{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:JQARITQTBYZ2MGQWIKBBWOA4PQ","short_pith_number":"pith:JQARITQT","canonical_record":{"source":{"id":"1409.8498","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2014-09-30T11:46:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"38a309b3cdb64131c8d03df834786cbe86dfe4a0c272e7a4bcf05573f34f7a30","abstract_canon_sha256":"9ff19b1318e59643df43146e7915db53f668539db2e1d9d218972f5835049bf1"},"schema_version":"1.0"},"canonical_sha256":"4c01144e130e33a61a1642821b381c7c0990a1393eeefbf14969573d380dfc39","source":{"kind":"arxiv","id":"1409.8498","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.8498","created_at":"2026-05-18T00:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"1409.8498v3","created_at":"2026-05-18T00:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.8498","created_at":"2026-05-18T00:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"JQARITQTBYZ2","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"JQARITQTBYZ2MGQW","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"JQARITQT","created_at":"2026-05-18T12:28:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:JQARITQTBYZ2MGQWIKBBWOA4PQ","target":"record","payload":{"canonical_record":{"source":{"id":"1409.8498","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2014-09-30T11:46:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"38a309b3cdb64131c8d03df834786cbe86dfe4a0c272e7a4bcf05573f34f7a30","abstract_canon_sha256":"9ff19b1318e59643df43146e7915db53f668539db2e1d9d218972f5835049bf1"},"schema_version":"1.0"},"canonical_sha256":"4c01144e130e33a61a1642821b381c7c0990a1393eeefbf14969573d380dfc39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:35.214076Z","signature_b64":"Z4uJ1Uc22njeB3d6IRGva1YXB5If6/r4cED8Omwz+L3Uub63OAlrJVGCcQlv7Ad5/+Q5SgPY6XqWR0QV/PNBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c01144e130e33a61a1642821b381c7c0990a1393eeefbf14969573d380dfc39","last_reissued_at":"2026-05-18T00:25:35.213438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:35.213438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1409.8498","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+0OSqVwqwMhPg5VPwsWywwulUV+RdMN6aPp1gxZmvrFfqIUIWJgvNV/wXX05DljUTxOl7llxIY7BG0uCiuOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T07:43:43.149003Z"},"content_sha256":"e8682e42c6f5c20fd032d675d9bda5004cbbbba5b8fa4fedbd12542906fede4f","schema_version":"1.0","event_id":"sha256:e8682e42c6f5c20fd032d675d9bda5004cbbbba5b8fa4fedbd12542906fede4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:JQARITQTBYZ2MGQWIKBBWOA4PQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-myopic learning in repeated stochastic games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"Jacob W. Crandall","submitted_at":"2014-09-30T11:46:29Z","abstract_excerpt":"In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of multiple (even infinite) equilibria and inherently large strategy spaces. In this paper, we introduce a method to reduce the strategy space of two-player general-sum RSGs to a handful of expert strategies. This process, called Mega, effectually reduces an RSG to a bandit problem. We show that the resulting strategy space preserves several important properties "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.8498","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4FUVrtd4gXr0lwigEsPj7hr9ZwUEkGlXhjPdodQk5WanaFDijewCARbD1uoBA0YlkqSn4RJTlwMc4XHp5RrXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T07:43:43.149350Z"},"content_sha256":"f9d348cd990885992a1e68fc199b29a05e9ba167c6b1ff15125df2c1c3d61b17","schema_version":"1.0","event_id":"sha256:f9d348cd990885992a1e68fc199b29a05e9ba167c6b1ff15125df2c1c3d61b17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/bundle.json","state_url":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T07:43:43Z","links":{"resolver":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ","bundle":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/bundle.json","state":"https://pith.science/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQARITQTBYZ2MGQWIKBBWOA4PQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:JQARITQTBYZ2MGQWIKBBWOA4PQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9ff19b1318e59643df43146e7915db53f668539db2e1d9d218972f5835049bf1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2014-09-30T11:46:29Z","title_canon_sha256":"38a309b3cdb64131c8d03df834786cbe86dfe4a0c272e7a4bcf05573f34f7a30"},"schema_version":"1.0","source":{"id":"1409.8498","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.8498","created_at":"2026-05-18T00:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"1409.8498v3","created_at":"2026-05-18T00:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.8498","created_at":"2026-05-18T00:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"JQARITQTBYZ2","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"JQARITQTBYZ2MGQW","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"JQARITQT","created_at":"2026-05-18T12:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:f9d348cd990885992a1e68fc199b29a05e9ba167c6b1ff15125df2c1c3d61b17","target":"graph","created_at":"2026-05-18T00:25:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of multiple (even infinite) equilibria and inherently large strategy spaces. In this paper, we introduce a method to reduce the strategy space of two-player general-sum RSGs to a handful of expert strategies. This process, called Mega, effectually reduces an RSG to a bandit problem. We show that the resulting strategy space preserves several important properties ","authors_text":"Jacob W. Crandall","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2014-09-30T11:46:29Z","title":"Non-myopic learning in repeated stochastic games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.8498","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e8682e42c6f5c20fd032d675d9bda5004cbbbba5b8fa4fedbd12542906fede4f","target":"record","created_at":"2026-05-18T00:25:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9ff19b1318e59643df43146e7915db53f668539db2e1d9d218972f5835049bf1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2014-09-30T11:46:29Z","title_canon_sha256":"38a309b3cdb64131c8d03df834786cbe86dfe4a0c272e7a4bcf05573f34f7a30"},"schema_version":"1.0","source":{"id":"1409.8498","kind":"arxiv","version":3}},"canonical_sha256":"4c01144e130e33a61a1642821b381c7c0990a1393eeefbf14969573d380dfc39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c01144e130e33a61a1642821b381c7c0990a1393eeefbf14969573d380dfc39","first_computed_at":"2026-05-18T00:25:35.213438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:35.213438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z4uJ1Uc22njeB3d6IRGva1YXB5If6/r4cED8Omwz+L3Uub63OAlrJVGCcQlv7Ad5/+Q5SgPY6XqWR0QV/PNBBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:35.214076Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.8498","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8682e42c6f5c20fd032d675d9bda5004cbbbba5b8fa4fedbd12542906fede4f","sha256:f9d348cd990885992a1e68fc199b29a05e9ba167c6b1ff15125df2c1c3d61b17"],"state_sha256":"633567b0b75154f380195c17179839811bb825672fbd5e5248ae1a45fcfa462d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNw/YUPWgjabDZ+amHOo1bxCjje9BynKhKjKD4k3Ma0MnaxHLLUt5cX6z1TOEABxayOQJ7K14hrfeH2/9gUaBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T07:43:43.151277Z","bundle_sha256":"b6bc398154e53f9ecb3b960c19036b4d72756552ce9545c0861f5de07658ad01"}}