{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SBSH3ZT4IEVQFNFWANJLJ4J7QX","short_pith_number":"pith:SBSH3ZT4","schema_version":"1.0","canonical_sha256":"90647de67c412b02b4b60352b4f13f85d2e49f5cc016950090dfd97407ec1c96","source":{"kind":"arxiv","id":"2212.11746","version":1},"attestation_state":"computed","paper":{"title":"Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Gaojie Jin, Leandro Soriano Marcolino, Qiang Ni, Ronghui Mu, Wenjie Ruan","submitted_at":"2022-12-22T14:36:27Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical scenarios, thus the analysis of robustness for c-MARL models is profoundly important. However, robustness certification for c-MARLs has not yet been explored in the community. In this paper, we propose a novel certification method, which is the first work to leverage a scalable approach for c-MARLs to determine actions with guaranteed certified bounds. c-MARL certification poses two key challenges compared with single-agent systems: (i) the accumulated uncertainty as the number of agents increases; (ii"},"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":"2212.11746","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-22T14:36:27Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"6bb96e0edd30437098592a4ec388c7c400325784581ac7208c2fdc17604a97b1","abstract_canon_sha256":"7e0d54ee07cb5f5f55b248e8871857c223fb7e56eb0b325b01fb1045dbd594f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:42.401141Z","signature_b64":"Pxe9JZraq8DyrejSFv09IOoEUyoQ2hPZYhymYGSzD67iPgx9M91o5i1PMSPJzKX028xCtxYe/wvAkfaWvuE1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90647de67c412b02b4b60352b4f13f85d2e49f5cc016950090dfd97407ec1c96","last_reissued_at":"2026-07-05T05:27:42.400741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:42.400741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Gaojie Jin, Leandro Soriano Marcolino, Qiang Ni, Ronghui Mu, Wenjie Ruan","submitted_at":"2022-12-22T14:36:27Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical scenarios, thus the analysis of robustness for c-MARL models is profoundly important. However, robustness certification for c-MARLs has not yet been explored in the community. In this paper, we propose a novel certification method, which is the first work to leverage a scalable approach for c-MARLs to determine actions with guaranteed certified bounds. c-MARL certification poses two key challenges compared with single-agent systems: (i) the accumulated uncertainty as the number of agents increases; (ii"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11746","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.11746/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":"2212.11746","created_at":"2026-07-05T05:27:42.400798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.11746v1","created_at":"2026-07-05T05:27:42.400798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11746","created_at":"2026-07-05T05:27:42.400798+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBSH3ZT4IEVQ","created_at":"2026-07-05T05:27:42.400798+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBSH3ZT4IEVQFNFW","created_at":"2026-07-05T05:27:42.400798+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBSH3ZT4","created_at":"2026-07-05T05:27:42.400798+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/SBSH3ZT4IEVQFNFWANJLJ4J7QX","json":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX.json","graph_json":"https://pith.science/api/pith-number/SBSH3ZT4IEVQFNFWANJLJ4J7QX/graph.json","events_json":"https://pith.science/api/pith-number/SBSH3ZT4IEVQFNFWANJLJ4J7QX/events.json","paper":"https://pith.science/paper/SBSH3ZT4"},"agent_actions":{"view_html":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX","download_json":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX.json","view_paper":"https://pith.science/paper/SBSH3ZT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.11746&json=true","fetch_graph":"https://pith.science/api/pith-number/SBSH3ZT4IEVQFNFWANJLJ4J7QX/graph.json","fetch_events":"https://pith.science/api/pith-number/SBSH3ZT4IEVQFNFWANJLJ4J7QX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX/action/storage_attestation","attest_author":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX/action/author_attestation","sign_citation":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX/action/citation_signature","submit_replication":"https://pith.science/pith/SBSH3ZT4IEVQFNFWANJLJ4J7QX/action/replication_record"}},"created_at":"2026-07-05T05:27:42.400798+00:00","updated_at":"2026-07-05T05:27:42.400798+00:00"}