{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IM7MSN3K74RRACLNK7MKRQGSIB","short_pith_number":"pith:IM7MSN3K","canonical_record":{"source":{"id":"1907.11543","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-26T12:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"acbf6cd1e3c9b68f583aebec6e27115d348094ba75cc31e2eba8fd9ddc8b4fc4","abstract_canon_sha256":"1c13f27cea9e41df1b4595b55119a91b963236cde8a1365c27cbf358893ff4d1"},"schema_version":"1.0"},"canonical_sha256":"433ec9376aff2310096d57d8a8c0d240592d7d43327f0ed257784bbac082dd80","source":{"kind":"arxiv","id":"1907.11543","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11543","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11543v2","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11543","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"IM7MSN3K74RR","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IM7MSN3K74RRACLN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IM7MSN3K","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IM7MSN3K74RRACLNK7MKRQGSIB","target":"record","payload":{"canonical_record":{"source":{"id":"1907.11543","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-26T12:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"acbf6cd1e3c9b68f583aebec6e27115d348094ba75cc31e2eba8fd9ddc8b4fc4","abstract_canon_sha256":"1c13f27cea9e41df1b4595b55119a91b963236cde8a1365c27cbf358893ff4d1"},"schema_version":"1.0"},"canonical_sha256":"433ec9376aff2310096d57d8a8c0d240592d7d43327f0ed257784bbac082dd80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:23.381760Z","signature_b64":"Vpl8k3fCSA5g8zVq4R7YkYMvckB0fm5g7QKPl5BYc3wcs6vE93Ld2nsPYi1Ct0/NceMJd4LkKD3o6oZv72tfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433ec9376aff2310096d57d8a8c0d240592d7d43327f0ed257784bbac082dd80","last_reissued_at":"2026-05-17T23:39:23.380931Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:23.380931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.11543","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5O2Um99DOx7EvVPG76QmznokIedWemlzKxvfpJ+AKQwUf4am1Z8B0lSA9Rj7oWWXpcgcVrLkOYHX60fWnDVFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:03:33.420650Z"},"content_sha256":"d7545767900e01c1308d4cd21a9caee0501ec09c8cd30f0b0ce0a3ac6508b36e","schema_version":"1.0","event_id":"sha256:d7545767900e01c1308d4cd21a9caee0501ec09c8cd30f0b0ce0a3ac6508b36e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IM7MSN3K74RRACLNK7MKRQGSIB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy-Regularized Stochastic Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Mohamadreza Ahmadi, Takashi Tanaka, Ufuk Topcu, Yagiz Savas","submitted_at":"2019-07-26T12:52:57Z","abstract_excerpt":"In two-player zero-sum stochastic games, where two competing players make decisions under uncertainty, a pair of optimal strategies is traditionally described by Nash equilibrium and computed under the assumption that the players have perfect information about the stochastic transition model of the environment. However, implementing such strategies may make the players vulnerable to unforeseen changes in the environment. In this paper, we introduce entropy-regularized stochastic games where each player aims to maximize the causal entropy of its strategy in addition to its expected payoff. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11543","kind":"arxiv","version":2},"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":"2026-05-17T23:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fwws3vP9KkanrlX4aC5AVoIfWvR6CMBr7lkxQGtHord8Y+KmStzE93K9j1rzWPDEsZibNzk/t2k+jGGZKXpIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:03:33.421066Z"},"content_sha256":"ebb4e7e88098ba12733a69b840115fa530fdeb720f2e37cd1c4d04d9349d8df8","schema_version":"1.0","event_id":"sha256:ebb4e7e88098ba12733a69b840115fa530fdeb720f2e37cd1c4d04d9349d8df8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IM7MSN3K74RRACLNK7MKRQGSIB/bundle.json","state_url":"https://pith.science/pith/IM7MSN3K74RRACLNK7MKRQGSIB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IM7MSN3K74RRACLNK7MKRQGSIB/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":"2026-05-28T20:03:33Z","links":{"resolver":"https://pith.science/pith/IM7MSN3K74RRACLNK7MKRQGSIB","bundle":"https://pith.science/pith/IM7MSN3K74RRACLNK7MKRQGSIB/bundle.json","state":"https://pith.science/pith/IM7MSN3K74RRACLNK7MKRQGSIB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IM7MSN3K74RRACLNK7MKRQGSIB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IM7MSN3K74RRACLNK7MKRQGSIB","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":"1c13f27cea9e41df1b4595b55119a91b963236cde8a1365c27cbf358893ff4d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-26T12:52:57Z","title_canon_sha256":"acbf6cd1e3c9b68f583aebec6e27115d348094ba75cc31e2eba8fd9ddc8b4fc4"},"schema_version":"1.0","source":{"id":"1907.11543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11543","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11543v2","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11543","created_at":"2026-05-17T23:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"IM7MSN3K74RR","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IM7MSN3K74RRACLN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IM7MSN3K","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:ebb4e7e88098ba12733a69b840115fa530fdeb720f2e37cd1c4d04d9349d8df8","target":"graph","created_at":"2026-05-17T23:39:23Z","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 two-player zero-sum stochastic games, where two competing players make decisions under uncertainty, a pair of optimal strategies is traditionally described by Nash equilibrium and computed under the assumption that the players have perfect information about the stochastic transition model of the environment. However, implementing such strategies may make the players vulnerable to unforeseen changes in the environment. In this paper, we introduce entropy-regularized stochastic games where each player aims to maximize the causal entropy of its strategy in addition to its expected payoff. The ","authors_text":"Mohamadreza Ahmadi, Takashi Tanaka, Ufuk Topcu, Yagiz Savas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-26T12:52:57Z","title":"Entropy-Regularized Stochastic Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11543","kind":"arxiv","version":2},"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:d7545767900e01c1308d4cd21a9caee0501ec09c8cd30f0b0ce0a3ac6508b36e","target":"record","created_at":"2026-05-17T23:39:23Z","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":"1c13f27cea9e41df1b4595b55119a91b963236cde8a1365c27cbf358893ff4d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-07-26T12:52:57Z","title_canon_sha256":"acbf6cd1e3c9b68f583aebec6e27115d348094ba75cc31e2eba8fd9ddc8b4fc4"},"schema_version":"1.0","source":{"id":"1907.11543","kind":"arxiv","version":2}},"canonical_sha256":"433ec9376aff2310096d57d8a8c0d240592d7d43327f0ed257784bbac082dd80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"433ec9376aff2310096d57d8a8c0d240592d7d43327f0ed257784bbac082dd80","first_computed_at":"2026-05-17T23:39:23.380931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:23.380931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vpl8k3fCSA5g8zVq4R7YkYMvckB0fm5g7QKPl5BYc3wcs6vE93Ld2nsPYi1Ct0/NceMJd4LkKD3o6oZv72tfBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:23.381760Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.11543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7545767900e01c1308d4cd21a9caee0501ec09c8cd30f0b0ce0a3ac6508b36e","sha256:ebb4e7e88098ba12733a69b840115fa530fdeb720f2e37cd1c4d04d9349d8df8"],"state_sha256":"2802395761d0c96358bc2127ee748f09d7a776ee1b93788f33d3b5e0f879249d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4B5f8QR8o5Vg1xAUywufxw5Le1HpySSVbAaLFVoKrVy1loekcLPYXPMD1BcT8CNVhNNyDRoE/PteTxWMfxBvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:03:33.424074Z","bundle_sha256":"44ff0a0742a75d74bdf29395c552942a42427fdcbafb3d99c7dacd1f6829c418"}}