{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5QVHR4QMBWYXQGPQSLPF2M2VIX","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":"86fa098a7239ab6c351d0f94eb07e76ccc15c6c4172bd17362b7a08b2df41b00","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T17:56:53Z","title_canon_sha256":"a2dd79751ef39d8cdb97201cd18c25348d7fd1c55b6ff7b08cd985135a36d309"},"schema_version":"1.0","source":{"id":"2310.05910","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05910","created_at":"2026-07-05T08:06:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05910v2","created_at":"2026-07-05T08:06:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05910","created_at":"2026-07-05T08:06:11Z"},{"alias_kind":"pith_short_12","alias_value":"5QVHR4QMBWYX","created_at":"2026-07-05T08:06:11Z"},{"alias_kind":"pith_short_16","alias_value":"5QVHR4QMBWYXQGPQ","created_at":"2026-07-05T08:06:11Z"},{"alias_kind":"pith_short_8","alias_value":"5QVHR4QM","created_at":"2026-07-05T08:06:11Z"}],"graph_snapshots":[{"event_id":"sha256:68cb0a6f7042526174d8c7501889ff77afc94f8cffd25b54a5b3686bee62be12","target":"graph","created_at":"2026-07-05T08:06:11Z","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/2310.05910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised Fine-Tuning (SFT) on response demonstrations combined with Reinforcement Learning from Human Feedback (RLHF) constitutes a powerful paradigm for aligning LLM-based AI agents. However, a significant limitation of such an approach is its dependency on high-quality human annotations, making its application to intricate tasks challenging due to difficulties in obtaining consistent response demonstrations and in-distribution response preferences. This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision, using only a small set of hu","authors_text":"Chuang Gan, David Cox, Hongxin Zhang, Qinhong Zhou, Yikang Shen, Yiming Yang, Zhenfang Chen, Zhiqing Sun","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T17:56:53Z","title":"SALMON: Self-Alignment with Instructable Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05910","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":"sha256:4e7c6918314ea7f2d15a027c70a9ac6e9ffa807f769605d0a430eea6aafdaa63","target":"record","created_at":"2026-07-05T08:06:11Z","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":"86fa098a7239ab6c351d0f94eb07e76ccc15c6c4172bd17362b7a08b2df41b00","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T17:56:53Z","title_canon_sha256":"a2dd79751ef39d8cdb97201cd18c25348d7fd1c55b6ff7b08cd985135a36d309"},"schema_version":"1.0","source":{"id":"2310.05910","kind":"arxiv","version":2}},"canonical_sha256":"ec2a78f20c0db17819f092de5d335545f521dbbd052780c9c1208888f6af99ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec2a78f20c0db17819f092de5d335545f521dbbd052780c9c1208888f6af99ef","first_computed_at":"2026-07-05T08:06:11.662386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:11.662386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7qgk5OGjt8XPUiwN41tc+cf9w4FpNZ6glkE2PlLqn0LLkIRGLwB8G2UQLBZRYaY4mfUksxSFk5CfRcPqLi74Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:11.662891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05910","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e7c6918314ea7f2d15a027c70a9ac6e9ffa807f769605d0a430eea6aafdaa63","sha256:68cb0a6f7042526174d8c7501889ff77afc94f8cffd25b54a5b3686bee62be12"],"state_sha256":"1a823a38b816137ee46bad6fa8260fab9c2de2ccd6b91597c8b6744a3461d0fb"}