{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B65QQBDKM4IS3OJCNCEUA5ORKU","short_pith_number":"pith:B65QQBDK","schema_version":"1.0","canonical_sha256":"0fbb08046a67112db92268894075d1552976cb72f4eeaf6f11dd86978e3f67bd","source":{"kind":"arxiv","id":"2407.16312","version":2},"attestation_state":"computed","paper":{"title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.MA","authors_text":"Ann Now\\'e, Diederik M. Roijers, El-Ghazali Talbi, Florian Felten, Gao Peng, Gr\\'egoire Danoy, Hendrik Baier, Hicham Azmani, Jordan K. Terry, Patrick Mannion, Roxana R\\u{a}dulescu, Umut Ucak, Willem R\\\"opke","submitted_at":"2024-07-23T09:05:06Z","abstract_excerpt":"Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitat"},"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":"2407.16312","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-07-23T09:05:06Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"2116183261b27bebdd46f95a3e96071a2b892eb5705d5502d6c5f115f7efd3a4","abstract_canon_sha256":"c8fcc10c1dcdbb64ccb3fd84d74e06f2620110161f911c6622ee022e4e4ed0c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:29.233116Z","signature_b64":"CNcu9ievh9wiRwrElHJhVmtLSsWO7ZrPWT+YmMA4uIwgFEOo5pecpkSW5FeWjYX4liE7AMDj9vVVCzSzXTBlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fbb08046a67112db92268894075d1552976cb72f4eeaf6f11dd86978e3f67bd","last_reissued_at":"2026-07-05T09:26:29.232613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:29.232613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.MA","authors_text":"Ann Now\\'e, Diederik M. Roijers, El-Ghazali Talbi, Florian Felten, Gao Peng, Gr\\'egoire Danoy, Hendrik Baier, Hicham Azmani, Jordan K. Terry, Patrick Mannion, Roxana R\\u{a}dulescu, Umut Ucak, Willem R\\\"opke","submitted_at":"2024-07-23T09:05:06Z","abstract_excerpt":"Many challenging tasks such as managing traffic systems, electricity grids, or supply chains involve complex decision-making processes that must balance multiple conflicting objectives and coordinate the actions of various independent decision-makers (DMs). One perspective for formalising and addressing such tasks is multi-objective multi-agent reinforcement learning (MOMARL). MOMARL broadens reinforcement learning (RL) to problems with multiple agents each needing to consider multiple objectives in their learning process. In reinforcement learning research, benchmarks are crucial in facilitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16312","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/2407.16312/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":"2407.16312","created_at":"2026-07-05T09:26:29.232675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16312v2","created_at":"2026-07-05T09:26:29.232675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16312","created_at":"2026-07-05T09:26:29.232675+00:00"},{"alias_kind":"pith_short_12","alias_value":"B65QQBDKM4IS","created_at":"2026-07-05T09:26:29.232675+00:00"},{"alias_kind":"pith_short_16","alias_value":"B65QQBDKM4IS3OJC","created_at":"2026-07-05T09:26:29.232675+00:00"},{"alias_kind":"pith_short_8","alias_value":"B65QQBDK","created_at":"2026-07-05T09:26:29.232675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30893","citing_title":"Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21321","citing_title":"Objective-Behavior Alignment: Diagnostics for MORL Policy Selection","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10585","citing_title":"Controllability in preference-conditioned multi-objective reinforcement learning","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU","json":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU.json","graph_json":"https://pith.science/api/pith-number/B65QQBDKM4IS3OJCNCEUA5ORKU/graph.json","events_json":"https://pith.science/api/pith-number/B65QQBDKM4IS3OJCNCEUA5ORKU/events.json","paper":"https://pith.science/paper/B65QQBDK"},"agent_actions":{"view_html":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU","download_json":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU.json","view_paper":"https://pith.science/paper/B65QQBDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16312&json=true","fetch_graph":"https://pith.science/api/pith-number/B65QQBDKM4IS3OJCNCEUA5ORKU/graph.json","fetch_events":"https://pith.science/api/pith-number/B65QQBDKM4IS3OJCNCEUA5ORKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU/action/storage_attestation","attest_author":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU/action/author_attestation","sign_citation":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU/action/citation_signature","submit_replication":"https://pith.science/pith/B65QQBDKM4IS3OJCNCEUA5ORKU/action/replication_record"}},"created_at":"2026-07-05T09:26:29.232675+00:00","updated_at":"2026-07-05T09:26:29.232675+00:00"}