum mean discrepancy (MMD) penalties, and develop a computational framework that exploits this kernel structure. Both costs are estimated from finite-sample empirical distributions using a random Fourier U-statistic representation that is unbiased and has linear cost in the batch size. The drift of the controlled diffusion is parametrized by a neural network and trained via stochastic gradient descent. For this subclass we prov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29371","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/2605.29371/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":"2605.29371","created_at":"2026-05-29T01:05:35.759579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29371v1","created_at":"2026-05-29T01:05:35.759579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29371","created_at":"2026-05-29T01:05:35.759579+00:00"},{"alias_kind":"pith_short_12","alias_value":"OF3MLSQ5EH7V","created_at":"2026-05-29T01:05:35.759579+00:00"},{"alias_kind":"pith_short_16","alias_value":"OF3MLSQ5EH7VNVTL","created_at":"2026-05-29T01:05:35.759579+00:00"},{"alias_kind":"pith_short_8","alias_value":"OF3MLSQ5","created_at":"2026-05-29T01:05:35.759579+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/OF3MLSQ5EH7VNVTL6YPNOGMR66","json":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66.json","graph_json":"https://pith.science/api/pith-number/OF3MLSQ5EH7VNVTL6YPNOGMR66/graph.json","events_json":"https://pith.science/api/pith-number/OF3MLSQ5EH7VNVTL6YPNOGMR66/events.json","paper":"https://pith.science/paper/OF3MLSQ5"},"agent_actions":{"view_html":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66","download_json":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66.json","view_paper":"https://pith.science/paper/OF3MLSQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29371&json=true","fetch_graph":"https://pith.science/api/pith-number/OF3MLSQ5EH7VNVTL6YPNOGMR66/graph.json","fetch_events":"https://pith.science/api/pith-number/OF3MLSQ5EH7VNVTL6YPNOGMR66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66/action/storage_attestation","attest_author":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66/action/author_attestation","sign_citation":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66/action/citation_signature","submit_replication":"https://pith.science/pith/OF3MLSQ5EH7VNVTL6YPNOGMR66/action/replication_record"}},"created_at":"2026-05-29T01:05:35.759579+00:00","updated_at":"2026-05-29T01:05:35.759579+00:00"}