{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:URI2DUCNJSTIRFZU3C6T7Z4ICD","short_pith_number":"pith:URI2DUCN","canonical_record":{"source":{"id":"2301.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T22:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"8399b1342d9d2e8a814ad2e1a8c359c71826910b79b2577c6808e543201c79e6","abstract_canon_sha256":"1accddcd0b77043c599528d884cbc9b79c65195bb31080537a92f1671d028a29"},"schema_version":"1.0"},"canonical_sha256":"a451a1d04d4ca6889734d8bd3fe78810e018075c9cd5d9bcb320f4438e3ce559","source":{"kind":"arxiv","id":"2301.04741","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04741","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04741v2","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04741","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"URI2DUCNJSTI","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"URI2DUCNJSTIRFZU","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"URI2DUCN","created_at":"2026-07-05T07:43:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:URI2DUCNJSTIRFZU3C6T7Z4ICD","target":"record","payload":{"canonical_record":{"source":{"id":"2301.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T22:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"8399b1342d9d2e8a814ad2e1a8c359c71826910b79b2577c6808e543201c79e6","abstract_canon_sha256":"1accddcd0b77043c599528d884cbc9b79c65195bb31080537a92f1671d028a29"},"schema_version":"1.0"},"canonical_sha256":"a451a1d04d4ca6889734d8bd3fe78810e018075c9cd5d9bcb320f4438e3ce559","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:30.003253Z","signature_b64":"YClpzMPcOgvMMcrG8CTWnzrO815N5ZOO0wTN/7BhN6PRCuR1QzVGJv5IEcUbNG7ejsvS5uwxaHmkHb0/IDjsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a451a1d04d4ca6889734d8bd3fe78810e018075c9cd5d9bcb320f4438e3ce559","last_reissued_at":"2026-07-05T07:43:30.002701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:30.002701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.04741","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7ahVRg7tkNWNKKkeZM8JWBdv7Sr95zn8QADfY2dakojsg0WaBxFudpXQPl6uncMdLoY6c3b4lDK9KFBduW6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:59:48.885246Z"},"content_sha256":"d10dfc75a53daa32e3d9dc938710b539f8f00b4dfd0b6833e9979c549b6d14df","schema_version":"1.0","event_id":"sha256:d10dfc75a53daa32e3d9dc938710b539f8f00b4dfd0b6833e9979c549b6d14df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:URI2DUCNJSTIRFZU3C6T7Z4ICD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel S. Brown, Ellen Novoseller, Gaurav Datta, Yi Liu","submitted_at":"2023-01-11T22:22:54Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a high-fidelity simulator or analytic model or take a model-free approach that requires extensive, possibly unsafe online environment interactions. In this paper, we study the benefits and challenges of using a learned dynamics model when performing PbRL. In particular, we provide evidence that a learned dynamics model offers the following benefits when performing Pb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04741","kind":"arxiv","version":2},"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/2301.04741/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":"2026-07-05T07:43:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPhisJPEgxNRK6FYXVboi0LyaQmAZbMniOY09sGv97FluxUTmoIS/2UgKKKWKPjAC0SUQhF87OLfvu/shG3EDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:59:48.885652Z"},"content_sha256":"4c33b816bbbc809316b374c2af0da662c9d9e71b677b71b7cda0e5860bc7e864","schema_version":"1.0","event_id":"sha256:4c33b816bbbc809316b374c2af0da662c9d9e71b677b71b7cda0e5860bc7e864"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/bundle.json","state_url":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/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":"2026-07-06T16:59:48Z","links":{"resolver":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD","bundle":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/bundle.json","state":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:URI2DUCNJSTIRFZU3C6T7Z4ICD","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":"1accddcd0b77043c599528d884cbc9b79c65195bb31080537a92f1671d028a29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T22:22:54Z","title_canon_sha256":"8399b1342d9d2e8a814ad2e1a8c359c71826910b79b2577c6808e543201c79e6"},"schema_version":"1.0","source":{"id":"2301.04741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.04741","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"arxiv_version","alias_value":"2301.04741v2","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04741","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"pith_short_12","alias_value":"URI2DUCNJSTI","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"pith_short_16","alias_value":"URI2DUCNJSTIRFZU","created_at":"2026-07-05T07:43:30Z"},{"alias_kind":"pith_short_8","alias_value":"URI2DUCN","created_at":"2026-07-05T07:43:30Z"}],"graph_snapshots":[{"event_id":"sha256:4c33b816bbbc809316b374c2af0da662c9d9e71b677b71b7cda0e5860bc7e864","target":"graph","created_at":"2026-07-05T07:43:30Z","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/2301.04741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a high-fidelity simulator or analytic model or take a model-free approach that requires extensive, possibly unsafe online environment interactions. In this paper, we study the benefits and challenges of using a learned dynamics model when performing PbRL. In particular, we provide evidence that a learned dynamics model offers the following benefits when performing Pb","authors_text":"Daniel S. Brown, Ellen Novoseller, Gaurav Datta, Yi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T22:22:54Z","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04741","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:d10dfc75a53daa32e3d9dc938710b539f8f00b4dfd0b6833e9979c549b6d14df","target":"record","created_at":"2026-07-05T07:43:30Z","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":"1accddcd0b77043c599528d884cbc9b79c65195bb31080537a92f1671d028a29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T22:22:54Z","title_canon_sha256":"8399b1342d9d2e8a814ad2e1a8c359c71826910b79b2577c6808e543201c79e6"},"schema_version":"1.0","source":{"id":"2301.04741","kind":"arxiv","version":2}},"canonical_sha256":"a451a1d04d4ca6889734d8bd3fe78810e018075c9cd5d9bcb320f4438e3ce559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a451a1d04d4ca6889734d8bd3fe78810e018075c9cd5d9bcb320f4438e3ce559","first_computed_at":"2026-07-05T07:43:30.002701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:30.002701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YClpzMPcOgvMMcrG8CTWnzrO815N5ZOO0wTN/7BhN6PRCuR1QzVGJv5IEcUbNG7ejsvS5uwxaHmkHb0/IDjsCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:30.003253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.04741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d10dfc75a53daa32e3d9dc938710b539f8f00b4dfd0b6833e9979c549b6d14df","sha256:4c33b816bbbc809316b374c2af0da662c9d9e71b677b71b7cda0e5860bc7e864"],"state_sha256":"3f77a8aaa368bcc70ca76ec2da150e68b84865f0d3827a292e86bd5cf0a1fbbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nO6VjeujrtbUMIAQ5Mlb6SRUH6k5hUivs8T8dbD7DkakFhWMcwz2DjvgqAhIH3u6oCGMgGw+yZ1Dmu4YK8gXBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:59:48.888103Z","bundle_sha256":"b5a66deafdf90a3f18c3acda8ace03879fbdb3a936838604c061b9c9c2696acf"}}