{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:64IO6GUKSKXEO4EUILOLG5GC7Y","short_pith_number":"pith:64IO6GUK","schema_version":"1.0","canonical_sha256":"f710ef1a8a92ae47709442dcb374c2fe23b34eb75038c6de61d9a023f1548077","source":{"kind":"arxiv","id":"2606.25398","version":1},"attestation_state":"computed","paper":{"title":"MAPL: Multi-Objective Preference Learning for Robot Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Joseph Campbell, Muhan Lin, Shuyang Shi, Xiyue Chen","submitted_at":"2026-06-24T04:52:04Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.25398","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-24T04:52:04Z","cross_cats_sorted":[],"title_canon_sha256":"2e3ecc6203324850fe89fac70fa42ab9d0620aa6bb2e8e5a832d3434c7d8cf0e","abstract_canon_sha256":"ee72b3afe5015c5fe8bcf8dc91288a3b9ff7ee09baebff2607ee432f6548279e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:04.313372Z","signature_b64":"+QP2IzvtmnYsXeZSNoPR++A4ngzar6nBKLm+bMpy6EhPC75GZlJHn6ZSUek9nOc32mli68GPhkcYD9OrASVuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f710ef1a8a92ae47709442dcb374c2fe23b34eb75038c6de61d9a023f1548077","last_reissued_at":"2026-06-25T01:18:04.312994Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:04.312994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAPL: Multi-Objective Preference Learning for Robot Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Joseph Campbell, Muhan Lin, Shuyang Shi, Xiyue Chen","submitted_at":"2026-06-24T04:52:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25398","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/2606.25398/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.25398","created_at":"2026-06-25T01:18:04.313063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25398v1","created_at":"2026-06-25T01:18:04.313063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25398","created_at":"2026-06-25T01:18:04.313063+00:00"},{"alias_kind":"pith_short_12","alias_value":"64IO6GUKSKXE","created_at":"2026-06-25T01:18:04.313063+00:00"},{"alias_kind":"pith_short_16","alias_value":"64IO6GUKSKXEO4EU","created_at":"2026-06-25T01:18:04.313063+00:00"},{"alias_kind":"pith_short_8","alias_value":"64IO6GUK","created_at":"2026-06-25T01:18:04.313063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y","json":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y.json","graph_json":"https://pith.science/api/pith-number/64IO6GUKSKXEO4EUILOLG5GC7Y/graph.json","events_json":"https://pith.science/api/pith-number/64IO6GUKSKXEO4EUILOLG5GC7Y/events.json","paper":"https://pith.science/paper/64IO6GUK"},"agent_actions":{"view_html":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y","download_json":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y.json","view_paper":"https://pith.science/paper/64IO6GUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25398&json=true","fetch_graph":"https://pith.science/api/pith-number/64IO6GUKSKXEO4EUILOLG5GC7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/64IO6GUKSKXEO4EUILOLG5GC7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y/action/storage_attestation","attest_author":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y/action/author_attestation","sign_citation":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y/action/citation_signature","submit_replication":"https://pith.science/pith/64IO6GUKSKXEO4EUILOLG5GC7Y/action/replication_record"}},"created_at":"2026-06-25T01:18:04.313063+00:00","updated_at":"2026-06-25T01:18:04.313063+00:00"}