{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CU6S6HZHV35MMRBVVQ6LS7DDVZ","short_pith_number":"pith:CU6S6HZH","canonical_record":{"source":{"id":"2608.03562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T12:28:39Z","cross_cats_sorted":[],"title_canon_sha256":"c8f23d8159ee64dbbfdbc88be225fa1051d56edb9ece4f2f4dba54d938f7d7c0","abstract_canon_sha256":"5f8cf1b737acb880d3688ed742f3515413c8dd0f4eec30b4502bcf0f7efd80e3"},"schema_version":"1.0"},"canonical_sha256":"153d2f1f27aefac64435ac3cb97c63ae6e796fcad676b280ef035885cd9a216c","source":{"kind":"arxiv","id":"2608.03562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03562","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03562v1","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03562","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"CU6S6HZHV35M","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"CU6S6HZHV35MMRBV","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"CU6S6HZH","created_at":"2026-08-05T01:36:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CU6S6HZHV35MMRBVVQ6LS7DDVZ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T12:28:39Z","cross_cats_sorted":[],"title_canon_sha256":"c8f23d8159ee64dbbfdbc88be225fa1051d56edb9ece4f2f4dba54d938f7d7c0","abstract_canon_sha256":"5f8cf1b737acb880d3688ed742f3515413c8dd0f4eec30b4502bcf0f7efd80e3"},"schema_version":"1.0"},"canonical_sha256":"153d2f1f27aefac64435ac3cb97c63ae6e796fcad676b280ef035885cd9a216c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:36:39.204173Z","signature_b64":"DMYx972y+H3h1N9kujm6SpEhHKIP0ciWYBRCPCE78h7wAB8rjm6m/bqfYn0xUnvSbFKosNmNbpzxJbTlJtd/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"153d2f1f27aefac64435ac3cb97c63ae6e796fcad676b280ef035885cd9a216c","last_reissued_at":"2026-08-05T01:36:39.202680Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:36:39.202680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03562","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":"2026-08-05T01:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRZgRstpPCxm4qTiC24juneoo7YbSu+Nw8qTCXlVeK7+QB5u7AQq7vFSCkFRtGF4gGhhpL8DSb6vAjO1xvn/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:29:01.512407Z"},"content_sha256":"8fa486ab1fc1b90d102f6b363eac6ff975930608f1e2c13b51e7fb515d4fc20f","schema_version":"1.0","event_id":"sha256:8fa486ab1fc1b90d102f6b363eac6ff975930608f1e2c13b51e7fb515d4fc20f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CU6S6HZHV35MMRBVVQ6LS7DDVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust General Utility for Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Brian Summa, Fangzheng Wu, Zixuan Liu, Zizhan Zheng","submitted_at":"2026-08-04T12:28:39Z","abstract_excerpt":"Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broader range of applications. However, previous work on general utility RL typically assumes the evaluation utility is fixed and correctly specified. In practice, the utility used at deployment can deviate from the training one, creating a robustness gap that prior work does not address. Motivated by this, we propose robust general-utility RL, a minimax learning framework that trains policies against utility misspecificat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03562","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/2608.03562/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":"2026-08-05T01:36:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ndMsmfl+xZxVRFJQPjrIuDhqkeNL4ON8Q8Uz1osTqF8BX7gzKqR/cZ1fulJflrZzTeVaw97Q4UmstjWyfTrvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:29:01.512987Z"},"content_sha256":"e828cbedaa424c76590ea8ed9a4068bd259b994c461d4cdfb502df3262c8bc5a","schema_version":"1.0","event_id":"sha256:e828cbedaa424c76590ea8ed9a4068bd259b994c461d4cdfb502df3262c8bc5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CU6S6HZHV35MMRBVVQ6LS7DDVZ/bundle.json","state_url":"https://pith.science/pith/CU6S6HZHV35MMRBVVQ6LS7DDVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CU6S6HZHV35MMRBVVQ6LS7DDVZ/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":"2026-08-16T10:29:01Z","links":{"resolver":"https://pith.science/pith/CU6S6HZHV35MMRBVVQ6LS7DDVZ","bundle":"https://pith.science/pith/CU6S6HZHV35MMRBVVQ6LS7DDVZ/bundle.json","state":"https://pith.science/pith/CU6S6HZHV35MMRBVVQ6LS7DDVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CU6S6HZHV35MMRBVVQ6LS7DDVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CU6S6HZHV35MMRBVVQ6LS7DDVZ","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":"5f8cf1b737acb880d3688ed742f3515413c8dd0f4eec30b4502bcf0f7efd80e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T12:28:39Z","title_canon_sha256":"c8f23d8159ee64dbbfdbc88be225fa1051d56edb9ece4f2f4dba54d938f7d7c0"},"schema_version":"1.0","source":{"id":"2608.03562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03562","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03562v1","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03562","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"pith_short_12","alias_value":"CU6S6HZHV35M","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"pith_short_16","alias_value":"CU6S6HZHV35MMRBV","created_at":"2026-08-05T01:36:39Z"},{"alias_kind":"pith_short_8","alias_value":"CU6S6HZH","created_at":"2026-08-05T01:36:39Z"}],"graph_snapshots":[{"event_id":"sha256:e828cbedaa424c76590ea8ed9a4068bd259b994c461d4cdfb502df3262c8bc5a","target":"graph","created_at":"2026-08-05T01:36:39Z","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/2608.03562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broader range of applications. However, previous work on general utility RL typically assumes the evaluation utility is fixed and correctly specified. In practice, the utility used at deployment can deviate from the training one, creating a robustness gap that prior work does not address. Motivated by this, we propose robust general-utility RL, a minimax learning framework that trains policies against utility misspecificat","authors_text":"Brian Summa, Fangzheng Wu, Zixuan Liu, Zizhan Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T12:28:39Z","title":"Robust General Utility for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03562","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":"sha256:8fa486ab1fc1b90d102f6b363eac6ff975930608f1e2c13b51e7fb515d4fc20f","target":"record","created_at":"2026-08-05T01:36:39Z","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":"5f8cf1b737acb880d3688ed742f3515413c8dd0f4eec30b4502bcf0f7efd80e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T12:28:39Z","title_canon_sha256":"c8f23d8159ee64dbbfdbc88be225fa1051d56edb9ece4f2f4dba54d938f7d7c0"},"schema_version":"1.0","source":{"id":"2608.03562","kind":"arxiv","version":1}},"canonical_sha256":"153d2f1f27aefac64435ac3cb97c63ae6e796fcad676b280ef035885cd9a216c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"153d2f1f27aefac64435ac3cb97c63ae6e796fcad676b280ef035885cd9a216c","first_computed_at":"2026-08-05T01:36:39.202680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:36:39.202680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DMYx972y+H3h1N9kujm6SpEhHKIP0ciWYBRCPCE78h7wAB8rjm6m/bqfYn0xUnvSbFKosNmNbpzxJbTlJtd/Dg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:36:39.204173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fa486ab1fc1b90d102f6b363eac6ff975930608f1e2c13b51e7fb515d4fc20f","sha256:e828cbedaa424c76590ea8ed9a4068bd259b994c461d4cdfb502df3262c8bc5a"],"state_sha256":"44a41d11634fd63d58e30534f2622f762e5bc027ec429cbc61376262f3a05ac7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOo8qaqce2nHeAkF/qOVsq0ctmnKzrA7ugkvCg2Q6/1Vby9AePaCud6zMgSbWAfehL4aZIs9CNu5lXXcrvmbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:29:01.516676Z","bundle_sha256":"eac5efada50ddec486df7ab38b759db0e300d294d80e7da0c703b771a7730495"}}