{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4NRC2BQW7TVOBAKZ6YWLZDB44A","short_pith_number":"pith:4NRC2BQW","canonical_record":{"source":{"id":"2602.12386","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-12T20:29:41Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"e5c8bf9912340e1a5d4fa45aca0e75d9d3178f5e7a48feeb11f63388966f719c","abstract_canon_sha256":"c8dcaaab48ca3462e01e62809e3d819244305626ba4b39bf9f6ba353a6f25123"},"schema_version":"1.0"},"canonical_sha256":"e3622d0616fceae08159f62cbc8c3ce036d84b92556111bdb6d4e719037fe786","source":{"kind":"arxiv","id":"2602.12386","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12386","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12386v2","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12386","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"pith_short_12","alias_value":"4NRC2BQW7TVO","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"pith_short_16","alias_value":"4NRC2BQW7TVOBAKZ","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"pith_short_8","alias_value":"4NRC2BQW","created_at":"2026-06-01T01:02:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4NRC2BQW7TVOBAKZ6YWLZDB44A","target":"record","payload":{"canonical_record":{"source":{"id":"2602.12386","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-12T20:29:41Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"e5c8bf9912340e1a5d4fa45aca0e75d9d3178f5e7a48feeb11f63388966f719c","abstract_canon_sha256":"c8dcaaab48ca3462e01e62809e3d819244305626ba4b39bf9f6ba353a6f25123"},"schema_version":"1.0"},"canonical_sha256":"e3622d0616fceae08159f62cbc8c3ce036d84b92556111bdb6d4e719037fe786","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:34.169074Z","signature_b64":"taV1kPnQK61zGix3zhfzFELcrL9I+rLIwRbUGLGTHGnSLgDjSv28BMmNlFX3K8pnCHMP1uKn4wLXu/MjexsrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3622d0616fceae08159f62cbc8c3ce036d84b92556111bdb6d4e719037fe786","last_reissued_at":"2026-06-01T01:02:34.168077Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:34.168077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.12386","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":"2026-06-01T01:02:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ZjlarQvjJDndKjaCO7CaPphId60r8NMY2eXbxdrELHVds+1LkV1o7NX9V44G1zbEuYSzdXLXL/vD8Flw4DICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:16:43.159697Z"},"content_sha256":"06a5d888c16f79f44c744275b0ce48cc1c9e6d97095888916d563c3d510735ef","schema_version":"1.0","event_id":"sha256:06a5d888c16f79f44c744275b0ce48cc1c9e6d97095888916d563c3d510735ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4NRC2BQW7TVOBAKZ6YWLZDB44A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Convergent Actor-Critic for MARL through Risk-aversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Eric Mazumdar, Yizhou Zhang","submitted_at":"2026-02-12T20:29:41Z","abstract_excerpt":"Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing stationary forms of classic game-theoretic equilibria is computationally intractable -- a stark contrast to the comparative ease of solving single-agent RL or zero-sum games. To bridge this gap, we study Risk-averse Quantal response Equilibria (RQE), a solution concept rooted in behavioral game theory that incorporates risk aversion and bounded rationality. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12386","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.12386/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xZ2hQXDPxj0raRkU2VPimFK76dQpO+T5czXLw4PwhsDwVHMqzEizuX1vEfRmsoXSJOe6yDyVdnjjLirSaaFUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:16:43.160086Z"},"content_sha256":"2ea275d160ea6212d73c3e2c5b159c5740be92f6c7ff2dffddcf725733666338","schema_version":"1.0","event_id":"sha256:2ea275d160ea6212d73c3e2c5b159c5740be92f6c7ff2dffddcf725733666338"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/bundle.json","state_url":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/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":"2026-06-01T21:16:43Z","links":{"resolver":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A","bundle":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/bundle.json","state":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4NRC2BQW7TVOBAKZ6YWLZDB44A","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":"c8dcaaab48ca3462e01e62809e3d819244305626ba4b39bf9f6ba353a6f25123","cross_cats_sorted":["cs.GT","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-12T20:29:41Z","title_canon_sha256":"e5c8bf9912340e1a5d4fa45aca0e75d9d3178f5e7a48feeb11f63388966f719c"},"schema_version":"1.0","source":{"id":"2602.12386","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12386","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12386v2","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12386","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"pith_short_12","alias_value":"4NRC2BQW7TVO","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"pith_short_16","alias_value":"4NRC2BQW7TVOBAKZ","created_at":"2026-06-01T01:02:34Z"},{"alias_kind":"pith_short_8","alias_value":"4NRC2BQW","created_at":"2026-06-01T01:02:34Z"}],"graph_snapshots":[{"event_id":"sha256:2ea275d160ea6212d73c3e2c5b159c5740be92f6c7ff2dffddcf725733666338","target":"graph","created_at":"2026-06-01T01:02:34Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.12386/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing stationary forms of classic game-theoretic equilibria is computationally intractable -- a stark contrast to the comparative ease of solving single-agent RL or zero-sum games. To bridge this gap, we study Risk-averse Quantal response Equilibria (RQE), a solution concept rooted in behavioral game theory that incorporates risk aversion and bounded rationality. We ","authors_text":"Eric Mazumdar, Yizhou Zhang","cross_cats":["cs.GT","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-12T20:29:41Z","title":"Provably Convergent Actor-Critic for MARL through Risk-aversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12386","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":"sha256:06a5d888c16f79f44c744275b0ce48cc1c9e6d97095888916d563c3d510735ef","target":"record","created_at":"2026-06-01T01:02:34Z","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":"c8dcaaab48ca3462e01e62809e3d819244305626ba4b39bf9f6ba353a6f25123","cross_cats_sorted":["cs.GT","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-12T20:29:41Z","title_canon_sha256":"e5c8bf9912340e1a5d4fa45aca0e75d9d3178f5e7a48feeb11f63388966f719c"},"schema_version":"1.0","source":{"id":"2602.12386","kind":"arxiv","version":2}},"canonical_sha256":"e3622d0616fceae08159f62cbc8c3ce036d84b92556111bdb6d4e719037fe786","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3622d0616fceae08159f62cbc8c3ce036d84b92556111bdb6d4e719037fe786","first_computed_at":"2026-06-01T01:02:34.168077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:34.168077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"taV1kPnQK61zGix3zhfzFELcrL9I+rLIwRbUGLGTHGnSLgDjSv28BMmNlFX3K8pnCHMP1uKn4wLXu/MjexsrAQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:34.169074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.12386","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06a5d888c16f79f44c744275b0ce48cc1c9e6d97095888916d563c3d510735ef","sha256:2ea275d160ea6212d73c3e2c5b159c5740be92f6c7ff2dffddcf725733666338"],"state_sha256":"19b0263b0412d929c417f9f10273b1aa6c1017fd3b4aff954b3c29763a274a51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0B7wwQWu5lWUx8qmavr8cUZh3PpckDnIijNClc1390gWaE6PW7e/RlQc5Q9Zr8w/rGr3GYsUUaJZUgdeqNP7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:16:43.162185Z","bundle_sha256":"ba75f89ab517cf6843033c73367848d159190f74759c4b1ef1040f1b851350c7"}}