{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2WR7RAPBEHTUREUM6ZZXS6JZBY","short_pith_number":"pith:2WR7RAPB","schema_version":"1.0","canonical_sha256":"d5a3f881e121e748928cf6737979390e23c7d9884389e19ece432888b0c27a8b","source":{"kind":"arxiv","id":"2306.08419","version":1},"attestation_state":"computed","paper":{"title":"Mediated Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Dmitry Ivanov, Ilya Zisman, Kirill Chernyshev","submitted_at":"2023-06-14T10:31:37Z","abstract_excerpt":"The majority of Multi-Agent Reinforcement Learning (MARL) literature equates the cooperation of self-interested agents in mixed environments to the problem of social welfare maximization, allowing agents to arbitrarily share rewards and private information. This results in agents that forgo their individual goals in favour of social good, which can potentially be exploited by selfish defectors. We argue that cooperation also requires agents' identities and boundaries to be respected by making sure that the emergent behaviour is an equilibrium, i.e., a convention that no agent can deviate from "},"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":"2306.08419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-06-14T10:31:37Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"1cbabe5b99a9d521d9b17f823c087d7acbf567e2ee91aecf7021a3329aa916be","abstract_canon_sha256":"87481e9591497fb2d7adc601c8893984e5e2cb593e3c61583546ac172f5788e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:52.463932Z","signature_b64":"4maqONpEHHu2gs8ma/xc/N6/sAS11xvryE/D5L27bVjfZFjWCe8qwQx6LEFckUHUV1GIFUOTjhKx61Zv2Qf6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5a3f881e121e748928cf6737979390e23c7d9884389e19ece432888b0c27a8b","last_reissued_at":"2026-07-05T06:20:52.463577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:52.463577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mediated Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Dmitry Ivanov, Ilya Zisman, Kirill Chernyshev","submitted_at":"2023-06-14T10:31:37Z","abstract_excerpt":"The majority of Multi-Agent Reinforcement Learning (MARL) literature equates the cooperation of self-interested agents in mixed environments to the problem of social welfare maximization, allowing agents to arbitrarily share rewards and private information. This results in agents that forgo their individual goals in favour of social good, which can potentially be exploited by selfish defectors. We argue that cooperation also requires agents' identities and boundaries to be respected by making sure that the emergent behaviour is an equilibrium, i.e., a convention that no agent can deviate from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08419","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/2306.08419/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":"2306.08419","created_at":"2026-07-05T06:20:52.463632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08419v1","created_at":"2026-07-05T06:20:52.463632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08419","created_at":"2026-07-05T06:20:52.463632+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WR7RAPBEHTU","created_at":"2026-07-05T06:20:52.463632+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WR7RAPBEHTUREUM","created_at":"2026-07-05T06:20:52.463632+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WR7RAPB","created_at":"2026-07-05T06:20:52.463632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09894","citing_title":"Competitive mediator games and urban CAV routing markets","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY","json":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY.json","graph_json":"https://pith.science/api/pith-number/2WR7RAPBEHTUREUM6ZZXS6JZBY/graph.json","events_json":"https://pith.science/api/pith-number/2WR7RAPBEHTUREUM6ZZXS6JZBY/events.json","paper":"https://pith.science/paper/2WR7RAPB"},"agent_actions":{"view_html":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY","download_json":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY.json","view_paper":"https://pith.science/paper/2WR7RAPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08419&json=true","fetch_graph":"https://pith.science/api/pith-number/2WR7RAPBEHTUREUM6ZZXS6JZBY/graph.json","fetch_events":"https://pith.science/api/pith-number/2WR7RAPBEHTUREUM6ZZXS6JZBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY/action/storage_attestation","attest_author":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY/action/author_attestation","sign_citation":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY/action/citation_signature","submit_replication":"https://pith.science/pith/2WR7RAPBEHTUREUM6ZZXS6JZBY/action/replication_record"}},"created_at":"2026-07-05T06:20:52.463632+00:00","updated_at":"2026-07-05T06:20:52.463632+00:00"}