{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T6FYN75SVTD6U2ZDWR2LIQ4DPX","short_pith_number":"pith:T6FYN75S","canonical_record":{"source":{"id":"2306.00324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:43:53Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"f696e8006eba3791eb600dd17c2c2aa15c6c08e6c9362b363bddc6b26c390e9f","abstract_canon_sha256":"03c6e83845d2e11f8fed8c3bc5e9d0203c0ce650d030a5096fbc3d206d464812"},"schema_version":"1.0"},"canonical_sha256":"9f8b86ffb2acc7ea6b23b474b443837dc738caf4e8099e9899ed0d33ee4a7ea3","source":{"kind":"arxiv","id":"2306.00324","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00324","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00324v1","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00324","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"pith_short_12","alias_value":"T6FYN75SVTD6","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"pith_short_16","alias_value":"T6FYN75SVTD6U2ZD","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"pith_short_8","alias_value":"T6FYN75S","created_at":"2026-07-05T06:16:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T6FYN75SVTD6U2ZDWR2LIQ4DPX","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:43:53Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"f696e8006eba3791eb600dd17c2c2aa15c6c08e6c9362b363bddc6b26c390e9f","abstract_canon_sha256":"03c6e83845d2e11f8fed8c3bc5e9d0203c0ce650d030a5096fbc3d206d464812"},"schema_version":"1.0"},"canonical_sha256":"9f8b86ffb2acc7ea6b23b474b443837dc738caf4e8099e9899ed0d33ee4a7ea3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:24.971171Z","signature_b64":"ucbqj2jVzM21Drl501gUn6pzxIW7bbzkPU/y5Lu30WpDfzI8W1GjI6m44clUOCyJcIKpfi5UhLHr7HCYba4CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f8b86ffb2acc7ea6b23b474b443837dc738caf4e8099e9899ed0d33ee4a7ea3","last_reissued_at":"2026-07-05T06:16:24.970691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:24.970691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00324","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:16:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ImEBZHHYsQ7DVDyC52glx/zjXxpRJIVFIJVwIAEFTjsIzk4YebeRDqmHTK/nBGwiudCSXCIMUycs20Ugc5WQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:16:09.035105Z"},"content_sha256":"682bcb32c4589838778fdabbef96c1d1e403c8614c1160f4563dc291f3992c05","schema_version":"1.0","event_id":"sha256:682bcb32c4589838778fdabbef96c1d1e403c8614c1160f4563dc291f3992c05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T6FYN75SVTD6U2ZDWR2LIQ4DPX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Arnob Ghosh, Ness B. Shroff, Peizhong Ju","submitted_at":"2023-06-01T03:43:53Z","abstract_excerpt":"Fairness plays a crucial role in various multi-agent systems (e.g., communication networks, financial markets, etc.). Many multi-agent dynamical interactions can be cast as Markov Decision Processes (MDPs). While existing research has focused on studying fairness in known environments, the exploration of fairness in such systems for unknown environments remains open. In this paper, we propose a Reinforcement Learning (RL) approach to achieve fairness in multi-agent finite-horizon episodic MDPs. Instead of maximizing the sum of individual agents' value functions, we introduce a fairness functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00324","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/2306.00324/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":"2026-07-05T06:16:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZIoGiUEOVZZnGhr/HuLO4fWBoQf+GagWPkBqXHra0buOZAhaZi1buLT/HMaFRl7sng3wikp8a+PZ/KV8FKJeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:16:09.035599Z"},"content_sha256":"261becb378549d57f8c5358fe8d42d6150821a7e7ff4fce3068e6789f50a3606","schema_version":"1.0","event_id":"sha256:261becb378549d57f8c5358fe8d42d6150821a7e7ff4fce3068e6789f50a3606"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6FYN75SVTD6U2ZDWR2LIQ4DPX/bundle.json","state_url":"https://pith.science/pith/T6FYN75SVTD6U2ZDWR2LIQ4DPX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6FYN75SVTD6U2ZDWR2LIQ4DPX/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":"2026-08-17T20:16:09Z","links":{"resolver":"https://pith.science/pith/T6FYN75SVTD6U2ZDWR2LIQ4DPX","bundle":"https://pith.science/pith/T6FYN75SVTD6U2ZDWR2LIQ4DPX/bundle.json","state":"https://pith.science/pith/T6FYN75SVTD6U2ZDWR2LIQ4DPX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6FYN75SVTD6U2ZDWR2LIQ4DPX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T6FYN75SVTD6U2ZDWR2LIQ4DPX","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":"03c6e83845d2e11f8fed8c3bc5e9d0203c0ce650d030a5096fbc3d206d464812","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:43:53Z","title_canon_sha256":"f696e8006eba3791eb600dd17c2c2aa15c6c08e6c9362b363bddc6b26c390e9f"},"schema_version":"1.0","source":{"id":"2306.00324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00324","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00324v1","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00324","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"pith_short_12","alias_value":"T6FYN75SVTD6","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"pith_short_16","alias_value":"T6FYN75SVTD6U2ZD","created_at":"2026-07-05T06:16:24Z"},{"alias_kind":"pith_short_8","alias_value":"T6FYN75S","created_at":"2026-07-05T06:16:24Z"}],"graph_snapshots":[{"event_id":"sha256:261becb378549d57f8c5358fe8d42d6150821a7e7ff4fce3068e6789f50a3606","target":"graph","created_at":"2026-07-05T06:16:24Z","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/2306.00324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fairness plays a crucial role in various multi-agent systems (e.g., communication networks, financial markets, etc.). Many multi-agent dynamical interactions can be cast as Markov Decision Processes (MDPs). While existing research has focused on studying fairness in known environments, the exploration of fairness in such systems for unknown environments remains open. In this paper, we propose a Reinforcement Learning (RL) approach to achieve fairness in multi-agent finite-horizon episodic MDPs. Instead of maximizing the sum of individual agents' value functions, we introduce a fairness functio","authors_text":"Arnob Ghosh, Ness B. Shroff, Peizhong Ju","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:43:53Z","title":"Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00324","kind":"arxiv","version":1},"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":"sha256:682bcb32c4589838778fdabbef96c1d1e403c8614c1160f4563dc291f3992c05","target":"record","created_at":"2026-07-05T06:16:24Z","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":"03c6e83845d2e11f8fed8c3bc5e9d0203c0ce650d030a5096fbc3d206d464812","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T03:43:53Z","title_canon_sha256":"f696e8006eba3791eb600dd17c2c2aa15c6c08e6c9362b363bddc6b26c390e9f"},"schema_version":"1.0","source":{"id":"2306.00324","kind":"arxiv","version":1}},"canonical_sha256":"9f8b86ffb2acc7ea6b23b474b443837dc738caf4e8099e9899ed0d33ee4a7ea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f8b86ffb2acc7ea6b23b474b443837dc738caf4e8099e9899ed0d33ee4a7ea3","first_computed_at":"2026-07-05T06:16:24.970691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:24.970691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ucbqj2jVzM21Drl501gUn6pzxIW7bbzkPU/y5Lu30WpDfzI8W1GjI6m44clUOCyJcIKpfi5UhLHr7HCYba4CCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:24.971171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:682bcb32c4589838778fdabbef96c1d1e403c8614c1160f4563dc291f3992c05","sha256:261becb378549d57f8c5358fe8d42d6150821a7e7ff4fce3068e6789f50a3606"],"state_sha256":"7b91923c7b2927ce56201198de3c09baa1e3f1a0a2ab2695a639bf84025cd33d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NgN3+jkcSy2ObMhRL8BCCQE+/Ke4ZqQazD9NQNSlnch20Ruc01Hjo5JKm3FUDb4HGefik1/vemvEYgWFM6nVDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:16:09.041844Z","bundle_sha256":"585387c7c2dd0d5875d4412791bb01cfe0a0bc632c38a433754f55cf5b81a5ca"}}