{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NKAAMBHZKW2HOCIDIBM4SQFFWK","short_pith_number":"pith:NKAAMBHZ","schema_version":"1.0","canonical_sha256":"6a800604f955b47709034059c940a5b28220ec51ecb158ce85039be76fa271a1","source":{"kind":"arxiv","id":"2305.14709","version":1},"attestation_state":"computed","paper":{"title":"Regret Matching+: (In)Stability and Fast Convergence in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GT","authors_text":"Christian Kroer, Chung-Wei Lee, Gabriele Farina, Haipeng Luo, Julien Grand-Cl\\'ement","submitted_at":"2023-05-24T04:26:21Z","abstract_excerpt":"Regret Matching+ (RM+) and its variants are important algorithms for solving large-scale games. However, a theoretical understanding of their success in practice is still a mystery. Moreover, recent advances on fast convergence in games are limited to no-regret algorithms such as online mirror descent, which satisfy stability. In this paper, we first give counterexamples showing that RM+ and its predictive version can be unstable, which might cause other players to suffer large regret. We then provide two fixes: restarting and chopping off the positive orthant that RM+ works in. We show that t"},"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":"2305.14709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2023-05-24T04:26:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b663e22f4f5318b6218de525111b393eeb36a52d8dd673af2395f4f28b260d6","abstract_canon_sha256":"dd5115ef722c2fcdef444d52122e0955fecce5c4ee342ff668ec4d5a2704d741"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:26.996194Z","signature_b64":"AJ64xr6JAbHMdpDAFt/Q4g67fp10+yJvn0+JYgcidPK1nbvZ6neGO33nRdzl0/VfDf96wnb5WZh488Ty+zyfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a800604f955b47709034059c940a5b28220ec51ecb158ce85039be76fa271a1","last_reissued_at":"2026-07-05T06:13:26.995782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:26.995782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret Matching+: (In)Stability and Fast Convergence in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GT","authors_text":"Christian Kroer, Chung-Wei Lee, Gabriele Farina, Haipeng Luo, Julien Grand-Cl\\'ement","submitted_at":"2023-05-24T04:26:21Z","abstract_excerpt":"Regret Matching+ (RM+) and its variants are important algorithms for solving large-scale games. However, a theoretical understanding of their success in practice is still a mystery. Moreover, recent advances on fast convergence in games are limited to no-regret algorithms such as online mirror descent, which satisfy stability. In this paper, we first give counterexamples showing that RM+ and its predictive version can be unstable, which might cause other players to suffer large regret. We then provide two fixes: restarting and chopping off the positive orthant that RM+ works in. We show that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14709","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/2305.14709/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":"2305.14709","created_at":"2026-07-05T06:13:26.995835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14709v1","created_at":"2026-07-05T06:13:26.995835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14709","created_at":"2026-07-05T06:13:26.995835+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKAAMBHZKW2H","created_at":"2026-07-05T06:13:26.995835+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKAAMBHZKW2HOCID","created_at":"2026-07-05T06:13:26.995835+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKAAMBHZ","created_at":"2026-07-05T06:13:26.995835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00533","citing_title":"Rapid Learning in Constrained Minimax Games with Negative Momentum","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK","json":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK.json","graph_json":"https://pith.science/api/pith-number/NKAAMBHZKW2HOCIDIBM4SQFFWK/graph.json","events_json":"https://pith.science/api/pith-number/NKAAMBHZKW2HOCIDIBM4SQFFWK/events.json","paper":"https://pith.science/paper/NKAAMBHZ"},"agent_actions":{"view_html":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK","download_json":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK.json","view_paper":"https://pith.science/paper/NKAAMBHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14709&json=true","fetch_graph":"https://pith.science/api/pith-number/NKAAMBHZKW2HOCIDIBM4SQFFWK/graph.json","fetch_events":"https://pith.science/api/pith-number/NKAAMBHZKW2HOCIDIBM4SQFFWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK/action/storage_attestation","attest_author":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK/action/author_attestation","sign_citation":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK/action/citation_signature","submit_replication":"https://pith.science/pith/NKAAMBHZKW2HOCIDIBM4SQFFWK/action/replication_record"}},"created_at":"2026-07-05T06:13:26.995835+00:00","updated_at":"2026-07-05T06:13:26.995835+00:00"}