{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AD2YWTAYDBYKWCU5GGBMXBBRLL","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":"74b776b443a409650deca8cc01541a916330e74fa7cababfb2301666a6447f14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-06T23:12:26Z","title_canon_sha256":"6f91758c03d22b851c3cb3f1eab81f3f54a67824a3017f4886d691961d90869e"},"schema_version":"1.0","source":{"id":"2212.03363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03363","created_at":"2026-07-05T05:23:15Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03363v1","created_at":"2026-07-05T05:23:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03363","created_at":"2026-07-05T05:23:15Z"},{"alias_kind":"pith_short_12","alias_value":"AD2YWTAYDBYK","created_at":"2026-07-05T05:23:15Z"},{"alias_kind":"pith_short_16","alias_value":"AD2YWTAYDBYKWCU5","created_at":"2026-07-05T05:23:15Z"},{"alias_kind":"pith_short_8","alias_value":"AD2YWTAY","created_at":"2026-07-05T05:23:15Z"}],"graph_snapshots":[{"event_id":"sha256:cfcec5c7313f88b6699c6b3ac2836e8190e93f207c155ad1b9a1f699559461ca","target":"graph","created_at":"2026-07-05T05:23:15Z","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/2212.03363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and policy exploitation. Preference based RL algorithms seek to overcome these challenges by directly learning reward functions from human feedback. Unfortunately, prior work either requires an unreasonable number of queries implausible for any human to answer or overly restricts the class of reward functions to guarantee the elicitation of the most informative qu","authors_text":"Dorsa Sadigh, Joey Hejna","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-06T23:12:26Z","title":"Few-Shot Preference Learning for Human-in-the-Loop RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03363","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":"sha256:2391f96401a645e1a00547ad86da092fcfcf77e297e4dd5949caf11c2232876a","target":"record","created_at":"2026-07-05T05:23:15Z","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":"74b776b443a409650deca8cc01541a916330e74fa7cababfb2301666a6447f14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-06T23:12:26Z","title_canon_sha256":"6f91758c03d22b851c3cb3f1eab81f3f54a67824a3017f4886d691961d90869e"},"schema_version":"1.0","source":{"id":"2212.03363","kind":"arxiv","version":1}},"canonical_sha256":"00f58b4c181870ab0a9d3182cb84315ae1290694a3588428d3e0247b88c742e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00f58b4c181870ab0a9d3182cb84315ae1290694a3588428d3e0247b88c742e5","first_computed_at":"2026-07-05T05:23:15.349101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:15.349101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V9OzEJH9KCNLxH9m5KGQPJVQwAmBtrgNEB+zg81ZJlhmpa3Rnj3PpAaXVpJ1lYwFUi5ebgWk740VFwlF78gXBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:15.349533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.03363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2391f96401a645e1a00547ad86da092fcfcf77e297e4dd5949caf11c2232876a","sha256:cfcec5c7313f88b6699c6b3ac2836e8190e93f207c155ad1b9a1f699559461ca"],"state_sha256":"d1823badee9dcb7c0d726a11425476ec6e5f6d11941c6fc0cbd5890c9006e8f1"}