{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NKPFOUJ6IPKD3ALQFYHQ57W5UU","short_pith_number":"pith:NKPFOUJ6","schema_version":"1.0","canonical_sha256":"6a9e57513e43d43d81702e0f0efedda514008417df2e6442426213b3e075d4b5","source":{"kind":"arxiv","id":"2203.10050","version":1},"attestation_state":"computed","paper":{"title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Honglak Lee, Jinwoo Shin, Jongjin Park, Kimin Lee, Pieter Abbeel, Younggyo Seo","submitted_at":"2022-03-18T16:50:38Z","abstract_excerpt":"Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent behaviors. However, preference-based learning often requires a large amount of human feedback, making it difficult to apply this approach to various applications. This data-efficiency problem, on the other hand, has been typically addressed by using unlabeled samples or data augmentation techniques in the context of supervised learning. Motivated by the recent su"},"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":"2203.10050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T16:50:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6befeca2faaaef0eb640989fe2b3d1825c063299b2dc10751fc89f2fa8aad33c","abstract_canon_sha256":"80c0a94397d029a9fca413cecd77fb7198b88944733c46d505cc8cb12def1e86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:27.354593Z","signature_b64":"V3WhG2EyimHLkzqJ2XlT24NMrWB9WBXeGHHmydOvZ4tXZN3De/+DNXc9QaQASU7v8aMtVf0TOznLkqfoqZoQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a9e57513e43d43d81702e0f0efedda514008417df2e6442426213b3e075d4b5","last_reissued_at":"2026-07-05T04:06:27.353946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:27.353946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Honglak Lee, Jinwoo Shin, Jongjin Park, Kimin Lee, Pieter Abbeel, Younggyo Seo","submitted_at":"2022-03-18T16:50:38Z","abstract_excerpt":"Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent behaviors. However, preference-based learning often requires a large amount of human feedback, making it difficult to apply this approach to various applications. This data-efficiency problem, on the other hand, has been typically addressed by using unlabeled samples or data augmentation techniques in the context of supervised learning. Motivated by the recent su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10050","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/2203.10050/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":"2203.10050","created_at":"2026-07-05T04:06:27.354026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10050v1","created_at":"2026-07-05T04:06:27.354026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10050","created_at":"2026-07-05T04:06:27.354026+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKPFOUJ6IPKD","created_at":"2026-07-05T04:06:27.354026+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKPFOUJ6IPKD3ALQ","created_at":"2026-07-05T04:06:27.354026+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKPFOUJ6","created_at":"2026-07-05T04:06:27.354026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25398","citing_title":"MAPL: Multi-Objective Preference Learning for Robot Locomotion","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24622","citing_title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23640","citing_title":"Learning Process Rewards via Success Visitation Matching for Efficient RL","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14648","citing_title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15134","citing_title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU","json":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU.json","graph_json":"https://pith.science/api/pith-number/NKPFOUJ6IPKD3ALQFYHQ57W5UU/graph.json","events_json":"https://pith.science/api/pith-number/NKPFOUJ6IPKD3ALQFYHQ57W5UU/events.json","paper":"https://pith.science/paper/NKPFOUJ6"},"agent_actions":{"view_html":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU","download_json":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU.json","view_paper":"https://pith.science/paper/NKPFOUJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10050&json=true","fetch_graph":"https://pith.science/api/pith-number/NKPFOUJ6IPKD3ALQFYHQ57W5UU/graph.json","fetch_events":"https://pith.science/api/pith-number/NKPFOUJ6IPKD3ALQFYHQ57W5UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/action/storage_attestation","attest_author":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/action/author_attestation","sign_citation":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/action/citation_signature","submit_replication":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/action/replication_record"}},"created_at":"2026-07-05T04:06:27.354026+00:00","updated_at":"2026-07-05T04:06:27.354026+00:00"}