{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PM4FTMNRLMLU7FTJ5EXXDZNCJI","short_pith_number":"pith:PM4FTMNR","canonical_record":{"source":{"id":"2212.01382","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-11-30T01:40:59Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"92a0b64aaa7ff7ce278594a98044e2f8e957bf0a43ace479eaac63775261b7bb","abstract_canon_sha256":"4035b0064305cd1bffa509e748d5e17c480faddc11bf0168a5af9b1ccc0546c9"},"schema_version":"1.0"},"canonical_sha256":"7b3859b1b15b174f9669e92f71e5a24a033f246a84f9493793305a06375042d9","source":{"kind":"arxiv","id":"2212.01382","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01382","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01382v5","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01382","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"PM4FTMNRLMLU","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"pith_short_16","alias_value":"PM4FTMNRLMLU7FTJ","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"pith_short_8","alias_value":"PM4FTMNR","created_at":"2026-07-05T07:42:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PM4FTMNRLMLU7FTJ5EXXDZNCJI","target":"record","payload":{"canonical_record":{"source":{"id":"2212.01382","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-11-30T01:40:59Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"92a0b64aaa7ff7ce278594a98044e2f8e957bf0a43ace479eaac63775261b7bb","abstract_canon_sha256":"4035b0064305cd1bffa509e748d5e17c480faddc11bf0168a5af9b1ccc0546c9"},"schema_version":"1.0"},"canonical_sha256":"7b3859b1b15b174f9669e92f71e5a24a033f246a84f9493793305a06375042d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:38.464444Z","signature_b64":"8ADpA0GzlKkGBaSGVGdxLy77uGqbRig2aCzv+KqdBkXUWj/bjtzp/CVw0WjK14WH13OVJG/NbuyuzXw24sVuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3859b1b15b174f9669e92f71e5a24a033f246a84f9493793305a06375042d9","last_reissued_at":"2026-07-05T07:42:38.464018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:38.464018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.01382","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EWUpyNuzQHd2sXNiI08JlwWRzy1UzjiREM0NC0B5TKasOFe0/BJzRVQqsw+kVKveyplH+wKILL6LZFcywlcdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:54.628202Z"},"content_sha256":"cbdeed211865deff23c2f6918de34399fe752e5c3273d6235ff6b9f8f70c2101","schema_version":"1.0","event_id":"sha256:cbdeed211865deff23c2f6918de34399fe752e5c3273d6235ff6b9f8f70c2101"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PM4FTMNRLMLU7FTJ5EXXDZNCJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Welfare and Fairness in Multi-objective Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.GT","authors_text":"Brandon Fain, Muhang Tian, Nianli Peng, Zimeng Fan","submitted_at":"2022-11-30T01:40:59Z","abstract_excerpt":"We study fair multi-objective reinforcement learning in which an agent must learn a policy that simultaneously achieves high reward on multiple dimensions of a vector-valued reward. Motivated by the fair resource allocation literature, we model this as an expected welfare maximization problem, for some nonlinear fair welfare function of the vector of long-term cumulative rewards. One canonical example of such a function is the Nash Social Welfare, or geometric mean, the log transform of which is also known as the Proportional Fairness objective. We show that even approximately optimal optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01382","kind":"arxiv","version":5},"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/2212.01382/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":"2026-07-05T07:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"relezGvANd1D97P93UA0s+A0jPgT+3Kl0bqg5Rf3dqSO7JtUjzZbaZRwb/R7zXV8znX6TV3/ZrcrLyBrz0YDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:54.628852Z"},"content_sha256":"2a0bd025620c542d11924d3ccf588863ea0f2de26be81444ec9a7f555e8a5f44","schema_version":"1.0","event_id":"sha256:2a0bd025620c542d11924d3ccf588863ea0f2de26be81444ec9a7f555e8a5f44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/bundle.json","state_url":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/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":"2026-07-07T01:59:54Z","links":{"resolver":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI","bundle":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/bundle.json","state":"https://pith.science/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PM4FTMNRLMLU7FTJ5EXXDZNCJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PM4FTMNRLMLU7FTJ5EXXDZNCJI","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":"4035b0064305cd1bffa509e748d5e17c480faddc11bf0168a5af9b1ccc0546c9","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-11-30T01:40:59Z","title_canon_sha256":"92a0b64aaa7ff7ce278594a98044e2f8e957bf0a43ace479eaac63775261b7bb"},"schema_version":"1.0","source":{"id":"2212.01382","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01382","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01382v5","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01382","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"PM4FTMNRLMLU","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"pith_short_16","alias_value":"PM4FTMNRLMLU7FTJ","created_at":"2026-07-05T07:42:38Z"},{"alias_kind":"pith_short_8","alias_value":"PM4FTMNR","created_at":"2026-07-05T07:42:38Z"}],"graph_snapshots":[{"event_id":"sha256:2a0bd025620c542d11924d3ccf588863ea0f2de26be81444ec9a7f555e8a5f44","target":"graph","created_at":"2026-07-05T07:42:38Z","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/2212.01382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study fair multi-objective reinforcement learning in which an agent must learn a policy that simultaneously achieves high reward on multiple dimensions of a vector-valued reward. Motivated by the fair resource allocation literature, we model this as an expected welfare maximization problem, for some nonlinear fair welfare function of the vector of long-term cumulative rewards. One canonical example of such a function is the Nash Social Welfare, or geometric mean, the log transform of which is also known as the Proportional Fairness objective. We show that even approximately optimal optimiza","authors_text":"Brandon Fain, Muhang Tian, Nianli Peng, Zimeng Fan","cross_cats":["cs.AI","cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-11-30T01:40:59Z","title":"Welfare and Fairness in Multi-objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01382","kind":"arxiv","version":5},"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:cbdeed211865deff23c2f6918de34399fe752e5c3273d6235ff6b9f8f70c2101","target":"record","created_at":"2026-07-05T07:42:38Z","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":"4035b0064305cd1bffa509e748d5e17c480faddc11bf0168a5af9b1ccc0546c9","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2022-11-30T01:40:59Z","title_canon_sha256":"92a0b64aaa7ff7ce278594a98044e2f8e957bf0a43ace479eaac63775261b7bb"},"schema_version":"1.0","source":{"id":"2212.01382","kind":"arxiv","version":5}},"canonical_sha256":"7b3859b1b15b174f9669e92f71e5a24a033f246a84f9493793305a06375042d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b3859b1b15b174f9669e92f71e5a24a033f246a84f9493793305a06375042d9","first_computed_at":"2026-07-05T07:42:38.464018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:38.464018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ADpA0GzlKkGBaSGVGdxLy77uGqbRig2aCzv+KqdBkXUWj/bjtzp/CVw0WjK14WH13OVJG/NbuyuzXw24sVuBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:38.464444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.01382","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbdeed211865deff23c2f6918de34399fe752e5c3273d6235ff6b9f8f70c2101","sha256:2a0bd025620c542d11924d3ccf588863ea0f2de26be81444ec9a7f555e8a5f44"],"state_sha256":"5dbef485793d46e4f519431940fdeacbe3702d6fc25cc8372c35e08bf510ab52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"moyr5b5qi/GUegnzMDlWK4bdJjyAjPIpmzHEKoIAQCGBtbXUVyti3UDKh3PEaqcA3RZo/HjQ2GABJI2x+sUqDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T01:59:54.632609Z","bundle_sha256":"de581f8fd6b4c0efa4ef3c27a03a6906df341dc9153147f22b65f6095e20e44e"}}