{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7NXWRYFS36RY6G63OK7WIYXOV7","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":"5fee1d0b5bcc2eed64d9d67122dca64ffaf592cd771df36758ed04a17e16df6f","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T17:59:28Z","title_canon_sha256":"cde4f46f4f4418bbb0ea45ada2dd300417db3652a663eab8279855bbd5cdcac1"},"schema_version":"1.0","source":{"id":"2305.03047","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03047","created_at":"2026-07-05T07:19:19Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03047v2","created_at":"2026-07-05T07:19:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03047","created_at":"2026-07-05T07:19:19Z"},{"alias_kind":"pith_short_12","alias_value":"7NXWRYFS36RY","created_at":"2026-07-05T07:19:19Z"},{"alias_kind":"pith_short_16","alias_value":"7NXWRYFS36RY6G63","created_at":"2026-07-05T07:19:19Z"},{"alias_kind":"pith_short_8","alias_value":"7NXWRYFS","created_at":"2026-07-05T07:19:19Z"}],"graph_snapshots":[{"event_id":"sha256:81f913dc59da62a9ec0b601bd29520c6a724fb139c6c7e2cca75e1384d770291","target":"graph","created_at":"2026-07-05T07:19:19Z","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/2305.03047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of large language models (LLMs) with human intentions, ensuring they are helpful, ethical, and reliable. However, this dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision and the related issues on quality, reliability, diversity, self-consistency, and undesirable biases. To address these challenges, we propose a novel approa","authors_text":"Chuang Gan, David Cox, Hongxin Zhang, Qinhong Zhou, Yikang Shen, Yiming Yang, Zhenfang Chen, Zhiqing Sun","cross_cats":["cs.AI","cs.CL","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T17:59:28Z","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03047","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":"sha256:745eab36f568aa95dc988338586f2f909111dcd6ace8bb3433392c2feeaaae1a","target":"record","created_at":"2026-07-05T07:19:19Z","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":"5fee1d0b5bcc2eed64d9d67122dca64ffaf592cd771df36758ed04a17e16df6f","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-04T17:59:28Z","title_canon_sha256":"cde4f46f4f4418bbb0ea45ada2dd300417db3652a663eab8279855bbd5cdcac1"},"schema_version":"1.0","source":{"id":"2305.03047","kind":"arxiv","version":2}},"canonical_sha256":"fb6f68e0b2dfa38f1bdb72bf6462eeafc83af6f8be5b14fa297050b8510aeb4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb6f68e0b2dfa38f1bdb72bf6462eeafc83af6f8be5b14fa297050b8510aeb4a","first_computed_at":"2026-07-05T07:19:19.838735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:19.838735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a6Zp91PXWIdAG9NAKpiXcCN5I7ItQwTdXE4pfUPYB/j0I4Ya0PtFCzHUD6Fa8NloQpRkefTivgNGRO5hgwTVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:19.839246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03047","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:745eab36f568aa95dc988338586f2f909111dcd6ace8bb3433392c2feeaaae1a","sha256:81f913dc59da62a9ec0b601bd29520c6a724fb139c6c7e2cca75e1384d770291"],"state_sha256":"38efb0a6cf7fcb84d4b24c810b493900ec783dcd3edbf97f84e068dc77cc9f11"}