{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:64IO6GUKSKXEO4EUILOLG5GC7Y","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":"ee72b3afe5015c5fe8bcf8dc91288a3b9ff7ee09baebff2607ee432f6548279e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T04:52:04Z","title_canon_sha256":"2e3ecc6203324850fe89fac70fa42ab9d0620aa6bb2e8e5a832d3434c7d8cf0e"},"schema_version":"1.0","source":{"id":"2606.25398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25398","created_at":"2026-06-25T01:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25398v1","created_at":"2026-06-25T01:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25398","created_at":"2026-06-25T01:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"64IO6GUKSKXE","created_at":"2026-06-25T01:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"64IO6GUKSKXEO4EU","created_at":"2026-06-25T01:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"64IO6GUK","created_at":"2026-06-25T01:18:04Z"}],"graph_snapshots":[{"event_id":"sha256:ca921604400714fb69593542c09eb8d03f53e24ee706a67cf97f646a7235d648","target":"graph","created_at":"2026-06-25T01:18:04Z","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/2606.25398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward design remains a major bottleneck in reinforcement learning for robot locomotion, where successful policies often depend on carefully tuned, task-specific reward functions. Preference-based reinforcement learning offers an alternative, but existing LLM-based methods typically ask for a single overall judgment between behaviors, making it difficult to capture the multiple competing objectives that underlie high-quality locomotion. We present Multi-Objective AI-Informed Preference Learning (MAPL), a framework that learns locomotion rewards from high-level natural language objectives rathe","authors_text":"Joseph Campbell, Muhan Lin, Shuyang Shi, Xiyue Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T04:52:04Z","title":"MAPL: Multi-Objective Preference Learning for Robot Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25398","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":"sha256:3dc43b6c9a2f72a16ce99e657970a14ec71743e65730ccc0427923f39b8087ff","target":"record","created_at":"2026-06-25T01:18:04Z","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":"ee72b3afe5015c5fe8bcf8dc91288a3b9ff7ee09baebff2607ee432f6548279e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T04:52:04Z","title_canon_sha256":"2e3ecc6203324850fe89fac70fa42ab9d0620aa6bb2e8e5a832d3434c7d8cf0e"},"schema_version":"1.0","source":{"id":"2606.25398","kind":"arxiv","version":1}},"canonical_sha256":"f710ef1a8a92ae47709442dcb374c2fe23b34eb75038c6de61d9a023f1548077","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f710ef1a8a92ae47709442dcb374c2fe23b34eb75038c6de61d9a023f1548077","first_computed_at":"2026-06-25T01:18:04.312994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:04.312994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+QP2IzvtmnYsXeZSNoPR++A4ngzar6nBKLm+bMpy6EhPC75GZlJHn6ZSUek9nOc32mli68GPhkcYD9OrASVuDg==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:04.313372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc43b6c9a2f72a16ce99e657970a14ec71743e65730ccc0427923f39b8087ff","sha256:ca921604400714fb69593542c09eb8d03f53e24ee706a67cf97f646a7235d648"],"state_sha256":"bec2818a96a0991a43bd8ae3cdeba65557edb2d91da9c3019f86d266584bbe72"}