{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:URTNIFOBS5WJO5EL5PPSI5YV3Y","short_pith_number":"pith:URTNIFOB","canonical_record":{"source":{"id":"2606.23995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:05:01Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"ceb06a33fec482f9f88fba31ffbb2f6d38645e41b0e346fb9490dc25bcc564e0","abstract_canon_sha256":"ff8b02e964330cc76191944b93663593c41309069b74b47a3fb8ce4a93b85caf"},"schema_version":"1.0"},"canonical_sha256":"a466d415c1976c97748bebdf247715de07c53270931f395e10a93e2a69c69b2b","source":{"kind":"arxiv","id":"2606.23995","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23995","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23995v1","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23995","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"URTNIFOBS5WJ","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"URTNIFOBS5WJO5EL","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"URTNIFOB","created_at":"2026-06-24T00:14:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:URTNIFOBS5WJO5EL5PPSI5YV3Y","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:05:01Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"ceb06a33fec482f9f88fba31ffbb2f6d38645e41b0e346fb9490dc25bcc564e0","abstract_canon_sha256":"ff8b02e964330cc76191944b93663593c41309069b74b47a3fb8ce4a93b85caf"},"schema_version":"1.0"},"canonical_sha256":"a466d415c1976c97748bebdf247715de07c53270931f395e10a93e2a69c69b2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:32.570591Z","signature_b64":"e47X0Iiv1SLSP0YcwF4Uop67qTUVVk7IgMCtc+wLjeROTlC1km56Ypjyi4kwfieRN9hURstN7C6oCvy2MXxCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a466d415c1976c97748bebdf247715de07c53270931f395e10a93e2a69c69b2b","last_reissued_at":"2026-06-24T00:14:32.570184Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:32.570184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23995","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":"2026-06-24T00:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6m0o86CxDw8iNHgvIezFaJRGyGYGM2ZVqQzadEgGksI2eIg5E6e5O2rU01bwFQbmwi//Van6VbSgVZ8+ggLiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T23:34:26.527584Z"},"content_sha256":"d3e8eb89b34c45b66fd1b8b89cc67bcebee190caa70b41a10b3a1421b3999376","schema_version":"1.0","event_id":"sha256:d3e8eb89b34c45b66fd1b8b89cc67bcebee190caa70b41a10b3a1421b3999376"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:URTNIFOBS5WJO5EL5PPSI5YV3Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Albert Wang, Chase McDonald, Eugene Vinitsky, JB Lanier, Nathan Tsang, Roy Fox, Tristan Maidment, Wesley N. Kerr","submitted_at":"2026-06-22T23:05:01Z","abstract_excerpt":"Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can match or exceed specialized game-theoretic algorithms for solving two-player zero-sum imperfect-information games. The uniform distribution has emerged as a strong policy regularization target for this purpose, but it regularizes equally toward all actions regardless of their viability. We introduce EMAgnet, which instead regularizes toward an exponential moving average (EMA) of the last-iterate policy's parameters, providing an adaptive regularization target that evolves with the agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23995","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/2606.23995/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":"2026-06-24T00:14:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+pk6qNildzc5THcq41QDY6yZPTgsE1sz9mZxNNVjrt3VPRMpHBPp+9CfhdtzSNmsgrQkH2TTGlgEoWz9dkijBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T23:34:26.527960Z"},"content_sha256":"2436767ac4d2f307cdf552f589dda6f3c32f4f039c30c1941c235ce23909ba02","schema_version":"1.0","event_id":"sha256:2436767ac4d2f307cdf552f589dda6f3c32f4f039c30c1941c235ce23909ba02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URTNIFOBS5WJO5EL5PPSI5YV3Y/bundle.json","state_url":"https://pith.science/pith/URTNIFOBS5WJO5EL5PPSI5YV3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URTNIFOBS5WJO5EL5PPSI5YV3Y/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":"2026-06-28T23:34:26Z","links":{"resolver":"https://pith.science/pith/URTNIFOBS5WJO5EL5PPSI5YV3Y","bundle":"https://pith.science/pith/URTNIFOBS5WJO5EL5PPSI5YV3Y/bundle.json","state":"https://pith.science/pith/URTNIFOBS5WJO5EL5PPSI5YV3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URTNIFOBS5WJO5EL5PPSI5YV3Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:URTNIFOBS5WJO5EL5PPSI5YV3Y","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":"ff8b02e964330cc76191944b93663593c41309069b74b47a3fb8ce4a93b85caf","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:05:01Z","title_canon_sha256":"ceb06a33fec482f9f88fba31ffbb2f6d38645e41b0e346fb9490dc25bcc564e0"},"schema_version":"1.0","source":{"id":"2606.23995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23995","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23995v1","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23995","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"pith_short_12","alias_value":"URTNIFOBS5WJ","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"pith_short_16","alias_value":"URTNIFOBS5WJO5EL","created_at":"2026-06-24T00:14:32Z"},{"alias_kind":"pith_short_8","alias_value":"URTNIFOB","created_at":"2026-06-24T00:14:32Z"}],"graph_snapshots":[{"event_id":"sha256:2436767ac4d2f307cdf552f589dda6f3c32f4f039c30c1941c235ce23909ba02","target":"graph","created_at":"2026-06-24T00:14:32Z","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/2606.23995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has established that regularized policy gradient methods such as PPO, when used in self-play, can match or exceed specialized game-theoretic algorithms for solving two-player zero-sum imperfect-information games. The uniform distribution has emerged as a strong policy regularization target for this purpose, but it regularizes equally toward all actions regardless of their viability. We introduce EMAgnet, which instead regularizes toward an exponential moving average (EMA) of the last-iterate policy's parameters, providing an adaptive regularization target that evolves with the agen","authors_text":"Albert Wang, Chase McDonald, Eugene Vinitsky, JB Lanier, Nathan Tsang, Roy Fox, Tristan Maidment, Wesley N. Kerr","cross_cats":["cs.AI","cs.GT","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:05:01Z","title":"EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23995","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:d3e8eb89b34c45b66fd1b8b89cc67bcebee190caa70b41a10b3a1421b3999376","target":"record","created_at":"2026-06-24T00:14:32Z","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":"ff8b02e964330cc76191944b93663593c41309069b74b47a3fb8ce4a93b85caf","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T23:05:01Z","title_canon_sha256":"ceb06a33fec482f9f88fba31ffbb2f6d38645e41b0e346fb9490dc25bcc564e0"},"schema_version":"1.0","source":{"id":"2606.23995","kind":"arxiv","version":1}},"canonical_sha256":"a466d415c1976c97748bebdf247715de07c53270931f395e10a93e2a69c69b2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a466d415c1976c97748bebdf247715de07c53270931f395e10a93e2a69c69b2b","first_computed_at":"2026-06-24T00:14:32.570184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:32.570184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e47X0Iiv1SLSP0YcwF4Uop67qTUVVk7IgMCtc+wLjeROTlC1km56Ypjyi4kwfieRN9hURstN7C6oCvy2MXxCAw==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:32.570591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3e8eb89b34c45b66fd1b8b89cc67bcebee190caa70b41a10b3a1421b3999376","sha256:2436767ac4d2f307cdf552f589dda6f3c32f4f039c30c1941c235ce23909ba02"],"state_sha256":"d721ef36b07b7b9672feee43d1a5db8d0edfa6baa1ea14639e4854f21dfc93ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cj7xzGEuBnUZukyL6IrY9jN0VO0eRZPuSf6JMYV481rL7JmP8Rpk9WsfbT7lqmjzDUBPpkqCQcKnwy7ZUQ4cAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T23:34:26.529892Z","bundle_sha256":"c450c88bafd8362a23c96aa9e6d2548220bbf4a3e0a7072680dbc13a960be888"}}