{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XFJQVZGUXFPYKGF6M6ZFIESFWD","short_pith_number":"pith:XFJQVZGU","canonical_record":{"source":{"id":"2102.03479","kind":"arxiv","version":19},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-06T02:28:09Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1b2c9abbee7e35f9c49f1bd5af6f6d51b5f066b448d93b65652a115180b09503","abstract_canon_sha256":"6d24eeedaacb3b500c69781bd53958bcabff7007f1fc4f47777f995b00284236"},"schema_version":"1.0"},"canonical_sha256":"b9530ae4d4b95f8518be67b2541245b0c6c8e072fbc236c00ef5267d986a100f","source":{"kind":"arxiv","id":"2102.03479","version":19},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03479","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03479v19","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03479","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"XFJQVZGUXFPY","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"XFJQVZGUXFPYKGF6","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"XFJQVZGU","created_at":"2026-07-05T06:18:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XFJQVZGUXFPYKGF6M6ZFIESFWD","target":"record","payload":{"canonical_record":{"source":{"id":"2102.03479","kind":"arxiv","version":19},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-06T02:28:09Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"1b2c9abbee7e35f9c49f1bd5af6f6d51b5f066b448d93b65652a115180b09503","abstract_canon_sha256":"6d24eeedaacb3b500c69781bd53958bcabff7007f1fc4f47777f995b00284236"},"schema_version":"1.0"},"canonical_sha256":"b9530ae4d4b95f8518be67b2541245b0c6c8e072fbc236c00ef5267d986a100f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:34.439357Z","signature_b64":"WGvWwEuopZ66UEZN8jv9WQALSnxXa7oSQstVIzEiHlTcWAuJ+pyA76lzKXPcI2JGoyX48rRoSmcJJlSd4FSfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9530ae4d4b95f8518be67b2541245b0c6c8e072fbc236c00ef5267d986a100f","last_reissued_at":"2026-07-05T06:18:34.438929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:34.438929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.03479","source_version":19,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkptqbX1gmqFNrhqx5yI34cJGN8arSGWbzV0DZ0mdlxiP+DeZkSNkwLIKhOad5qdt9kKyUqhn0qXRNl6seTnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:40:19.866979Z"},"content_sha256":"89f84bf667229178ab00f1cffe711a2c7d4ac70fc6ac8727535e0f545c01b073","schema_version":"1.0","event_id":"sha256:89f84bf667229178ab00f1cffe711a2c7d4ac70fc6ac8727535e0f545c01b073"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XFJQVZGUXFPYKGF6M6ZFIESFWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative 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":"Haibin Wu, Jian Hu, Seth Austin Harding, Shih-wei Liao, Siyang Jiang","submitted_at":"2021-02-06T02:28:09Z","abstract_excerpt":"Many complex multi-agent systems such as robot swarms control and autonomous vehicle coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a widely popular MARL algorithm, has been used as a baseline for the benchmark environments, e.g., Starcraft Multi-Agent Challenge (SMAC), Difficulty-Enhanced Predator-Prey (DEPP). Recent variants of QMIX target relaxing the monotonicity constraint of QMIX, allowing for performance improvement in SMAC. In this paper, we investigate the code-level optimizations of these variants and the monotonicity constraint. (1) We find tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03479","kind":"arxiv","version":19},"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/2102.03479/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":"2026-07-05T06:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/eCd3wGiM3OXJy3DH5p61laEBTuB0TntJWoW7PehwxkG+v7QZab18WHAPiri00e/0/u+cPyhYKn5X+1NktLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:40:19.867499Z"},"content_sha256":"144f59326efa120e68f9c1543b621237af23772e52c2b7d4c4383bd6f5b0e724","schema_version":"1.0","event_id":"sha256:144f59326efa120e68f9c1543b621237af23772e52c2b7d4c4383bd6f5b0e724"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFJQVZGUXFPYKGF6M6ZFIESFWD/bundle.json","state_url":"https://pith.science/pith/XFJQVZGUXFPYKGF6M6ZFIESFWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFJQVZGUXFPYKGF6M6ZFIESFWD/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":"2026-08-07T12:40:19Z","links":{"resolver":"https://pith.science/pith/XFJQVZGUXFPYKGF6M6ZFIESFWD","bundle":"https://pith.science/pith/XFJQVZGUXFPYKGF6M6ZFIESFWD/bundle.json","state":"https://pith.science/pith/XFJQVZGUXFPYKGF6M6ZFIESFWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFJQVZGUXFPYKGF6M6ZFIESFWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XFJQVZGUXFPYKGF6M6ZFIESFWD","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":"6d24eeedaacb3b500c69781bd53958bcabff7007f1fc4f47777f995b00284236","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-06T02:28:09Z","title_canon_sha256":"1b2c9abbee7e35f9c49f1bd5af6f6d51b5f066b448d93b65652a115180b09503"},"schema_version":"1.0","source":{"id":"2102.03479","kind":"arxiv","version":19}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03479","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03479v19","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03479","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"XFJQVZGUXFPY","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"XFJQVZGUXFPYKGF6","created_at":"2026-07-05T06:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"XFJQVZGU","created_at":"2026-07-05T06:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:144f59326efa120e68f9c1543b621237af23772e52c2b7d4c4383bd6f5b0e724","target":"graph","created_at":"2026-07-05T06:18:34Z","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/2102.03479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many complex multi-agent systems such as robot swarms control and autonomous vehicle coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a widely popular MARL algorithm, has been used as a baseline for the benchmark environments, e.g., Starcraft Multi-Agent Challenge (SMAC), Difficulty-Enhanced Predator-Prey (DEPP). Recent variants of QMIX target relaxing the monotonicity constraint of QMIX, allowing for performance improvement in SMAC. In this paper, we investigate the code-level optimizations of these variants and the monotonicity constraint. (1) We find tha","authors_text":"Haibin Wu, Jian Hu, Seth Austin Harding, Shih-wei Liao, Siyang Jiang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-06T02:28:09Z","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03479","kind":"arxiv","version":19},"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":"sha256:89f84bf667229178ab00f1cffe711a2c7d4ac70fc6ac8727535e0f545c01b073","target":"record","created_at":"2026-07-05T06:18:34Z","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":"6d24eeedaacb3b500c69781bd53958bcabff7007f1fc4f47777f995b00284236","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-06T02:28:09Z","title_canon_sha256":"1b2c9abbee7e35f9c49f1bd5af6f6d51b5f066b448d93b65652a115180b09503"},"schema_version":"1.0","source":{"id":"2102.03479","kind":"arxiv","version":19}},"canonical_sha256":"b9530ae4d4b95f8518be67b2541245b0c6c8e072fbc236c00ef5267d986a100f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9530ae4d4b95f8518be67b2541245b0c6c8e072fbc236c00ef5267d986a100f","first_computed_at":"2026-07-05T06:18:34.438929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:34.438929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WGvWwEuopZ66UEZN8jv9WQALSnxXa7oSQstVIzEiHlTcWAuJ+pyA76lzKXPcI2JGoyX48rRoSmcJJlSd4FSfAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:34.439357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.03479","source_kind":"arxiv","source_version":19}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89f84bf667229178ab00f1cffe711a2c7d4ac70fc6ac8727535e0f545c01b073","sha256:144f59326efa120e68f9c1543b621237af23772e52c2b7d4c4383bd6f5b0e724"],"state_sha256":"3bd02dbbd99598d43bd28dd704e59925475587cf8a8ad0cfed50abd4603df6eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56t4HCXD7YGOZ7eZcIZ6EWyKAEYl6iR1UBzRNhs7dVBUidj7wt+Ujtr8YG37SXQ7RtyfECiNTfd5NfFQ27sCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:40:19.873470Z","bundle_sha256":"182ce4b5614a66c9b888f8703e5aa8623b5416f1f46c8035d5443f2b1b39be92"}}