{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NKPFOUJ6IPKD3ALQFYHQ57W5UU","short_pith_number":"pith:NKPFOUJ6","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"},"canonical_sha256":"6a9e57513e43d43d81702e0f0efedda514008417df2e6442426213b3e075d4b5","source":{"kind":"arxiv","id":"2203.10050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10050","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10050v1","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10050","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"NKPFOUJ6IPKD","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"NKPFOUJ6IPKD3ALQ","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"NKPFOUJ6","created_at":"2026-07-05T04:06:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NKPFOUJ6IPKD3ALQFYHQ57W5UU","target":"record","payload":{"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"},"canonical_sha256":"6a9e57513e43d43d81702e0f0efedda514008417df2e6442426213b3e075d4b5","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"},"source_kind":"arxiv","source_id":"2203.10050","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SZYOzmsIp8gdUH5xzqB2c/lYSdP/VUlYBvoHgmJiRzHG+S7iYEluMzIxuVkB/mvvba26EYyIly0TKLYoeYMBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:02.797804Z"},"content_sha256":"ee346e48624f28a86a10986498bab74bb7fda13ab737de7a27b24e03e457e76f","schema_version":"1.0","event_id":"sha256:ee346e48624f28a86a10986498bab74bb7fda13ab737de7a27b24e03e457e76f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NKPFOUJ6IPKD3ALQFYHQ57W5UU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1GilDeL0D2afTZOfzA6wWcBuYXQKQ6Uq32WBQ+nI+9mnY/8KeqpZYo4kIDH0TKvM0OAoAyLW6uxGPINW2NXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:02.798296Z"},"content_sha256":"ef91e082663f16bf51b98d22c86fdd92bf05c43f5305a5ba1cf71e7b07a5980e","schema_version":"1.0","event_id":"sha256:ef91e082663f16bf51b98d22c86fdd92bf05c43f5305a5ba1cf71e7b07a5980e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/bundle.json","state_url":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T13:57:02Z","links":{"resolver":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU","bundle":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/bundle.json","state":"https://pith.science/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKPFOUJ6IPKD3ALQFYHQ57W5UU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NKPFOUJ6IPKD3ALQFYHQ57W5UU","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":"80c0a94397d029a9fca413cecd77fb7198b88944733c46d505cc8cb12def1e86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T16:50:38Z","title_canon_sha256":"6befeca2faaaef0eb640989fe2b3d1825c063299b2dc10751fc89f2fa8aad33c"},"schema_version":"1.0","source":{"id":"2203.10050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10050","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10050v1","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10050","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"NKPFOUJ6IPKD","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"NKPFOUJ6IPKD3ALQ","created_at":"2026-07-05T04:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"NKPFOUJ6","created_at":"2026-07-05T04:06:27Z"}],"graph_snapshots":[{"event_id":"sha256:ef91e082663f16bf51b98d22c86fdd92bf05c43f5305a5ba1cf71e7b07a5980e","target":"graph","created_at":"2026-07-05T04:06:27Z","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/2203.10050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Honglak Lee, Jinwoo Shin, Jongjin Park, Kimin Lee, Pieter Abbeel, Younggyo Seo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T16:50:38Z","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10050","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:ee346e48624f28a86a10986498bab74bb7fda13ab737de7a27b24e03e457e76f","target":"record","created_at":"2026-07-05T04:06:27Z","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":"80c0a94397d029a9fca413cecd77fb7198b88944733c46d505cc8cb12def1e86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-18T16:50:38Z","title_canon_sha256":"6befeca2faaaef0eb640989fe2b3d1825c063299b2dc10751fc89f2fa8aad33c"},"schema_version":"1.0","source":{"id":"2203.10050","kind":"arxiv","version":1}},"canonical_sha256":"6a9e57513e43d43d81702e0f0efedda514008417df2e6442426213b3e075d4b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a9e57513e43d43d81702e0f0efedda514008417df2e6442426213b3e075d4b5","first_computed_at":"2026-07-05T04:06:27.353946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:27.353946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V3WhG2EyimHLkzqJ2XlT24NMrWB9WBXeGHHmydOvZ4tXZN3De/+DNXc9QaQASU7v8aMtVf0TOznLkqfoqZoQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:27.354593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee346e48624f28a86a10986498bab74bb7fda13ab737de7a27b24e03e457e76f","sha256:ef91e082663f16bf51b98d22c86fdd92bf05c43f5305a5ba1cf71e7b07a5980e"],"state_sha256":"6621dd5d00af7544d6c396d57696ebc5bd333c91a2aa446cda7510969fd7553e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbAlcr4eJwL/Ig2Iv9xU7AZ71h675F5/Eym4fDdG6vdvuGCyD3Ju7ElNwRKCQkaMrETZGRBSkp5M1rpCUYVQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:57:02.802977Z","bundle_sha256":"cb1e98eb2317d4a22b5cdc0421c1c2a7bc7c76c2ea47c21b03fc0806b64f306e"}}