{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F7X3X6UNIIDNQRKOFG6B6W74N7","short_pith_number":"pith:F7X3X6UN","canonical_record":{"source":{"id":"2202.00872","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-02-02T04:32:11Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"3927577c4ffbc4cc661ae788f761ea2ed03c598e980a6668f97be9e4496b8068","abstract_canon_sha256":"1ece58a601a2827e3ae348860e2bdc87f6d2ecf08e806df3db1064a0c23d4f76"},"schema_version":"1.0"},"canonical_sha256":"2fefbbfa8d4206d8454e29bc1f5bfc6fe1779d91c6689c83da48e484cefe41db","source":{"kind":"arxiv","id":"2202.00872","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00872","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00872v2","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00872","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_12","alias_value":"F7X3X6UNIIDN","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_16","alias_value":"F7X3X6UNIIDNQRKO","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_8","alias_value":"F7X3X6UN","created_at":"2026-07-05T05:11:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F7X3X6UNIIDNQRKOFG6B6W74N7","target":"record","payload":{"canonical_record":{"source":{"id":"2202.00872","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-02-02T04:32:11Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"3927577c4ffbc4cc661ae788f761ea2ed03c598e980a6668f97be9e4496b8068","abstract_canon_sha256":"1ece58a601a2827e3ae348860e2bdc87f6d2ecf08e806df3db1064a0c23d4f76"},"schema_version":"1.0"},"canonical_sha256":"2fefbbfa8d4206d8454e29bc1f5bfc6fe1779d91c6689c83da48e484cefe41db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:36.762529Z","signature_b64":"oaJQQoeR+pvkj1y8wCEtDudn4Xf5h77+oerl2e4dlHSPK1ZdL/I2fVuFWJ7QUzlF7L/6a4t2OJZ/wQrhh+tBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fefbbfa8d4206d8454e29bc1f5bfc6fe1779d91c6689c83da48e484cefe41db","last_reissued_at":"2026-07-05T05:11:36.762092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:36.762092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.00872","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":"2026-07-05T05:11:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udmcZ07QPesTNvmP+swEVNsr8ErOguldfTg9iMmmpeK2VUIhk8ZZCtgs4n212j/PM6mBYk6U+sce7au7nMJzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:16.776136Z"},"content_sha256":"e87b661495ba427243d7203da93037102db85f439f8fa078afe61eff9420124c","schema_version":"1.0","event_id":"sha256:e87b661495ba427243d7203da93037102db85f439f8fa078afe61eff9420124c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F7X3X6UNIIDNQRKOFG6B6W74N7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"math.OC","authors_text":"Bo Dai, Dale Schuurmans, Jincheng Mei, Na Li, Runyu Zhang","submitted_at":"2022-02-02T04:32:11Z","abstract_excerpt":"Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central coordination introduces significant additional difficulties in the convergence analysis. Even for a stochastic game with identical interest, there can be multiple Nash Equilibria (NEs), which disables proof techniques that rely on the existence of a unique global optimum. Moreover, the softmax parameterization introduces non-NE policies with zero gradient, making "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00872","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/2202.00872/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":"2026-07-05T05:11:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8kt5MPjFyBjcAehsLKm5VdY/pOTqsbT/4MC9UqDjS8pKKSacVUaTDQottVm9S8Ssna+JNmZimxVUF0dOJSI8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:43:16.776526Z"},"content_sha256":"231e72f17ccf92fde6eb3d61013d87267acd3fb47a8189c63fce9147d1f18a73","schema_version":"1.0","event_id":"sha256:231e72f17ccf92fde6eb3d61013d87267acd3fb47a8189c63fce9147d1f18a73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7X3X6UNIIDNQRKOFG6B6W74N7/bundle.json","state_url":"https://pith.science/pith/F7X3X6UNIIDNQRKOFG6B6W74N7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7X3X6UNIIDNQRKOFG6B6W74N7/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":"2026-07-07T08:43:16Z","links":{"resolver":"https://pith.science/pith/F7X3X6UNIIDNQRKOFG6B6W74N7","bundle":"https://pith.science/pith/F7X3X6UNIIDNQRKOFG6B6W74N7/bundle.json","state":"https://pith.science/pith/F7X3X6UNIIDNQRKOFG6B6W74N7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7X3X6UNIIDNQRKOFG6B6W74N7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F7X3X6UNIIDNQRKOFG6B6W74N7","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":"1ece58a601a2827e3ae348860e2bdc87f6d2ecf08e806df3db1064a0c23d4f76","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-02-02T04:32:11Z","title_canon_sha256":"3927577c4ffbc4cc661ae788f761ea2ed03c598e980a6668f97be9e4496b8068"},"schema_version":"1.0","source":{"id":"2202.00872","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00872","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00872v2","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00872","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_12","alias_value":"F7X3X6UNIIDN","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_16","alias_value":"F7X3X6UNIIDNQRKO","created_at":"2026-07-05T05:11:36Z"},{"alias_kind":"pith_short_8","alias_value":"F7X3X6UN","created_at":"2026-07-05T05:11:36Z"}],"graph_snapshots":[{"event_id":"sha256:231e72f17ccf92fde6eb3d61013d87267acd3fb47a8189c63fce9147d1f18a73","target":"graph","created_at":"2026-07-05T05:11:36Z","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/2202.00872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central coordination introduces significant additional difficulties in the convergence analysis. Even for a stochastic game with identical interest, there can be multiple Nash Equilibria (NEs), which disables proof techniques that rely on the existence of a unique global optimum. Moreover, the softmax parameterization introduces non-NE policies with zero gradient, making ","authors_text":"Bo Dai, Dale Schuurmans, Jincheng Mei, Na Li, Runyu Zhang","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-02-02T04:32:11Z","title":"On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00872","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:e87b661495ba427243d7203da93037102db85f439f8fa078afe61eff9420124c","target":"record","created_at":"2026-07-05T05:11:36Z","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":"1ece58a601a2827e3ae348860e2bdc87f6d2ecf08e806df3db1064a0c23d4f76","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-02-02T04:32:11Z","title_canon_sha256":"3927577c4ffbc4cc661ae788f761ea2ed03c598e980a6668f97be9e4496b8068"},"schema_version":"1.0","source":{"id":"2202.00872","kind":"arxiv","version":2}},"canonical_sha256":"2fefbbfa8d4206d8454e29bc1f5bfc6fe1779d91c6689c83da48e484cefe41db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fefbbfa8d4206d8454e29bc1f5bfc6fe1779d91c6689c83da48e484cefe41db","first_computed_at":"2026-07-05T05:11:36.762092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:36.762092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oaJQQoeR+pvkj1y8wCEtDudn4Xf5h77+oerl2e4dlHSPK1ZdL/I2fVuFWJ7QUzlF7L/6a4t2OJZ/wQrhh+tBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:36.762529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00872","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e87b661495ba427243d7203da93037102db85f439f8fa078afe61eff9420124c","sha256:231e72f17ccf92fde6eb3d61013d87267acd3fb47a8189c63fce9147d1f18a73"],"state_sha256":"3d412a5e01c69bfe3c68fc9f24a91f75205506951fcdc740cf924985610cda12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"muiGla2Ede9H7Rw9PWVcF1v5IUT0Z8fNcbuza1xJruOui05QkVk/D7kglGjj+OXUNpnXTEwW9gDCqQwOPjeMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:43:16.778594Z","bundle_sha256":"8e5855a72051ccd46fbb8dcfa31a861fc0608c19b9a4b105b5e3e5becd2e4619"}}