{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5AGFPLMU5E7AM6LIHNYTJEO7Q5","short_pith_number":"pith:5AGFPLMU","schema_version":"1.0","canonical_sha256":"e80c57ad94e93e0679683b713491df8743fea42d09ec80934d8133ebe6ef8363","source":{"kind":"arxiv","id":"2310.11518","version":3},"attestation_state":"computed","paper":{"title":"Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"James R. Wright, Revan MacQueen","submitted_at":"2023-10-17T18:33:21Z","abstract_excerpt":"Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that the agents the learner will face post-training may have dramatically different behavior than the learner came to expect by interacting with itself. For the special case of two-player constant-sum games, self-play that reaches Nash equilibrium is guaranteed to produce strategies that perform well against any post-training opponent; however, no such guarantee"},"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":"2310.11518","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2023-10-17T18:33:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c6e1431b8d666d363cec1487941f9c3e109db2b4150534e5fddda267417c00d7","abstract_canon_sha256":"b8edaf8994e5d8fb30cbd321c4a6ecc5f45152cdfaba9d72a732e30f020d945e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:12.244797Z","signature_b64":"HSQwazUsloP++C/vwfKUuVef2/hgphzXgrsHhfa4rCm//kV40zxMmc8nPkNqeI58u9E4Qj82jhSLXnEmYpO/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e80c57ad94e93e0679683b713491df8743fea42d09ec80934d8133ebe6ef8363","last_reissued_at":"2026-07-05T07:18:12.244214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:12.244214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"James R. Wright, Revan MacQueen","submitted_at":"2023-10-17T18:33:21Z","abstract_excerpt":"Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that the agents the learner will face post-training may have dramatically different behavior than the learner came to expect by interacting with itself. For the special case of two-player constant-sum games, self-play that reaches Nash equilibrium is guaranteed to produce strategies that perform well against any post-training opponent; however, no such guarantee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11518","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/2310.11518/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":"2310.11518","created_at":"2026-07-05T07:18:12.244269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11518v3","created_at":"2026-07-05T07:18:12.244269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11518","created_at":"2026-07-05T07:18:12.244269+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AGFPLMU5E7A","created_at":"2026-07-05T07:18:12.244269+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AGFPLMU5E7AM6LI","created_at":"2026-07-05T07:18:12.244269+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AGFPLMU","created_at":"2026-07-05T07:18:12.244269+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/5AGFPLMU5E7AM6LIHNYTJEO7Q5","json":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5.json","graph_json":"https://pith.science/api/pith-number/5AGFPLMU5E7AM6LIHNYTJEO7Q5/graph.json","events_json":"https://pith.science/api/pith-number/5AGFPLMU5E7AM6LIHNYTJEO7Q5/events.json","paper":"https://pith.science/paper/5AGFPLMU"},"agent_actions":{"view_html":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5","download_json":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5.json","view_paper":"https://pith.science/paper/5AGFPLMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11518&json=true","fetch_graph":"https://pith.science/api/pith-number/5AGFPLMU5E7AM6LIHNYTJEO7Q5/graph.json","fetch_events":"https://pith.science/api/pith-number/5AGFPLMU5E7AM6LIHNYTJEO7Q5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5/action/storage_attestation","attest_author":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5/action/author_attestation","sign_citation":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5/action/citation_signature","submit_replication":"https://pith.science/pith/5AGFPLMU5E7AM6LIHNYTJEO7Q5/action/replication_record"}},"created_at":"2026-07-05T07:18:12.244269+00:00","updated_at":"2026-07-05T07:18:12.244269+00:00"}