{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NISXR6YQSOUBLKPZ6QTE2OHFZX","short_pith_number":"pith:NISXR6YQ","schema_version":"1.0","canonical_sha256":"6a2578fb1093a815a9f9f4264d38e5cde04eac116cf70fca34f4f1b51da32a04","source":{"kind":"arxiv","id":"2306.13233","version":3},"attestation_state":"computed","paper":{"title":"On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff","submitted_at":"2023-06-22T22:45:48Z","abstract_excerpt":"This paper studies a variant of two-player zero-sum matrix games, where, at each timestep, the row player selects row $i$, the column player selects column $j$, and the row player receives a noisy reward with expected value $A_{i,j}$, along with noisy feedback on the input matrix $A$. The row player's goal is to maximize their total reward against an adversarial column player. Nash regret, defined as the difference between the player's total reward and the game's Nash equilibrium value scaled by the time horizon $T$, is often used to evaluate algorithmic performance in zero-sum games.\n  We beg"},"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":"2306.13233","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T22:45:48Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"80f16936939ff4fea5dc676e381b7dc408ef47bc6be1e9bbc60c98896524bc49","abstract_canon_sha256":"1f8be65513a4aa689d95405c98d7a3ede2ba294ae817b7e01f45bf31d28ad5e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:37.475596Z","signature_b64":"IOvjKURg6r+fMOHMF+9USAw7Topk8E7+Z22sWhw3/7E0NdI03iLrDfoQg82lxHeeSVC6fBdotzJo0yY9qHoJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2578fb1093a815a9f9f4264d38e5cde04eac116cf70fca34f4f1b51da32a04","last_reissued_at":"2026-07-05T11:08:37.475096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:37.475096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff","submitted_at":"2023-06-22T22:45:48Z","abstract_excerpt":"This paper studies a variant of two-player zero-sum matrix games, where, at each timestep, the row player selects row $i$, the column player selects column $j$, and the row player receives a noisy reward with expected value $A_{i,j}$, along with noisy feedback on the input matrix $A$. The row player's goal is to maximize their total reward against an adversarial column player. Nash regret, defined as the difference between the player's total reward and the game's Nash equilibrium value scaled by the time horizon $T$, is often used to evaluate algorithmic performance in zero-sum games.\n  We beg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13233","kind":"arxiv","version":3},"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/2306.13233/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":"2306.13233","created_at":"2026-07-05T11:08:37.475151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13233v3","created_at":"2026-07-05T11:08:37.475151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13233","created_at":"2026-07-05T11:08:37.475151+00:00"},{"alias_kind":"pith_short_12","alias_value":"NISXR6YQSOUB","created_at":"2026-07-05T11:08:37.475151+00:00"},{"alias_kind":"pith_short_16","alias_value":"NISXR6YQSOUBLKPZ","created_at":"2026-07-05T11:08:37.475151+00:00"},{"alias_kind":"pith_short_8","alias_value":"NISXR6YQ","created_at":"2026-07-05T11:08:37.475151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23351","citing_title":"Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX","json":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX.json","graph_json":"https://pith.science/api/pith-number/NISXR6YQSOUBLKPZ6QTE2OHFZX/graph.json","events_json":"https://pith.science/api/pith-number/NISXR6YQSOUBLKPZ6QTE2OHFZX/events.json","paper":"https://pith.science/paper/NISXR6YQ"},"agent_actions":{"view_html":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX","download_json":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX.json","view_paper":"https://pith.science/paper/NISXR6YQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13233&json=true","fetch_graph":"https://pith.science/api/pith-number/NISXR6YQSOUBLKPZ6QTE2OHFZX/graph.json","fetch_events":"https://pith.science/api/pith-number/NISXR6YQSOUBLKPZ6QTE2OHFZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX/action/storage_attestation","attest_author":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX/action/author_attestation","sign_citation":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX/action/citation_signature","submit_replication":"https://pith.science/pith/NISXR6YQSOUBLKPZ6QTE2OHFZX/action/replication_record"}},"created_at":"2026-07-05T11:08:37.475151+00:00","updated_at":"2026-07-05T11:08:37.475151+00:00"}