{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FZMFAVZF5QPMYNFFQNT55CUI6T","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":"40fc9fab9af34ae9b3319d85e5be1138e2dfa4c7cc3bded44c9cdf5114b7ac7b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T02:11:21Z","title_canon_sha256":"a5c1921d0fde9e6d7a23ce1d8bb294f2546add8f273496cee3a8421ef5995d2c"},"schema_version":"1.0","source":{"id":"2310.05344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05344","created_at":"2026-07-05T06:58:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05344v1","created_at":"2026-07-05T06:58:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05344","created_at":"2026-07-05T06:58:44Z"},{"alias_kind":"pith_short_12","alias_value":"FZMFAVZF5QPM","created_at":"2026-07-05T06:58:44Z"},{"alias_kind":"pith_short_16","alias_value":"FZMFAVZF5QPMYNFF","created_at":"2026-07-05T06:58:44Z"},{"alias_kind":"pith_short_8","alias_value":"FZMFAVZF","created_at":"2026-07-05T06:58:44Z"}],"graph_snapshots":[{"event_id":"sha256:2864444b9539db6cd0e70435d27a805ca8b2164340cc63d21e4761dbc7c1a2a6","target":"graph","created_at":"2026-07-05T06:58:44Z","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/2310.05344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) stages. However, RLHF faces inherent limitations stemming from a complex training setup and its tendency to align the model with implicit values that end users cannot control at run-time. Moreover, reward models in RLHF stage commonly rely on single-dimensional feedback as opposed to explicit, multifaceted signals that indicate attributes such as he","authors_text":"Makesh Narsimhan Sreedhar, Oleksii Kuchaiev, Xianchao Wu, Yi Dong, Zhilin Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T02:11:21Z","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05344","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":"sha256:0de6c638109d4f690931892c3f1c840df5764b3b8bad6b933423948ff9972246","target":"record","created_at":"2026-07-05T06:58:44Z","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":"40fc9fab9af34ae9b3319d85e5be1138e2dfa4c7cc3bded44c9cdf5114b7ac7b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T02:11:21Z","title_canon_sha256":"a5c1921d0fde9e6d7a23ce1d8bb294f2546add8f273496cee3a8421ef5995d2c"},"schema_version":"1.0","source":{"id":"2310.05344","kind":"arxiv","version":1}},"canonical_sha256":"2e58505725ec1ecc34a58367de8a88f4c973a8eb3fbe1d73d5bc416cc196b314","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e58505725ec1ecc34a58367de8a88f4c973a8eb3fbe1d73d5bc416cc196b314","first_computed_at":"2026-07-05T06:58:44.028042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:44.028042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"23s8Kr/wbSB8riAxIp3UkDx9lzM4pgLN0O/+xCy5T8WZ8Q9B9GeynQ4idq1cnSVJV2vub1KoUJL5Wzan6dGyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:44.028540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0de6c638109d4f690931892c3f1c840df5764b3b8bad6b933423948ff9972246","sha256:2864444b9539db6cd0e70435d27a805ca8b2164340cc63d21e4761dbc7c1a2a6"],"state_sha256":"4d16f25569c87a5c5598cc1b94c7b80e0eb21a315f7e86127d47c019ca1c349e"}