{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6553DB6QLJ52HVWSM2ERZCOEFX","short_pith_number":"pith:6553DB6Q","canonical_record":{"source":{"id":"2303.00957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T04:24:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c766bbf901cf9eb4dd74925a3d3eeca3caf787265c8e833d0bb066d41e0e11f8","abstract_canon_sha256":"6b93aa2a85e3f0a0a655e0d8951eb636823033d966d1eb8ea3c07acc320fbdc1"},"schema_version":"1.0"},"canonical_sha256":"f77bb187d05a7ba3d6d266891c89c42de635dbfc9df38930cbc3816b93a71ec5","source":{"kind":"arxiv","id":"2303.00957","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00957","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00957v1","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00957","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"6553DB6QLJ52","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"pith_short_16","alias_value":"6553DB6QLJ52HVWS","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"pith_short_8","alias_value":"6553DB6Q","created_at":"2026-07-05T05:47:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6553DB6QLJ52HVWSM2ERZCOEFX","target":"record","payload":{"canonical_record":{"source":{"id":"2303.00957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T04:24:29Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c766bbf901cf9eb4dd74925a3d3eeca3caf787265c8e833d0bb066d41e0e11f8","abstract_canon_sha256":"6b93aa2a85e3f0a0a655e0d8951eb636823033d966d1eb8ea3c07acc320fbdc1"},"schema_version":"1.0"},"canonical_sha256":"f77bb187d05a7ba3d6d266891c89c42de635dbfc9df38930cbc3816b93a71ec5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:24.855375Z","signature_b64":"0ivAGiUcM79xTiyRKB0ZE621RGiBXPgd1xM9qzlilWPEhMGv2+DZQyZQzbb/fodWLBAKvX0RnV11Y3DoUJ5kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f77bb187d05a7ba3d6d266891c89c42de635dbfc9df38930cbc3816b93a71ec5","last_reissued_at":"2026-07-05T05:47:24.854946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:24.854946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.00957","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":"2026-07-05T05:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TKmlTznRU3gIgMyv0NwgAXvkHJCiba96Xht7PKolZ3ipi5n3Bh7Mi+kRnA70kU3qANRwBQ5I/GL6l7rGI6IjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T22:11:31.054872Z"},"content_sha256":"fbd4a5f3998e2c201b37b462b1dc7fe4bd10c530deedbce56bf40ba5e46e124b","schema_version":"1.0","event_id":"sha256:fbd4a5f3998e2c201b37b462b1dc7fe4bd10c530deedbce56bf40ba5e46e124b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6553DB6QLJ52HVWSM2ERZCOEFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Changyeon Kim, Honglak Lee, Jinwoo Shin, Jongjin Park, Kimin Lee, Pieter Abbeel","submitted_at":"2023-03-02T04:24:29Z","abstract_excerpt":"Preference-based reinforcement learning (RL) provides a framework to train agents using human preferences between two behaviors. However, preference-based RL has been challenging to scale since it requires a large amount of human feedback to learn a reward function aligned with human intent. In this paper, we present Preference Transformer, a neural architecture that models human preferences using transformers. Unlike prior approaches assuming human judgment is based on the Markovian rewards which contribute to the decision equally, we introduce a new preference model based on the weighted sum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00957","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/2303.00957/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":"2026-07-05T05:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WzNMmmabt6ndFThUH1J0YdVRRu9E90vCqV090RWFMbzxf5aBx8bvHxu68H1pHxI2IM5Mo8bHbiUlOXY/4n4gAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T22:11:31.055265Z"},"content_sha256":"e528b27ed7f59c6e711af4a5cdfbe5c729f4a188d98f4ee8fb6fc0b45107d422","schema_version":"1.0","event_id":"sha256:e528b27ed7f59c6e711af4a5cdfbe5c729f4a188d98f4ee8fb6fc0b45107d422"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6553DB6QLJ52HVWSM2ERZCOEFX/bundle.json","state_url":"https://pith.science/pith/6553DB6QLJ52HVWSM2ERZCOEFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6553DB6QLJ52HVWSM2ERZCOEFX/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":"2026-07-19T22:11:31Z","links":{"resolver":"https://pith.science/pith/6553DB6QLJ52HVWSM2ERZCOEFX","bundle":"https://pith.science/pith/6553DB6QLJ52HVWSM2ERZCOEFX/bundle.json","state":"https://pith.science/pith/6553DB6QLJ52HVWSM2ERZCOEFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6553DB6QLJ52HVWSM2ERZCOEFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6553DB6QLJ52HVWSM2ERZCOEFX","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":"6b93aa2a85e3f0a0a655e0d8951eb636823033d966d1eb8ea3c07acc320fbdc1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T04:24:29Z","title_canon_sha256":"c766bbf901cf9eb4dd74925a3d3eeca3caf787265c8e833d0bb066d41e0e11f8"},"schema_version":"1.0","source":{"id":"2303.00957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00957","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00957v1","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00957","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"6553DB6QLJ52","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"pith_short_16","alias_value":"6553DB6QLJ52HVWS","created_at":"2026-07-05T05:47:24Z"},{"alias_kind":"pith_short_8","alias_value":"6553DB6Q","created_at":"2026-07-05T05:47:24Z"}],"graph_snapshots":[{"event_id":"sha256:e528b27ed7f59c6e711af4a5cdfbe5c729f4a188d98f4ee8fb6fc0b45107d422","target":"graph","created_at":"2026-07-05T05:47:24Z","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/2303.00957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (RL) provides a framework to train agents using human preferences between two behaviors. However, preference-based RL has been challenging to scale since it requires a large amount of human feedback to learn a reward function aligned with human intent. In this paper, we present Preference Transformer, a neural architecture that models human preferences using transformers. Unlike prior approaches assuming human judgment is based on the Markovian rewards which contribute to the decision equally, we introduce a new preference model based on the weighted sum","authors_text":"Changyeon Kim, Honglak Lee, Jinwoo Shin, Jongjin Park, Kimin Lee, Pieter Abbeel","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T04:24:29Z","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00957","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:fbd4a5f3998e2c201b37b462b1dc7fe4bd10c530deedbce56bf40ba5e46e124b","target":"record","created_at":"2026-07-05T05:47:24Z","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":"6b93aa2a85e3f0a0a655e0d8951eb636823033d966d1eb8ea3c07acc320fbdc1","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T04:24:29Z","title_canon_sha256":"c766bbf901cf9eb4dd74925a3d3eeca3caf787265c8e833d0bb066d41e0e11f8"},"schema_version":"1.0","source":{"id":"2303.00957","kind":"arxiv","version":1}},"canonical_sha256":"f77bb187d05a7ba3d6d266891c89c42de635dbfc9df38930cbc3816b93a71ec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f77bb187d05a7ba3d6d266891c89c42de635dbfc9df38930cbc3816b93a71ec5","first_computed_at":"2026-07-05T05:47:24.854946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:24.854946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ivAGiUcM79xTiyRKB0ZE621RGiBXPgd1xM9qzlilWPEhMGv2+DZQyZQzbb/fodWLBAKvX0RnV11Y3DoUJ5kCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:24.855375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbd4a5f3998e2c201b37b462b1dc7fe4bd10c530deedbce56bf40ba5e46e124b","sha256:e528b27ed7f59c6e711af4a5cdfbe5c729f4a188d98f4ee8fb6fc0b45107d422"],"state_sha256":"e757cb6995f10c68cf13e99887b8df2a37f4693bd19a1201991318eb64989ec9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5K8KYRCrfC3fzHgYDy7AKtPj3/+w5QwgVFzON4LMkoMDL/W/Sele7LZ0rOOY7HJurgT/dmFNYT1ng5vqMmtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T22:11:31.057474Z","bundle_sha256":"d1c6c39df962af3c1f655c84fff91c11e639bcbaa7fd8690e230c0b4c91d7b04"}}