{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NPR2Q33CTKR63E6KD6QHBW2AVJ","short_pith_number":"pith:NPR2Q33C","schema_version":"1.0","canonical_sha256":"6be3a86f629aa3ed93ca1fa070db40aa78de4eb462b6e330e9afdd5340f44198","source":{"kind":"arxiv","id":"2606.13076","version":1},"attestation_state":"computed","paper":{"title":"$\\alpha$-fair heterogeneous agent reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Arnaud Braud, Jean-Marie Bonnin, Tayeb Lemlouma, Yao-hua Franck Xu","submitted_at":"2026-06-11T08:59:41Z","abstract_excerpt":"Cooperation in multi-agent systems is typically optimized through utilitarian objectives that maximize overall efficiency but fail to account for reward distribution, often resulting in inequitable \"leader-follower\" dynamics. While fairness-based approaches encourage pro-social behaviors where every agent benefits from cooperation, many current algorithms - including those utilizing reward shaping - break the stationarity of Markov Games or lack rigorous theoretical guarantees. This creates a critical gap between fair objective methods and theoretically safe learning frameworks. We propose a n"},"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":"2606.13076","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-11T08:59:41Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"56dd557cbfce836e0b35dd3872db949392342540ac4ccd2d63d4ae9a2fcf7b64","abstract_canon_sha256":"3bffa01db377f3fa1c8ecf0f51019c7c4cc4078a6f6b1d8469030a1767d2a2c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:39.330423Z","signature_b64":"jA7P5ffWi9WxI32EJk+TNwSbxOjjieqOpx3i/NfWyxP2oK10/CMYQg6s4Fhdd53i7OU/Uz9QtQFy24q4KHdmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be3a86f629aa3ed93ca1fa070db40aa78de4eb462b6e330e9afdd5340f44198","last_reissued_at":"2026-06-12T01:09:39.330002Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:39.330002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\alpha$-fair heterogeneous agent reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Arnaud Braud, Jean-Marie Bonnin, Tayeb Lemlouma, Yao-hua Franck Xu","submitted_at":"2026-06-11T08:59:41Z","abstract_excerpt":"Cooperation in multi-agent systems is typically optimized through utilitarian objectives that maximize overall efficiency but fail to account for reward distribution, often resulting in inequitable \"leader-follower\" dynamics. While fairness-based approaches encourage pro-social behaviors where every agent benefits from cooperation, many current algorithms - including those utilizing reward shaping - break the stationarity of Markov Games or lack rigorous theoretical guarantees. This creates a critical gap between fair objective methods and theoretically safe learning frameworks. We propose a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13076","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/2606.13076/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":"2606.13076","created_at":"2026-06-12T01:09:39.330068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13076v1","created_at":"2026-06-12T01:09:39.330068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13076","created_at":"2026-06-12T01:09:39.330068+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPR2Q33CTKR6","created_at":"2026-06-12T01:09:39.330068+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPR2Q33CTKR63E6K","created_at":"2026-06-12T01:09:39.330068+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPR2Q33C","created_at":"2026-06-12T01:09:39.330068+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/NPR2Q33CTKR63E6KD6QHBW2AVJ","json":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ.json","graph_json":"https://pith.science/api/pith-number/NPR2Q33CTKR63E6KD6QHBW2AVJ/graph.json","events_json":"https://pith.science/api/pith-number/NPR2Q33CTKR63E6KD6QHBW2AVJ/events.json","paper":"https://pith.science/paper/NPR2Q33C"},"agent_actions":{"view_html":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ","download_json":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ.json","view_paper":"https://pith.science/paper/NPR2Q33C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13076&json=true","fetch_graph":"https://pith.science/api/pith-number/NPR2Q33CTKR63E6KD6QHBW2AVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NPR2Q33CTKR63E6KD6QHBW2AVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ/action/storage_attestation","attest_author":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ/action/author_attestation","sign_citation":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ/action/citation_signature","submit_replication":"https://pith.science/pith/NPR2Q33CTKR63E6KD6QHBW2AVJ/action/replication_record"}},"created_at":"2026-06-12T01:09:39.330068+00:00","updated_at":"2026-06-12T01:09:39.330068+00:00"}