{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P2NFHDVV6BDK6LSNNEJIOLFR52","short_pith_number":"pith:P2NFHDVV","schema_version":"1.0","canonical_sha256":"7e9a538eb5f046af2e4d6912872cb1ee94a6d8a8d912f8e1e836410dc6b6744c","source":{"kind":"arxiv","id":"2303.13808","version":2},"attestation_state":"computed","paper":{"title":"marl-jax: Multi-Agent Reinforcement Leaning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Anuj Mahajan, Kinal Mehta, Pawan Kumar","submitted_at":"2023-03-24T05:05:01Z","abstract_excerpt":"Recent advances in Reinforcement Learning (RL) have led to many exciting applications. These advancements have been driven by improvements in both algorithms and engineering, which have resulted in faster training of RL agents. We present marl-jax, a multi-agent reinforcement learning software package for training and evaluating social generalization of the agents. The package is designed for training a population of agents in multi-agent environments and evaluating their ability to generalize to diverse background agents. It is built on top of DeepMind's JAX ecosystem~\\cite{deepmind2020jax} a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.13808","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-03-24T05:05:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"13c7308f73e771229d7d060c38976751e8b80abf151d4e206e243adedf07bfc9","abstract_canon_sha256":"f8972265575f24b5dbf59dda93c897d96f62d5f52ee498915d12399b14e1b38b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:30.029065Z","signature_b64":"BsFg2Vi4YGiccGh4uJWQC25dBiB3tQSFvdyVLchUqoIFA09KuLQREqHYBy0QuLpfjie1mdswgy5IZ0wRQY16BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e9a538eb5f046af2e4d6912872cb1ee94a6d8a8d912f8e1e836410dc6b6744c","last_reissued_at":"2026-07-05T06:34:30.028564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:30.028564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"marl-jax: Multi-Agent Reinforcement Leaning Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Anuj Mahajan, Kinal Mehta, Pawan Kumar","submitted_at":"2023-03-24T05:05:01Z","abstract_excerpt":"Recent advances in Reinforcement Learning (RL) have led to many exciting applications. These advancements have been driven by improvements in both algorithms and engineering, which have resulted in faster training of RL agents. We present marl-jax, a multi-agent reinforcement learning software package for training and evaluating social generalization of the agents. The package is designed for training a population of agents in multi-agent environments and evaluating their ability to generalize to diverse background agents. It is built on top of DeepMind's JAX ecosystem~\\cite{deepmind2020jax} a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13808","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/2303.13808/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.13808","created_at":"2026-07-05T06:34:30.028634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13808v2","created_at":"2026-07-05T06:34:30.028634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13808","created_at":"2026-07-05T06:34:30.028634+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2NFHDVV6BDK","created_at":"2026-07-05T06:34:30.028634+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2NFHDVV6BDK6LSN","created_at":"2026-07-05T06:34:30.028634+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2NFHDVV","created_at":"2026-07-05T06:34:30.028634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52","json":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52.json","graph_json":"https://pith.science/api/pith-number/P2NFHDVV6BDK6LSNNEJIOLFR52/graph.json","events_json":"https://pith.science/api/pith-number/P2NFHDVV6BDK6LSNNEJIOLFR52/events.json","paper":"https://pith.science/paper/P2NFHDVV"},"agent_actions":{"view_html":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52","download_json":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52.json","view_paper":"https://pith.science/paper/P2NFHDVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13808&json=true","fetch_graph":"https://pith.science/api/pith-number/P2NFHDVV6BDK6LSNNEJIOLFR52/graph.json","fetch_events":"https://pith.science/api/pith-number/P2NFHDVV6BDK6LSNNEJIOLFR52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/action/storage_attestation","attest_author":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/action/author_attestation","sign_citation":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/action/citation_signature","submit_replication":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/action/replication_record"}},"created_at":"2026-07-05T06:34:30.028634+00:00","updated_at":"2026-07-05T06:34:30.028634+00:00"}