{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:I65B5MFL3PAUHXPPHO7OXVNL4J","short_pith_number":"pith:I65B5MFL","canonical_record":{"source":{"id":"2103.01955","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T18:59:56Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"ff1cae787cb842e2c779268bb68ba50d0652b65332830b16dc3ae4b03a0beb05","abstract_canon_sha256":"25cfe06cc57a0d64fab7ae2711b24ae779c6972aa14a24a531b220bdae65f992"},"schema_version":"1.0"},"canonical_sha256":"47ba1eb0abdbc143ddef3bbeebd5abe2513997e3600efc9ebf98fb11d34944db","source":{"kind":"arxiv","id":"2103.01955","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.01955","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.01955v4","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01955","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"I65B5MFL3PAU","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"pith_short_16","alias_value":"I65B5MFL3PAUHXPP","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"pith_short_8","alias_value":"I65B5MFL","created_at":"2026-07-05T05:13:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:I65B5MFL3PAUHXPPHO7OXVNL4J","target":"record","payload":{"canonical_record":{"source":{"id":"2103.01955","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T18:59:56Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"ff1cae787cb842e2c779268bb68ba50d0652b65332830b16dc3ae4b03a0beb05","abstract_canon_sha256":"25cfe06cc57a0d64fab7ae2711b24ae779c6972aa14a24a531b220bdae65f992"},"schema_version":"1.0"},"canonical_sha256":"47ba1eb0abdbc143ddef3bbeebd5abe2513997e3600efc9ebf98fb11d34944db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:03.827750Z","signature_b64":"dMs8InzkX2G0SijgjKhc5B2j+Ohk6rqLVYdzhAh9B1MVLkJPcuOwdJgKxEB8E+R6cur925+ImMxVqhaL9WJTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47ba1eb0abdbc143ddef3bbeebd5abe2513997e3600efc9ebf98fb11d34944db","last_reissued_at":"2026-07-05T05:13:03.827391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:03.827391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.01955","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PR+HPfpwAWmkkrmIJt4m+g6nqr3S6vIpHqWLCrpIf8kWGoHcEKLU//HMsLoVFbLujTtXqDKU7gdMCWHI6jzVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:26:15.127405Z"},"content_sha256":"f42f33c585e71295d0c202e8ba0a805da4f1bc44f8d4284c637c981f32a02ede","schema_version":"1.0","event_id":"sha256:f42f33c585e71295d0c202e8ba0a805da4f1bc44f8d4284c637c981f32a02ede"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:I65B5MFL3PAUHXPPHO7OXVNL4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Akash Velu, Alexandre Bayen, Chao Yu, Eugene Vinitsky, Jiaxuan Gao, Yi Wu, Yu Wang","submitted_at":"2021-03-02T18:59:56Z","abstract_excerpt":"Proximal Policy Optimization (PPO) is a ubiquitous on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems. In this work, we carefully study the performance of PPO in cooperative multi-agent settings. We show that PPO-based multi-agent algorithms achieve surprisingly strong performance in four popular multi-agent testbeds: the particle-world environments, the StarCraft multi-agent challe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01955","kind":"arxiv","version":4},"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/2103.01955/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":"2026-07-05T05:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1x8AG04viuhV2xqXvExOO5mh0lO20zpkZSu39RBO2SiApfG3zsRdSwU9Tu+dJBo22D1mAAQuLM7hiHk/SBNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:26:15.127780Z"},"content_sha256":"5ac7e6cce80f802ddc357ed464169da68c3d22c664c9c0bdd68adf687b2cf5e5","schema_version":"1.0","event_id":"sha256:5ac7e6cce80f802ddc357ed464169da68c3d22c664c9c0bdd68adf687b2cf5e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I65B5MFL3PAUHXPPHO7OXVNL4J/bundle.json","state_url":"https://pith.science/pith/I65B5MFL3PAUHXPPHO7OXVNL4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I65B5MFL3PAUHXPPHO7OXVNL4J/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":"2026-07-07T09:26:15Z","links":{"resolver":"https://pith.science/pith/I65B5MFL3PAUHXPPHO7OXVNL4J","bundle":"https://pith.science/pith/I65B5MFL3PAUHXPPHO7OXVNL4J/bundle.json","state":"https://pith.science/pith/I65B5MFL3PAUHXPPHO7OXVNL4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I65B5MFL3PAUHXPPHO7OXVNL4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:I65B5MFL3PAUHXPPHO7OXVNL4J","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":"25cfe06cc57a0d64fab7ae2711b24ae779c6972aa14a24a531b220bdae65f992","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T18:59:56Z","title_canon_sha256":"ff1cae787cb842e2c779268bb68ba50d0652b65332830b16dc3ae4b03a0beb05"},"schema_version":"1.0","source":{"id":"2103.01955","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.01955","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.01955v4","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.01955","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"I65B5MFL3PAU","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"pith_short_16","alias_value":"I65B5MFL3PAUHXPP","created_at":"2026-07-05T05:13:03Z"},{"alias_kind":"pith_short_8","alias_value":"I65B5MFL","created_at":"2026-07-05T05:13:03Z"}],"graph_snapshots":[{"event_id":"sha256:5ac7e6cce80f802ddc357ed464169da68c3d22c664c9c0bdd68adf687b2cf5e5","target":"graph","created_at":"2026-07-05T05:13:03Z","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/2103.01955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proximal Policy Optimization (PPO) is a ubiquitous on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems. In this work, we carefully study the performance of PPO in cooperative multi-agent settings. We show that PPO-based multi-agent algorithms achieve surprisingly strong performance in four popular multi-agent testbeds: the particle-world environments, the StarCraft multi-agent challe","authors_text":"Akash Velu, Alexandre Bayen, Chao Yu, Eugene Vinitsky, Jiaxuan Gao, Yi Wu, Yu Wang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T18:59:56Z","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.01955","kind":"arxiv","version":4},"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:f42f33c585e71295d0c202e8ba0a805da4f1bc44f8d4284c637c981f32a02ede","target":"record","created_at":"2026-07-05T05:13:03Z","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":"25cfe06cc57a0d64fab7ae2711b24ae779c6972aa14a24a531b220bdae65f992","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-02T18:59:56Z","title_canon_sha256":"ff1cae787cb842e2c779268bb68ba50d0652b65332830b16dc3ae4b03a0beb05"},"schema_version":"1.0","source":{"id":"2103.01955","kind":"arxiv","version":4}},"canonical_sha256":"47ba1eb0abdbc143ddef3bbeebd5abe2513997e3600efc9ebf98fb11d34944db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47ba1eb0abdbc143ddef3bbeebd5abe2513997e3600efc9ebf98fb11d34944db","first_computed_at":"2026-07-05T05:13:03.827391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:03.827391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dMs8InzkX2G0SijgjKhc5B2j+Ohk6rqLVYdzhAh9B1MVLkJPcuOwdJgKxEB8E+R6cur925+ImMxVqhaL9WJTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:03.827750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.01955","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f42f33c585e71295d0c202e8ba0a805da4f1bc44f8d4284c637c981f32a02ede","sha256:5ac7e6cce80f802ddc357ed464169da68c3d22c664c9c0bdd68adf687b2cf5e5"],"state_sha256":"0174a0750eeec690666ac6281893c9b4ff4491d702aed68066855bda4d3ad936"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+veW2jIX3x5fJE6Rs3ny4i6cYEexYywzqbqcRX56MZLl0Jbfd+ziV55oEAZVbFge5IlbkfUC/IaQas6XRPPUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:26:15.129624Z","bundle_sha256":"3288780815b61b126e893b094c934e06597d1aa6e61158852279e84a2f9a626f"}}