{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DQR6FFTWVAGQEMX26DX26MKKEJ","short_pith_number":"pith:DQR6FFTW","schema_version":"1.0","canonical_sha256":"1c23e29676a80d0232faf0efaf314a22627d9e70ba4980206b6fc4b384076193","source":{"kind":"arxiv","id":"2606.01159","version":1},"attestation_state":"computed","paper":{"title":"Fairness in two-player zero-sum games with bandit feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Pratik Gajane, S Akash","submitted_at":"2026-05-31T11:06:06Z","abstract_excerpt":"We study two-player zero-sum games (TPZSGs) with bandit feedback under fairness constraints requiring every action to be played with probability at least $\\alpha/m$. Existing instance-dependent results target $\\textit{pure}$ Nash equilibria, while fairness generically produces $\\textit{mixed}$ equilibria, a harder learning target. Our key technical tool is a reparametrization: every fair strategy decomposes as $p = (\\alpha/m)\\mathbf{1} + (1-\\alpha)\\widetilde{p}$ with $\\widetilde{p} \\in \\Delta_m$, and substituting into the payoff form yields $p^{\\top}Aq = \\widetilde{p}^{\\top}\\widetilde{A} q$ fo"},"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":"2606.01159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T11:06:06Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"2ef96745c58f73b169c1e58f4eb80814fbe2c36ff253190649a8b4485b676e1a","abstract_canon_sha256":"449271b7085adca9b7239844a141c2d18b5f4dbf9e1e06e75b2478153bf6a7be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:25.356793Z","signature_b64":"SsFR5sfS+FRgWNfT7FOr1p289g2ja8NJg+frO79UjNyigCSoL7u05VHO1TT9duP1WQNpsnYTYP83wPxi5O1dBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c23e29676a80d0232faf0efaf314a22627d9e70ba4980206b6fc4b384076193","last_reissued_at":"2026-06-02T02:04:25.356363Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:25.356363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness in two-player zero-sum games with bandit feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Pratik Gajane, S Akash","submitted_at":"2026-05-31T11:06:06Z","abstract_excerpt":"We study two-player zero-sum games (TPZSGs) with bandit feedback under fairness constraints requiring every action to be played with probability at least $\\alpha/m$. Existing instance-dependent results target $\\textit{pure}$ Nash equilibria, while fairness generically produces $\\textit{mixed}$ equilibria, a harder learning target. Our key technical tool is a reparametrization: every fair strategy decomposes as $p = (\\alpha/m)\\mathbf{1} + (1-\\alpha)\\widetilde{p}$ with $\\widetilde{p} \\in \\Delta_m$, and substituting into the payoff form yields $p^{\\top}Aq = \\widetilde{p}^{\\top}\\widetilde{A} q$ fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01159","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/2606.01159/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":"2606.01159","created_at":"2026-06-02T02:04:25.356423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01159v1","created_at":"2026-06-02T02:04:25.356423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01159","created_at":"2026-06-02T02:04:25.356423+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQR6FFTWVAGQ","created_at":"2026-06-02T02:04:25.356423+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQR6FFTWVAGQEMX2","created_at":"2026-06-02T02:04:25.356423+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQR6FFTW","created_at":"2026-06-02T02:04:25.356423+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/DQR6FFTWVAGQEMX26DX26MKKEJ","json":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ.json","graph_json":"https://pith.science/api/pith-number/DQR6FFTWVAGQEMX26DX26MKKEJ/graph.json","events_json":"https://pith.science/api/pith-number/DQR6FFTWVAGQEMX26DX26MKKEJ/events.json","paper":"https://pith.science/paper/DQR6FFTW"},"agent_actions":{"view_html":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ","download_json":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ.json","view_paper":"https://pith.science/paper/DQR6FFTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01159&json=true","fetch_graph":"https://pith.science/api/pith-number/DQR6FFTWVAGQEMX26DX26MKKEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DQR6FFTWVAGQEMX26DX26MKKEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ/action/storage_attestation","attest_author":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ/action/author_attestation","sign_citation":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ/action/citation_signature","submit_replication":"https://pith.science/pith/DQR6FFTWVAGQEMX26DX26MKKEJ/action/replication_record"}},"created_at":"2026-06-02T02:04:25.356423+00:00","updated_at":"2026-06-02T02:04:25.356423+00:00"}