{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SOBMMUXLUZQ22DE64O7I5HRI7C","short_pith_number":"pith:SOBMMUXL","canonical_record":{"source":{"id":"2202.10134","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-21T11:28:00Z","cross_cats_sorted":[],"title_canon_sha256":"2f8094d59de8e87e3663f5ea385c706a577dc7d5a096bb883bd64204a9c0a0c6","abstract_canon_sha256":"2da853c0d1d3894b52a5935d93c032e81d65591b3091b234f43da5995a078ac9"},"schema_version":"1.0"},"canonical_sha256":"9382c652eba661ad0c9ee3be8e9e28f89c0eac1d880bc132e61dea7d4cbd6ec0","source":{"kind":"arxiv","id":"2202.10134","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.10134","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"arxiv_version","alias_value":"2202.10134v2","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10134","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"pith_short_12","alias_value":"SOBMMUXLUZQ2","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"pith_short_16","alias_value":"SOBMMUXLUZQ22DE6","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"pith_short_8","alias_value":"SOBMMUXL","created_at":"2026-07-05T04:24:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SOBMMUXLUZQ22DE64O7I5HRI7C","target":"record","payload":{"canonical_record":{"source":{"id":"2202.10134","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-21T11:28:00Z","cross_cats_sorted":[],"title_canon_sha256":"2f8094d59de8e87e3663f5ea385c706a577dc7d5a096bb883bd64204a9c0a0c6","abstract_canon_sha256":"2da853c0d1d3894b52a5935d93c032e81d65591b3091b234f43da5995a078ac9"},"schema_version":"1.0"},"canonical_sha256":"9382c652eba661ad0c9ee3be8e9e28f89c0eac1d880bc132e61dea7d4cbd6ec0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:58.480915Z","signature_b64":"+OEknOfTe9/Y6znWEsyOZ7d6hUxfSg7xIaXqP3DpM842IfGYefIQKwGNoMrT3qba7xYJQgQyRiMx0rbvBM27Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9382c652eba661ad0c9ee3be8e9e28f89c0eac1d880bc132e61dea7d4cbd6ec0","last_reissued_at":"2026-07-05T04:24:58.480491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:58.480491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.10134","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":"2026-07-05T04:24:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LY+dALZl8qUcInA7Erq7G7ULx1JNF2MsOtFvAGAWCMLEDZs93VTie6te3vUiZrupcLHr5DmMW+T9JyK/dgVJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T17:26:49.256446Z"},"content_sha256":"f992dfe5db7bc9cdf82a1a22b666660e02e5d7f731cc43734b04875ecb6524ec","schema_version":"1.0","event_id":"sha256:f992dfe5db7bc9cdf82a1a22b666660e02e5d7f731cc43734b04875ecb6524ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SOBMMUXLUZQ22DE64O7I5HRI7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Houqiang Li, Jiangcheng Zhu, Jian Zhao, Mingyu Yang, Wengang Zhou, Xunhan Hu, Youpeng Zhao","submitted_at":"2022-02-21T11:28:00Z","abstract_excerpt":"In cooperative multi-agent tasks, a team of agents jointly interact with an environment by taking actions, receiving a team reward and observing the next state. During the interactions, the uncertainty of environment and reward will inevitably induce stochasticity in the long-term returns and the randomness can be exacerbated with the increasing number of agents. However, such randomness is ignored by most of the existing value-based multi-agent reinforcement learning (MARL) methods, which only model the expectation of Q-value for both individual agents and the team. Compared to using the expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10134","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/2202.10134/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":"2026-07-05T04:24:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xkjXylYg5PHyQJgYQV6rDo8BoX51IEAdhMlspdMJyf9FF9fklHa4kiUTTiyFyifA78eLHEEu/vog5otwH/4ABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T17:26:49.256818Z"},"content_sha256":"22a57eb588d1c7f2e971e77734e339d7121c8130951dcdd6e4f00f723c4ffb60","schema_version":"1.0","event_id":"sha256:22a57eb588d1c7f2e971e77734e339d7121c8130951dcdd6e4f00f723c4ffb60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOBMMUXLUZQ22DE64O7I5HRI7C/bundle.json","state_url":"https://pith.science/pith/SOBMMUXLUZQ22DE64O7I5HRI7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOBMMUXLUZQ22DE64O7I5HRI7C/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":"2026-07-14T17:26:49Z","links":{"resolver":"https://pith.science/pith/SOBMMUXLUZQ22DE64O7I5HRI7C","bundle":"https://pith.science/pith/SOBMMUXLUZQ22DE64O7I5HRI7C/bundle.json","state":"https://pith.science/pith/SOBMMUXLUZQ22DE64O7I5HRI7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOBMMUXLUZQ22DE64O7I5HRI7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SOBMMUXLUZQ22DE64O7I5HRI7C","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":"2da853c0d1d3894b52a5935d93c032e81d65591b3091b234f43da5995a078ac9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-21T11:28:00Z","title_canon_sha256":"2f8094d59de8e87e3663f5ea385c706a577dc7d5a096bb883bd64204a9c0a0c6"},"schema_version":"1.0","source":{"id":"2202.10134","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.10134","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"arxiv_version","alias_value":"2202.10134v2","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10134","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"pith_short_12","alias_value":"SOBMMUXLUZQ2","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"pith_short_16","alias_value":"SOBMMUXLUZQ22DE6","created_at":"2026-07-05T04:24:58Z"},{"alias_kind":"pith_short_8","alias_value":"SOBMMUXL","created_at":"2026-07-05T04:24:58Z"}],"graph_snapshots":[{"event_id":"sha256:22a57eb588d1c7f2e971e77734e339d7121c8130951dcdd6e4f00f723c4ffb60","target":"graph","created_at":"2026-07-05T04:24:58Z","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/2202.10134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In cooperative multi-agent tasks, a team of agents jointly interact with an environment by taking actions, receiving a team reward and observing the next state. During the interactions, the uncertainty of environment and reward will inevitably induce stochasticity in the long-term returns and the randomness can be exacerbated with the increasing number of agents. However, such randomness is ignored by most of the existing value-based multi-agent reinforcement learning (MARL) methods, which only model the expectation of Q-value for both individual agents and the team. Compared to using the expe","authors_text":"Houqiang Li, Jiangcheng Zhu, Jian Zhao, Mingyu Yang, Wengang Zhou, Xunhan Hu, Youpeng Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-21T11:28:00Z","title":"MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10134","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:f992dfe5db7bc9cdf82a1a22b666660e02e5d7f731cc43734b04875ecb6524ec","target":"record","created_at":"2026-07-05T04:24:58Z","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":"2da853c0d1d3894b52a5935d93c032e81d65591b3091b234f43da5995a078ac9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-21T11:28:00Z","title_canon_sha256":"2f8094d59de8e87e3663f5ea385c706a577dc7d5a096bb883bd64204a9c0a0c6"},"schema_version":"1.0","source":{"id":"2202.10134","kind":"arxiv","version":2}},"canonical_sha256":"9382c652eba661ad0c9ee3be8e9e28f89c0eac1d880bc132e61dea7d4cbd6ec0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9382c652eba661ad0c9ee3be8e9e28f89c0eac1d880bc132e61dea7d4cbd6ec0","first_computed_at":"2026-07-05T04:24:58.480491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:58.480491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+OEknOfTe9/Y6znWEsyOZ7d6hUxfSg7xIaXqP3DpM842IfGYefIQKwGNoMrT3qba7xYJQgQyRiMx0rbvBM27Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:58.480915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.10134","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f992dfe5db7bc9cdf82a1a22b666660e02e5d7f731cc43734b04875ecb6524ec","sha256:22a57eb588d1c7f2e971e77734e339d7121c8130951dcdd6e4f00f723c4ffb60"],"state_sha256":"43942f78b030f6b1075eace2e9797333a3dc735cb8630335a75c4071a291e4dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSPAv47JwALJhX3U3OjR77h3Pk8gQIfF1OSGRHymYA+eABA+Z06p1aUuQ/hkZD481fGhaolqpI1m0SpFMwjcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T17:26:49.259081Z","bundle_sha256":"b76ed2490ab60d4e9b19d5f1ede365866cecef7d71fa625bc685380bd4df923c"}}