{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:U3GA6365DJGCQ5WN7OKA2WMCRW","short_pith_number":"pith:U3GA6365","canonical_record":{"source":{"id":"2305.13735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:41:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a8430caf9ea36ba54e6eba59272a8f2eaf76cf4df68cb92e3dd0ebd1099a97ca","abstract_canon_sha256":"aabb4775ea34af123b25b76cf8aa2559cb564738e8435c4d8e07490792d35bf8"},"schema_version":"1.0"},"canonical_sha256":"a6cc0f6fdd1a4c2876cdfb940d59828da7802c0a1124e261f1ef29faaa365981","source":{"kind":"arxiv","id":"2305.13735","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13735","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13735v2","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13735","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"U3GA6365DJGC","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"U3GA6365DJGCQ5WN","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"U3GA6365","created_at":"2026-07-05T07:03:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:U3GA6365DJGCQ5WN7OKA2WMCRW","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13735","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:41:16Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a8430caf9ea36ba54e6eba59272a8f2eaf76cf4df68cb92e3dd0ebd1099a97ca","abstract_canon_sha256":"aabb4775ea34af123b25b76cf8aa2559cb564738e8435c4d8e07490792d35bf8"},"schema_version":"1.0"},"canonical_sha256":"a6cc0f6fdd1a4c2876cdfb940d59828da7802c0a1124e261f1ef29faaa365981","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:25.236116Z","signature_b64":"tjqsAQipPEQGetOc6GRHrT+ySC1S8gm/gDM8PwIdzXS5v/M5Hl5QQAZdFM1YAGkx7GA4ORvZEtCrAkODekL4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6cc0f6fdd1a4c2876cdfb940d59828da7802c0a1124e261f1ef29faaa365981","last_reissued_at":"2026-07-05T07:03:25.235653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:25.235653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13735","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":"2026-07-05T07:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uJq66LiWCjNhisodFx+NQi/33Rt+CceePe3qgWtCBMM95h16PDXA/35VB+8OOXiJ0IrvMbeeg65NKhIH/wjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:22.066959Z"},"content_sha256":"de2608805eb7ee13647d6d97b479af1921def6e4024df3902da28250ed21deaa","schema_version":"1.0","event_id":"sha256:de2608805eb7ee13647d6d97b479af1921def6e4024df3902da28250ed21deaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:U3GA6365DJGCQ5WN7OKA2WMCRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Large Language Models through Synthetic Feedback","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Donghyun Kwak, Jamin Shin, Kang Min Yoo, Minjoon Seo, Sanghwan Bae, Soyoung Kang, Sungdong Kim","submitted_at":"2023-05-23T06:41:16Z","abstract_excerpt":"Aligning large language models (LLMs) to human values has become increasingly important as it enables sophisticated steering of LLMs. However, it requires significant human demonstrations and feedback or distillation from proprietary LLMs such as ChatGPT. In this work, we propose a novel alignment learning framework with synthetic feedback not dependent on extensive human annotations and proprietary LLMs. First, we perform reward modeling (RM) with synthetic feedback by contrasting responses from vanilla LLMs with various sizes and prompts. Then, we use the RM to simulate high-quality demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13735","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/2305.13735/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":"2026-07-05T07:03:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beVKYeYHgWZd/b4d/ZHRSrPR9DWj3VHVadyqu6hrcHgCOBvcIVHz0ETl2Y8MglKJ4+M5UrHervcWAG+sEjRjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:20:22.067496Z"},"content_sha256":"d57d62c9c044c281a8468363ff02ad1f77cc038d8c12ad67c7f6098f30e94df4","schema_version":"1.0","event_id":"sha256:d57d62c9c044c281a8468363ff02ad1f77cc038d8c12ad67c7f6098f30e94df4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3GA6365DJGCQ5WN7OKA2WMCRW/bundle.json","state_url":"https://pith.science/pith/U3GA6365DJGCQ5WN7OKA2WMCRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3GA6365DJGCQ5WN7OKA2WMCRW/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":"2026-08-09T11:20:22Z","links":{"resolver":"https://pith.science/pith/U3GA6365DJGCQ5WN7OKA2WMCRW","bundle":"https://pith.science/pith/U3GA6365DJGCQ5WN7OKA2WMCRW/bundle.json","state":"https://pith.science/pith/U3GA6365DJGCQ5WN7OKA2WMCRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3GA6365DJGCQ5WN7OKA2WMCRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U3GA6365DJGCQ5WN7OKA2WMCRW","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":"aabb4775ea34af123b25b76cf8aa2559cb564738e8435c4d8e07490792d35bf8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:41:16Z","title_canon_sha256":"a8430caf9ea36ba54e6eba59272a8f2eaf76cf4df68cb92e3dd0ebd1099a97ca"},"schema_version":"1.0","source":{"id":"2305.13735","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13735","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13735v2","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13735","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"U3GA6365DJGC","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"U3GA6365DJGCQ5WN","created_at":"2026-07-05T07:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"U3GA6365","created_at":"2026-07-05T07:03:25Z"}],"graph_snapshots":[{"event_id":"sha256:d57d62c9c044c281a8468363ff02ad1f77cc038d8c12ad67c7f6098f30e94df4","target":"graph","created_at":"2026-07-05T07:03:25Z","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/2305.13735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models (LLMs) to human values has become increasingly important as it enables sophisticated steering of LLMs. However, it requires significant human demonstrations and feedback or distillation from proprietary LLMs such as ChatGPT. In this work, we propose a novel alignment learning framework with synthetic feedback not dependent on extensive human annotations and proprietary LLMs. First, we perform reward modeling (RM) with synthetic feedback by contrasting responses from vanilla LLMs with various sizes and prompts. Then, we use the RM to simulate high-quality demonstr","authors_text":"Donghyun Kwak, Jamin Shin, Kang Min Yoo, Minjoon Seo, Sanghwan Bae, Soyoung Kang, Sungdong Kim","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:41:16Z","title":"Aligning Large Language Models through Synthetic Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13735","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:de2608805eb7ee13647d6d97b479af1921def6e4024df3902da28250ed21deaa","target":"record","created_at":"2026-07-05T07:03:25Z","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":"aabb4775ea34af123b25b76cf8aa2559cb564738e8435c4d8e07490792d35bf8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T06:41:16Z","title_canon_sha256":"a8430caf9ea36ba54e6eba59272a8f2eaf76cf4df68cb92e3dd0ebd1099a97ca"},"schema_version":"1.0","source":{"id":"2305.13735","kind":"arxiv","version":2}},"canonical_sha256":"a6cc0f6fdd1a4c2876cdfb940d59828da7802c0a1124e261f1ef29faaa365981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6cc0f6fdd1a4c2876cdfb940d59828da7802c0a1124e261f1ef29faaa365981","first_computed_at":"2026-07-05T07:03:25.235653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:25.235653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tjqsAQipPEQGetOc6GRHrT+ySC1S8gm/gDM8PwIdzXS5v/M5Hl5QQAZdFM1YAGkx7GA4ORvZEtCrAkODekL4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:25.236116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13735","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de2608805eb7ee13647d6d97b479af1921def6e4024df3902da28250ed21deaa","sha256:d57d62c9c044c281a8468363ff02ad1f77cc038d8c12ad67c7f6098f30e94df4"],"state_sha256":"4fcf54fef181c97d0510ed2edbb4891ff43cf2230262857ca23425827a32a73a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XIuJjTv0/7+uvpMMFPO3x5GxsZsR54fkEiamdwDm6QLR39gTKqR8gB/izIou4Q1n/bmvxXPkueIi2KpJo5+qAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:20:22.071105Z","bundle_sha256":"3329f4bab82cadb577c9bc196559a6208c2eba6e1262dfddc871efc976f1a068"}}