{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZGEZF5KU5UCPELO7ZYW3XNDWQ7","short_pith_number":"pith:ZGEZF5KU","canonical_record":{"source":{"id":"1907.09467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-20T05:13:53Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8a52ca937baaa2e972295f36d93c4d3ddcd5f81ea532d4432b8faa529eee5794","abstract_canon_sha256":"751d19433c3e730d012a23762e9f2c9b502b24a2926708ba64159871a929e541"},"schema_version":"1.0"},"canonical_sha256":"c98992f554ed04f22ddfce2dbbb47687d5d9a221ff5bccc0e63e337444c0289a","source":{"kind":"arxiv","id":"1907.09467","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.09467","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"1907.09467v1","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09467","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZGEZF5KU5UCP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZGEZF5KU5UCPELO7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZGEZF5KU","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZGEZF5KU5UCPELO7ZYW3XNDWQ7","target":"record","payload":{"canonical_record":{"source":{"id":"1907.09467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-20T05:13:53Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8a52ca937baaa2e972295f36d93c4d3ddcd5f81ea532d4432b8faa529eee5794","abstract_canon_sha256":"751d19433c3e730d012a23762e9f2c9b502b24a2926708ba64159871a929e541"},"schema_version":"1.0"},"canonical_sha256":"c98992f554ed04f22ddfce2dbbb47687d5d9a221ff5bccc0e63e337444c0289a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:53.147619Z","signature_b64":"wHcVlfgtwJqRuytt51FMf6aIX5JyZnbZmyDIg4qggkPnyBWE59J7Anp2MX0X7HSvGGtkLZ3dDaEDPqfbhCIQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98992f554ed04f22ddfce2dbbb47687d5d9a221ff5bccc0e63e337444c0289a","last_reissued_at":"2026-05-17T23:39:53.147012Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:53.147012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.09467","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":"2026-05-17T23:39:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bnq2o+rlYfI1yFOA58bkiscOb9mPg6U4a8SJhp0NUT46ZMVNhMnqNECicLPnr7OPVVysgXlSYfX26PGA9uY6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:02:53.381782Z"},"content_sha256":"919eccf13631ffefb62d540a900aa88dbddd4374606cf5a3a480399b57b9a1f5","schema_version":"1.0","event_id":"sha256:919eccf13631ffefb62d540a900aa88dbddd4374606cf5a3a480399b57b9a1f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZGEZF5KU5UCPELO7ZYW3XNDWQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Arena: a toolkit for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jiechao Xiong, Lei Han, Meng Fang, Peng Sun, Qing Wang, Xinghai Sun, Zhengyou Zhang, Zhuobin Zheng","submitted_at":"2019-07-20T05:13:53Z","abstract_excerpt":"We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research. In MARL, it usually requires customizing observations, rewards and actions for each agent, changing cooperative-competitive agent-interaction, and playing with/against a third-party agent, etc. We provide a novel modular design, called Interface, for manipulating such routines in essentially two ways: 1) Different interfaces can be concatenated and combined, which extends the OpenAI Gym Wrappers concept to MARL scenarios. 2) During MARL training or testing, interfaces can be embedded in either wrapped OpenAI "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09467","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":""},"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":"2026-05-17T23:39:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MYr7eK7zB8C4ynQ7u0LfSzUa9Ze1/7AsBeQjSqAAkZ338XqGqgOdlMJENQiBRCkx5K1c4/eNlUJlvh8qAJJGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:02:53.382555Z"},"content_sha256":"fa1e906a8a9cd66fab2a27d293d5bacb6f32ee80ab1dab2d871a4aabc10670ac","schema_version":"1.0","event_id":"sha256:fa1e906a8a9cd66fab2a27d293d5bacb6f32ee80ab1dab2d871a4aabc10670ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZGEZF5KU5UCPELO7ZYW3XNDWQ7/bundle.json","state_url":"https://pith.science/pith/ZGEZF5KU5UCPELO7ZYW3XNDWQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZGEZF5KU5UCPELO7ZYW3XNDWQ7/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":"2026-06-06T09:02:53Z","links":{"resolver":"https://pith.science/pith/ZGEZF5KU5UCPELO7ZYW3XNDWQ7","bundle":"https://pith.science/pith/ZGEZF5KU5UCPELO7ZYW3XNDWQ7/bundle.json","state":"https://pith.science/pith/ZGEZF5KU5UCPELO7ZYW3XNDWQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZGEZF5KU5UCPELO7ZYW3XNDWQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZGEZF5KU5UCPELO7ZYW3XNDWQ7","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":"751d19433c3e730d012a23762e9f2c9b502b24a2926708ba64159871a929e541","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-20T05:13:53Z","title_canon_sha256":"8a52ca937baaa2e972295f36d93c4d3ddcd5f81ea532d4432b8faa529eee5794"},"schema_version":"1.0","source":{"id":"1907.09467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.09467","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"1907.09467v1","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09467","created_at":"2026-05-17T23:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZGEZF5KU5UCP","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZGEZF5KU5UCPELO7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZGEZF5KU","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:fa1e906a8a9cd66fab2a27d293d5bacb6f32ee80ab1dab2d871a4aabc10670ac","target":"graph","created_at":"2026-05-17T23:39:53Z","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"},"paper":{"abstract_excerpt":"We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research. In MARL, it usually requires customizing observations, rewards and actions for each agent, changing cooperative-competitive agent-interaction, and playing with/against a third-party agent, etc. We provide a novel modular design, called Interface, for manipulating such routines in essentially two ways: 1) Different interfaces can be concatenated and combined, which extends the OpenAI Gym Wrappers concept to MARL scenarios. 2) During MARL training or testing, interfaces can be embedded in either wrapped OpenAI ","authors_text":"Jiechao Xiong, Lei Han, Meng Fang, Peng Sun, Qing Wang, Xinghai Sun, Zhengyou Zhang, Zhuobin Zheng","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-20T05:13:53Z","title":"Arena: a toolkit for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09467","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":"sha256:919eccf13631ffefb62d540a900aa88dbddd4374606cf5a3a480399b57b9a1f5","target":"record","created_at":"2026-05-17T23:39:53Z","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":"751d19433c3e730d012a23762e9f2c9b502b24a2926708ba64159871a929e541","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-20T05:13:53Z","title_canon_sha256":"8a52ca937baaa2e972295f36d93c4d3ddcd5f81ea532d4432b8faa529eee5794"},"schema_version":"1.0","source":{"id":"1907.09467","kind":"arxiv","version":1}},"canonical_sha256":"c98992f554ed04f22ddfce2dbbb47687d5d9a221ff5bccc0e63e337444c0289a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c98992f554ed04f22ddfce2dbbb47687d5d9a221ff5bccc0e63e337444c0289a","first_computed_at":"2026-05-17T23:39:53.147012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:53.147012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wHcVlfgtwJqRuytt51FMf6aIX5JyZnbZmyDIg4qggkPnyBWE59J7Anp2MX0X7HSvGGtkLZ3dDaEDPqfbhCIQDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:53.147619Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.09467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:919eccf13631ffefb62d540a900aa88dbddd4374606cf5a3a480399b57b9a1f5","sha256:fa1e906a8a9cd66fab2a27d293d5bacb6f32ee80ab1dab2d871a4aabc10670ac"],"state_sha256":"9409e018736c1cef31a47b59632d2da2c1a4735ceae2875ec04c8ad758aa5e6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xuPBVUEdZb8VEDIBcuBf7qt02dBTakkrmRekJ4Rzx8IXvld0SX4lotibowYn0gHUHnIjD5iLc4g9l75+DIWvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T09:02:53.386892Z","bundle_sha256":"6ad33b33efc10c368e189a97f0bc428bd67967da2305ef08f2475e31c9b08824"}}