{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:P2NFHDVV6BDK6LSNNEJIOLFR52","short_pith_number":"pith:P2NFHDVV","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"},"canonical_sha256":"7e9a538eb5f046af2e4d6912872cb1ee94a6d8a8d912f8e1e836410dc6b6744c","source":{"kind":"arxiv","id":"2303.13808","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13808","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13808v2","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13808","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"pith_short_12","alias_value":"P2NFHDVV6BDK","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"pith_short_16","alias_value":"P2NFHDVV6BDK6LSN","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"pith_short_8","alias_value":"P2NFHDVV","created_at":"2026-07-05T06:34:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:P2NFHDVV6BDK6LSNNEJIOLFR52","target":"record","payload":{"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"},"canonical_sha256":"7e9a538eb5f046af2e4d6912872cb1ee94a6d8a8d912f8e1e836410dc6b6744c","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"},"source_kind":"arxiv","source_id":"2303.13808","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:34:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFIxD1aKl4AF5GI4LONq5pPcWTyWhV0XWRJfaeRtac2whz5C27W+IGn6fBft9SXJfMPw62q9xT6czhUpQN6lCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:28:17.291784Z"},"content_sha256":"ce29960a229ae0f8eef26da6ea3a27a5692269be1ec9bbf330a80fe48c2a10aa","schema_version":"1.0","event_id":"sha256:ce29960a229ae0f8eef26da6ea3a27a5692269be1ec9bbf330a80fe48c2a10aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:P2NFHDVV6BDK6LSNNEJIOLFR52","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:34:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGagkYhFk3UKVDvxU4uX/QzLukronCPe46cMMA6GwDxAV/LfJa6fEXIOUIM9Mc7RpNxvNEwYJG9X/+kyQhnNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:28:17.292152Z"},"content_sha256":"4797f2c7e58219bc96bb7230a9a6cdcefce8fa5a8faa9719ab99a1d40544a558","schema_version":"1.0","event_id":"sha256:4797f2c7e58219bc96bb7230a9a6cdcefce8fa5a8faa9719ab99a1d40544a558"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/bundle.json","state_url":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/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":"2026-07-08T13:28:17Z","links":{"resolver":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52","bundle":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/bundle.json","state":"https://pith.science/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2NFHDVV6BDK6LSNNEJIOLFR52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:P2NFHDVV6BDK6LSNNEJIOLFR52","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":"f8972265575f24b5dbf59dda93c897d96f62d5f52ee498915d12399b14e1b38b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-03-24T05:05:01Z","title_canon_sha256":"13c7308f73e771229d7d060c38976751e8b80abf151d4e206e243adedf07bfc9"},"schema_version":"1.0","source":{"id":"2303.13808","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13808","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13808v2","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13808","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"pith_short_12","alias_value":"P2NFHDVV6BDK","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"pith_short_16","alias_value":"P2NFHDVV6BDK6LSN","created_at":"2026-07-05T06:34:30Z"},{"alias_kind":"pith_short_8","alias_value":"P2NFHDVV","created_at":"2026-07-05T06:34:30Z"}],"graph_snapshots":[{"event_id":"sha256:4797f2c7e58219bc96bb7230a9a6cdcefce8fa5a8faa9719ab99a1d40544a558","target":"graph","created_at":"2026-07-05T06:34:30Z","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/2303.13808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anuj Mahajan, Kinal Mehta, Pawan Kumar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-03-24T05:05:01Z","title":"marl-jax: Multi-Agent Reinforcement Leaning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13808","kind":"arxiv","version":2},"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:ce29960a229ae0f8eef26da6ea3a27a5692269be1ec9bbf330a80fe48c2a10aa","target":"record","created_at":"2026-07-05T06:34:30Z","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":"f8972265575f24b5dbf59dda93c897d96f62d5f52ee498915d12399b14e1b38b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-03-24T05:05:01Z","title_canon_sha256":"13c7308f73e771229d7d060c38976751e8b80abf151d4e206e243adedf07bfc9"},"schema_version":"1.0","source":{"id":"2303.13808","kind":"arxiv","version":2}},"canonical_sha256":"7e9a538eb5f046af2e4d6912872cb1ee94a6d8a8d912f8e1e836410dc6b6744c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e9a538eb5f046af2e4d6912872cb1ee94a6d8a8d912f8e1e836410dc6b6744c","first_computed_at":"2026-07-05T06:34:30.028564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:30.028564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BsFg2Vi4YGiccGh4uJWQC25dBiB3tQSFvdyVLchUqoIFA09KuLQREqHYBy0QuLpfjie1mdswgy5IZ0wRQY16BA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:30.029065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13808","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce29960a229ae0f8eef26da6ea3a27a5692269be1ec9bbf330a80fe48c2a10aa","sha256:4797f2c7e58219bc96bb7230a9a6cdcefce8fa5a8faa9719ab99a1d40544a558"],"state_sha256":"57cde508228230cafff745bf766cfb291b92e168619521a332398814cbc56100"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SQguHWo+XfvYpK18ODo7AJ8LLNtzrh/i5B2qKmw+YSLDK49iv4Acw01Ba2nN1BlYQdLbU/OmsLmqgKGzv/k4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:28:17.294430Z","bundle_sha256":"176b537c29104c9c47b2ebb97236cc3edb202d52d6fbd0f8b1e32c7d6371abbe"}}