{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ED6M5RPVEJ5QVVTAETO4QQETH2","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":"a0a733c310aab809d90853194b5ec270aad3bbdca2325ac591b9e2814856f05c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-06T14:00:12Z","title_canon_sha256":"05450a21b7db6f43197fdcb440c35d7bef2a2d36b0989b83a1eb29defb595123"},"schema_version":"1.0","source":{"id":"2401.06785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06785","created_at":"2026-07-05T07:33:26Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06785v1","created_at":"2026-07-05T07:33:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06785","created_at":"2026-07-05T07:33:26Z"},{"alias_kind":"pith_short_12","alias_value":"ED6M5RPVEJ5Q","created_at":"2026-07-05T07:33:26Z"},{"alias_kind":"pith_short_16","alias_value":"ED6M5RPVEJ5QVVTA","created_at":"2026-07-05T07:33:26Z"},{"alias_kind":"pith_short_8","alias_value":"ED6M5RPV","created_at":"2026-07-05T07:33:26Z"}],"graph_snapshots":[{"event_id":"sha256:e92646e0de18e9423b4a319bd28f64bf650877ad147228146537fffbb9f2100b","target":"graph","created_at":"2026-07-05T07:33:26Z","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/2401.06785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models (LLMs) with human values is a vital task for LLM practitioners. Current alignment techniques have several limitations: (1) requiring a large amount of annotated data; (2) demanding heavy human involvement; (3) lacking a systematic mechanism to continuously improve. In this work, we study aligning LLMs to a new domain with limited samples (e.g. < 100). We propose an algorithm that can self-align LLMs iteratively without active human involvement. Unlike existing works, our algorithm relies on neither human-crafted instructions nor labeled rewards, significantly red","authors_text":"Hongyi Guo, Jiaheng Wei, Wei Shen, Xiaoying Zhang, Yang Liu, Yuanshun Yao, Zhaoran Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-06T14:00:12Z","title":"Human-Instruction-Free LLM Self-Alignment with Limited Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06785","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:ccd49e4f5f77f99f4e3a4529678473d467ffe464492947eadbbd3d22041419e1","target":"record","created_at":"2026-07-05T07:33:26Z","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":"a0a733c310aab809d90853194b5ec270aad3bbdca2325ac591b9e2814856f05c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-06T14:00:12Z","title_canon_sha256":"05450a21b7db6f43197fdcb440c35d7bef2a2d36b0989b83a1eb29defb595123"},"schema_version":"1.0","source":{"id":"2401.06785","kind":"arxiv","version":1}},"canonical_sha256":"20fccec5f5227b0ad66024ddc840933ebb17926545f61b19278a4795f385e4bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20fccec5f5227b0ad66024ddc840933ebb17926545f61b19278a4795f385e4bf","first_computed_at":"2026-07-05T07:33:26.345835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:26.345835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vYIqss6F+LKY+XZl6d/gS3dBbB8rHNeZ5Qx3ps0dOSIM5GQOorjRlAiVA0eGTNeuWdc9hqlICmDjfEuVqWp0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:26.346338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccd49e4f5f77f99f4e3a4529678473d467ffe464492947eadbbd3d22041419e1","sha256:e92646e0de18e9423b4a319bd28f64bf650877ad147228146537fffbb9f2100b"],"state_sha256":"cc06fc44976639a8402ec47c5ca393dcab73d2acdbae2a84907a3f8274449219"}