{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NFVABGHWFZVMMTIVOI6LWA7FT4","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":"a8e163a4dd4e29fefe460adbbea4827bfb53976ce3150f54c5c5aa8bb5ff9a03","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T15:50:29Z","title_canon_sha256":"8f9f03e46d357efc6b66e230007ccf35b2a43144502d2976d5c731c78e2ad30e"},"schema_version":"1.0","source":{"id":"2607.29559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29559","created_at":"2026-08-03T01:38:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29559v1","created_at":"2026-08-03T01:38:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29559","created_at":"2026-08-03T01:38:31Z"},{"alias_kind":"pith_short_12","alias_value":"NFVABGHWFZVM","created_at":"2026-08-03T01:38:31Z"},{"alias_kind":"pith_short_16","alias_value":"NFVABGHWFZVMMTIV","created_at":"2026-08-03T01:38:31Z"},{"alias_kind":"pith_short_8","alias_value":"NFVABGHW","created_at":"2026-08-03T01:38:31Z"}],"graph_snapshots":[{"event_id":"sha256:6278b82b9268d132a774ae84ea448be8a6c0d51eb98dffdf78a257362614ed31","target":"graph","created_at":"2026-08-03T01:38:31Z","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/2607.29559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve multiple, competing objectives, such as performance versus efficiency, where ground-truth reward functions are difficult to specify or inaccessible. While Multi-Objective RL (MORL) addresses such trade-offs by modeling rewards as vectors, existing approaches typically assume access to a well-specified reward function for each objective, inheriting the same challenges faced by single-objective RL. Meanwhile, Preference-based RL ","authors_text":"Angelo Cangelosi, Bei Peng, Manith Adikari, Samuele Vinanzi","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T15:50:29Z","title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29559","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":"sha256:8a78a7dfb14f2979dc718010db2162650e53e84accfa83ece47c68c8978a2c61","target":"record","created_at":"2026-08-03T01:38:31Z","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":"a8e163a4dd4e29fefe460adbbea4827bfb53976ce3150f54c5c5aa8bb5ff9a03","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T15:50:29Z","title_canon_sha256":"8f9f03e46d357efc6b66e230007ccf35b2a43144502d2976d5c731c78e2ad30e"},"schema_version":"1.0","source":{"id":"2607.29559","kind":"arxiv","version":1}},"canonical_sha256":"696a0098f62e6ac64d15723cbb03e59f181ff64262867824d246400db61fa8b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"696a0098f62e6ac64d15723cbb03e59f181ff64262867824d246400db61fa8b0","first_computed_at":"2026-08-03T01:38:31.590825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:38:31.590825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0YnMiGBW7OIXb/RUAiesIa9FloNczcoyDEcQGfTYes9dyzGxJebwwq3Ty+aJBVPmYMB9V0u9u15Xco9FETWTCQ==","signature_status":"signed_v1","signed_at":"2026-08-03T01:38:31.594099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a78a7dfb14f2979dc718010db2162650e53e84accfa83ece47c68c8978a2c61","sha256:6278b82b9268d132a774ae84ea448be8a6c0d51eb98dffdf78a257362614ed31"],"state_sha256":"6bd1629e3da8ca48f279f8a1369b7d3c3224e9cc728e4faa922c511ae0fa59dc"}