{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CEQ5VLIUKUUFI4ONHIPYUHE4KQ","short_pith_number":"pith:CEQ5VLIU","canonical_record":{"source":{"id":"2504.20593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T09:46:16Z","cross_cats_sorted":[],"title_canon_sha256":"5dd334f2bab02a58b89cdd1e40c2ddf37217fa2f47c34fffd1a129ff373baf17","abstract_canon_sha256":"444cc94a790fd8a749baa28f1fbb3f2ad82067d11a4ec6cb1a6ea3296ce8806e"},"schema_version":"1.0"},"canonical_sha256":"1121daad1455285471cd3a1f8a1c9c5438d05f5d3b7bf911f497e89d6e1033cb","source":{"kind":"arxiv","id":"2504.20593","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20593","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20593v1","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20593","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"pith_short_12","alias_value":"CEQ5VLIUKUUF","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"pith_short_16","alias_value":"CEQ5VLIUKUUFI4ON","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"pith_short_8","alias_value":"CEQ5VLIU","created_at":"2026-07-05T10:55:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CEQ5VLIUKUUFI4ONHIPYUHE4KQ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.20593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T09:46:16Z","cross_cats_sorted":[],"title_canon_sha256":"5dd334f2bab02a58b89cdd1e40c2ddf37217fa2f47c34fffd1a129ff373baf17","abstract_canon_sha256":"444cc94a790fd8a749baa28f1fbb3f2ad82067d11a4ec6cb1a6ea3296ce8806e"},"schema_version":"1.0"},"canonical_sha256":"1121daad1455285471cd3a1f8a1c9c5438d05f5d3b7bf911f497e89d6e1033cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:45.251163Z","signature_b64":"f78eWYbYRtyrhyfPH/UxfWFwTLY9ACzpy2hqKk1QCf2yG9nHEbEMeCq2ST7GuRqp4fQMqNytnAWAgmsjBuNqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1121daad1455285471cd3a1f8a1c9c5438d05f5d3b7bf911f497e89d6e1033cb","last_reissued_at":"2026-07-05T10:55:45.250657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:45.250657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.20593","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:55:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xinVvMHYFFpBh2H6TkTWwGvVK1PXSSbVX0DKSAalbNcTAHAsFidQZLDEpXqnN2cYAkpuWbBv6YeLl50yTVsTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:43:30.775121Z"},"content_sha256":"a803fa51add1519d94f724f5cb85bd8f53c355bd3701ea73f3536d0dbe894d16","schema_version":"1.0","event_id":"sha256:a803fa51add1519d94f724f5cb85bd8f53c355bd3701ea73f3536d0dbe894d16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CEQ5VLIUKUUFI4ONHIPYUHE4KQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Independent Learning in Performative Markov Potential Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debmalya Mandal, Goran Radanovi\\'c, Paulius Sasnauskas, Rilind Sahitaj, Yi\\u{g}it Yal{\\i}n","submitted_at":"2025-04-29T09:46:16Z","abstract_excerpt":"Performative Reinforcement Learning (PRL) refers to a scenario in which the deployed policy changes the reward and transition dynamics of the underlying environment. In this work, we study multi-agent PRL by incorporating performative effects into Markov Potential Games (MPGs). We introduce the notion of a performatively stable equilibrium (PSE) and show that it always exists under a reasonable sensitivity assumption. We then provide convergence results for state-of-the-art algorithms used to solve MPGs. Specifically, we show that independent policy gradient ascent (IPGA) and independent natur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20593","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/2504.20593/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":"2026-07-05T10:55:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lip9SiXe1HdIW/LXzqBY/uB3jLxuFm7uSj3yxTP5FahuPeadg+e4utfwZECPpI4ikXmnj5Dosta5hWMX8AdZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:43:30.775927Z"},"content_sha256":"4a91b760a12ccc5a061340a917ebfa96ddeb1eff1f0f50383f408b4b968ee0c7","schema_version":"1.0","event_id":"sha256:4a91b760a12ccc5a061340a917ebfa96ddeb1eff1f0f50383f408b4b968ee0c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/bundle.json","state_url":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/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":"2026-08-16T21:43:30Z","links":{"resolver":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ","bundle":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/bundle.json","state":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CEQ5VLIUKUUFI4ONHIPYUHE4KQ","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":"444cc94a790fd8a749baa28f1fbb3f2ad82067d11a4ec6cb1a6ea3296ce8806e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T09:46:16Z","title_canon_sha256":"5dd334f2bab02a58b89cdd1e40c2ddf37217fa2f47c34fffd1a129ff373baf17"},"schema_version":"1.0","source":{"id":"2504.20593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20593","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20593v1","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20593","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"pith_short_12","alias_value":"CEQ5VLIUKUUF","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"pith_short_16","alias_value":"CEQ5VLIUKUUFI4ON","created_at":"2026-07-05T10:55:45Z"},{"alias_kind":"pith_short_8","alias_value":"CEQ5VLIU","created_at":"2026-07-05T10:55:45Z"}],"graph_snapshots":[{"event_id":"sha256:4a91b760a12ccc5a061340a917ebfa96ddeb1eff1f0f50383f408b4b968ee0c7","target":"graph","created_at":"2026-07-05T10:55:45Z","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/2504.20593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Performative Reinforcement Learning (PRL) refers to a scenario in which the deployed policy changes the reward and transition dynamics of the underlying environment. In this work, we study multi-agent PRL by incorporating performative effects into Markov Potential Games (MPGs). We introduce the notion of a performatively stable equilibrium (PSE) and show that it always exists under a reasonable sensitivity assumption. We then provide convergence results for state-of-the-art algorithms used to solve MPGs. Specifically, we show that independent policy gradient ascent (IPGA) and independent natur","authors_text":"Debmalya Mandal, Goran Radanovi\\'c, Paulius Sasnauskas, Rilind Sahitaj, Yi\\u{g}it Yal{\\i}n","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T09:46:16Z","title":"Independent Learning in Performative Markov Potential Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20593","kind":"arxiv","version":1},"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:a803fa51add1519d94f724f5cb85bd8f53c355bd3701ea73f3536d0dbe894d16","target":"record","created_at":"2026-07-05T10:55:45Z","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":"444cc94a790fd8a749baa28f1fbb3f2ad82067d11a4ec6cb1a6ea3296ce8806e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T09:46:16Z","title_canon_sha256":"5dd334f2bab02a58b89cdd1e40c2ddf37217fa2f47c34fffd1a129ff373baf17"},"schema_version":"1.0","source":{"id":"2504.20593","kind":"arxiv","version":1}},"canonical_sha256":"1121daad1455285471cd3a1f8a1c9c5438d05f5d3b7bf911f497e89d6e1033cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1121daad1455285471cd3a1f8a1c9c5438d05f5d3b7bf911f497e89d6e1033cb","first_computed_at":"2026-07-05T10:55:45.250657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:45.250657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f78eWYbYRtyrhyfPH/UxfWFwTLY9ACzpy2hqKk1QCf2yG9nHEbEMeCq2ST7GuRqp4fQMqNytnAWAgmsjBuNqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:45.251163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a803fa51add1519d94f724f5cb85bd8f53c355bd3701ea73f3536d0dbe894d16","sha256:4a91b760a12ccc5a061340a917ebfa96ddeb1eff1f0f50383f408b4b968ee0c7"],"state_sha256":"2054514d7b48d95ae325cc5b716da92b51053bb4d7826d0c0cee4ddb51cd3539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3uXKVNyV31Zs3FG/7auEdxeC6JlB0VTEzW7vFjCJt2MoBOvVYitFYnMWiPSJSBsZQtYvPCFtCNusHwh97boUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T21:43:30.784995Z","bundle_sha256":"b5078eee02f64ab24ce40b17ad307d950befc7ff6d83b42ef797902c80db1b55"}}