{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CK7CWHU3E6YAN625H3TLBU5CTU","short_pith_number":"pith:CK7CWHU3","canonical_record":{"source":{"id":"1906.00190","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T09:18:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"71a0510405f4b279a36dac3ba1e15cd31b81a24ade8a40f368cb5e8aefa6bb5e","abstract_canon_sha256":"e7c7c889f3e57d744195bc8120bacdc2d2a7a44af984842778a4d63aeb139b07"},"schema_version":"1.0"},"canonical_sha256":"12be2b1e9b27b006fb5d3ee6b0d3a29d2c9b880a00ac86d333157e0dedcffcdb","source":{"kind":"arxiv","id":"1906.00190","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00190","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00190v5","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00190","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_12","alias_value":"CK7CWHU3E6YA","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_16","alias_value":"CK7CWHU3E6YAN625","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_8","alias_value":"CK7CWHU3","created_at":"2026-07-05T00:44:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CK7CWHU3E6YAN625H3TLBU5CTU","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00190","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T09:18:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"71a0510405f4b279a36dac3ba1e15cd31b81a24ade8a40f368cb5e8aefa6bb5e","abstract_canon_sha256":"e7c7c889f3e57d744195bc8120bacdc2d2a7a44af984842778a4d63aeb139b07"},"schema_version":"1.0"},"canonical_sha256":"12be2b1e9b27b006fb5d3ee6b0d3a29d2c9b880a00ac86d333157e0dedcffcdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:25.710746Z","signature_b64":"yC1ya784HsmBRgjiAM/GQb6F7blpPsq+clv7tIHYoOiLqYHRGB6PcRFXF0v/TXkH3qnNIuDHxPhg1h4CbMD3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12be2b1e9b27b006fb5d3ee6b0d3a29d2c9b880a00ac86d333157e0dedcffcdb","last_reissued_at":"2026-07-05T00:44:25.710264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:25.710264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00190","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:44:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"taRtEQEI0KxHusZt2CdmFSR89S0PpHfHOUtav33AafxJHhHd51o3BxX2hxZLB2HZA6ers3gUe0KhVH9FuDc4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:38:56.544861Z"},"content_sha256":"c2f3cfb6685d7d4197f76a75b11e438b6afc468d0a42738c5d8fbbe319500a2c","schema_version":"1.0","event_id":"sha256:c2f3cfb6685d7d4197f76a75b11e438b6afc468d0a42738c5d8fbbe319500a2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CK7CWHU3E6YAN625H3TLBU5CTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Replicator Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Audrunas Gruslys, Daniel Hennes, Dustin Morrill, Edgar Duenez-Guzman, Jean-Baptiste Lespiau, Julien Perolat, Karl Tuyls, Marc Lanctot, Paavo Parmas, Remi Munos, Shayegan Omidshafiei","submitted_at":"2019-06-01T09:18:48Z","abstract_excerpt":"Policy gradient and actor-critic algorithms form the basis of many commonly used training techniques in deep reinforcement learning. Using these algorithms in multiagent environments poses problems such as nonstationarity and instability. In this paper, we first demonstrate that standard softmax-based policy gradient can be prone to poor performance in the presence of even the most benign nonstationarity. By contrast, it is known that the replicator dynamics, a well-studied model from evolutionary game theory, eliminates dominated strategies and exhibits convergence of the time-averaged trajec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00190","kind":"arxiv","version":5},"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/1906.00190/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":"2026-07-05T00:44:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yX2qFCJ3b+u65JTt/loxM3nel5+8nkD+Bmizvkqg3AbjaQP/8oyMoQKKvtdMuhNZT7368asNXRdK57U0gtgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T14:38:56.545247Z"},"content_sha256":"d8d1e386472906b67e31a77907d58e8d17c46486379f7dfcd5e2ef468b583b56","schema_version":"1.0","event_id":"sha256:d8d1e386472906b67e31a77907d58e8d17c46486379f7dfcd5e2ef468b583b56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CK7CWHU3E6YAN625H3TLBU5CTU/bundle.json","state_url":"https://pith.science/pith/CK7CWHU3E6YAN625H3TLBU5CTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CK7CWHU3E6YAN625H3TLBU5CTU/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":"2026-07-05T14:38:56Z","links":{"resolver":"https://pith.science/pith/CK7CWHU3E6YAN625H3TLBU5CTU","bundle":"https://pith.science/pith/CK7CWHU3E6YAN625H3TLBU5CTU/bundle.json","state":"https://pith.science/pith/CK7CWHU3E6YAN625H3TLBU5CTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CK7CWHU3E6YAN625H3TLBU5CTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CK7CWHU3E6YAN625H3TLBU5CTU","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":"e7c7c889f3e57d744195bc8120bacdc2d2a7a44af984842778a4d63aeb139b07","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T09:18:48Z","title_canon_sha256":"71a0510405f4b279a36dac3ba1e15cd31b81a24ade8a40f368cb5e8aefa6bb5e"},"schema_version":"1.0","source":{"id":"1906.00190","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00190","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00190v5","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00190","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_12","alias_value":"CK7CWHU3E6YA","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_16","alias_value":"CK7CWHU3E6YAN625","created_at":"2026-07-05T00:44:25Z"},{"alias_kind":"pith_short_8","alias_value":"CK7CWHU3","created_at":"2026-07-05T00:44:25Z"}],"graph_snapshots":[{"event_id":"sha256:d8d1e386472906b67e31a77907d58e8d17c46486379f7dfcd5e2ef468b583b56","target":"graph","created_at":"2026-07-05T00:44:25Z","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/1906.00190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient and actor-critic algorithms form the basis of many commonly used training techniques in deep reinforcement learning. Using these algorithms in multiagent environments poses problems such as nonstationarity and instability. In this paper, we first demonstrate that standard softmax-based policy gradient can be prone to poor performance in the presence of even the most benign nonstationarity. By contrast, it is known that the replicator dynamics, a well-studied model from evolutionary game theory, eliminates dominated strategies and exhibits convergence of the time-averaged trajec","authors_text":"Audrunas Gruslys, Daniel Hennes, Dustin Morrill, Edgar Duenez-Guzman, Jean-Baptiste Lespiau, Julien Perolat, Karl Tuyls, Marc Lanctot, Paavo Parmas, Remi Munos, Shayegan Omidshafiei","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T09:18:48Z","title":"Neural Replicator Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00190","kind":"arxiv","version":5},"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:c2f3cfb6685d7d4197f76a75b11e438b6afc468d0a42738c5d8fbbe319500a2c","target":"record","created_at":"2026-07-05T00:44:25Z","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":"e7c7c889f3e57d744195bc8120bacdc2d2a7a44af984842778a4d63aeb139b07","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T09:18:48Z","title_canon_sha256":"71a0510405f4b279a36dac3ba1e15cd31b81a24ade8a40f368cb5e8aefa6bb5e"},"schema_version":"1.0","source":{"id":"1906.00190","kind":"arxiv","version":5}},"canonical_sha256":"12be2b1e9b27b006fb5d3ee6b0d3a29d2c9b880a00ac86d333157e0dedcffcdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12be2b1e9b27b006fb5d3ee6b0d3a29d2c9b880a00ac86d333157e0dedcffcdb","first_computed_at":"2026-07-05T00:44:25.710264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:25.710264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yC1ya784HsmBRgjiAM/GQb6F7blpPsq+clv7tIHYoOiLqYHRGB6PcRFXF0v/TXkH3qnNIuDHxPhg1h4CbMD3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:25.710746Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00190","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2f3cfb6685d7d4197f76a75b11e438b6afc468d0a42738c5d8fbbe319500a2c","sha256:d8d1e386472906b67e31a77907d58e8d17c46486379f7dfcd5e2ef468b583b56"],"state_sha256":"c3948f6c8f3bf800e9fcce2290bc2077eceb5e9f5d81122c749771cdd8f86287"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RvNXTyj5qyEjnJBMLMb27mu07gOWl6j3ESSRdWU79gfeP+1jbiC1sGA+RRkjkqJc/Uev2+ceYJkg0OATN8caDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T14:38:56.547777Z","bundle_sha256":"4110ab5a6b08ff74bbff8d196144fc37a21945fbbc5bd7907a462d6cbe9bea66"}}