{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AZCL6LXEDGZWSJCTNYROM6NBBM","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":"31582798c9663841c37fac021b58af0b4bc108a0170702817a79337f073b8385","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T01:22:01Z","title_canon_sha256":"59d46b14b0db1b1df2fe741eef5cd82c35dbdeecc932d4ef29b05345135ad9e5"},"schema_version":"1.0","source":{"id":"2109.12750","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12750","created_at":"2026-07-05T03:23:51Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12750v2","created_at":"2026-07-05T03:23:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12750","created_at":"2026-07-05T03:23:51Z"},{"alias_kind":"pith_short_12","alias_value":"AZCL6LXEDGZW","created_at":"2026-07-05T03:23:51Z"},{"alias_kind":"pith_short_16","alias_value":"AZCL6LXEDGZWSJCT","created_at":"2026-07-05T03:23:51Z"},{"alias_kind":"pith_short_8","alias_value":"AZCL6LXE","created_at":"2026-07-05T03:23:51Z"}],"graph_snapshots":[{"event_id":"sha256:6101c5eeed0053f42fd351dc2a8cb41def503249f37ad224e48a4106952b4925","target":"graph","created_at":"2026-07-05T03:23:51Z","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/2109.12750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from human feedback has shown to be a useful approach in acquiring robot reward functions. However, expert feedback is often assumed to be drawn from an underlying unimodal reward function. This assumption does not always hold including in settings where multiple experts provide data or when a single expert provides data for different tasks -- we thus go beyond learning a unimodal reward and focus on learning a multimodal reward function. We formulate the multimodal reward learning as a mixture learning problem and develop a novel ranking-based learning approach, where the experts are","authors_text":"Dorsa Sadigh, Erdem B{\\i}y{\\i}k, Nima Anari, Vivek Myers","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T01:22:01Z","title":"Learning Multimodal Rewards from Rankings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12750","kind":"arxiv","version":2},"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":"sha256:61e46273a07e16f9da1cec75590b8101b0da287a8fba5e4ff17b070ac71a6476","target":"record","created_at":"2026-07-05T03:23:51Z","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":"31582798c9663841c37fac021b58af0b4bc108a0170702817a79337f073b8385","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-27T01:22:01Z","title_canon_sha256":"59d46b14b0db1b1df2fe741eef5cd82c35dbdeecc932d4ef29b05345135ad9e5"},"schema_version":"1.0","source":{"id":"2109.12750","kind":"arxiv","version":2}},"canonical_sha256":"0644bf2ee419b36924536e22e679a10b24b70d48c2484bcf6c8db50e7f5367e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0644bf2ee419b36924536e22e679a10b24b70d48c2484bcf6c8db50e7f5367e8","first_computed_at":"2026-07-05T03:23:51.139560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:51.139560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FPX8Bf0b3/BrSSrNRQGoa5y07j7sZ2QvR0O3V0QPch0R+nARxDjPZ2fL3KSK0CptE3snIazdPXJ1+y+aSwHlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:51.140119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.12750","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61e46273a07e16f9da1cec75590b8101b0da287a8fba5e4ff17b070ac71a6476","sha256:6101c5eeed0053f42fd351dc2a8cb41def503249f37ad224e48a4106952b4925"],"state_sha256":"ac15f7c1f05e0d749e431920d0d09ac03662e76679c4ce4ad89a5f4e153df650"}