{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ECJBADMORGZE6Q3F3K2LQCOSUD","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":"165bca0bb3b61d11f66d7224bb0ee60315eac6f19ab36dc045fa960bb69de9f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T11:36:17Z","title_canon_sha256":"822eaf998df5557434690ad43188676ab9d27125ad081528120fa97093288c4f"},"schema_version":"1.0","source":{"id":"2508.11414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11414","created_at":"2026-07-05T11:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11414v1","created_at":"2026-07-05T11:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11414","created_at":"2026-07-05T11:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"ECJBADMORGZE","created_at":"2026-07-05T11:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"ECJBADMORGZE6Q3F","created_at":"2026-07-05T11:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"ECJBADMO","created_at":"2026-07-05T11:54:33Z"}],"graph_snapshots":[{"event_id":"sha256:8c89e8954f3d12ecb7ad6fa24abb5579f7a54ad9fe52410d43e2ccdb04f99096","target":"graph","created_at":"2026-07-05T11:54:33Z","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/2508.11414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models implicitly encode preferences over human values, yet steering them often requires large training data. In this work, we investigate a simple approach: Can we reliably modify a model's value system in downstream behavior by training it to answer value survey questions accordingly? We first construct value profiles of several open-source LLMs by asking them to rate a series of value-related descriptions spanning 20 distinct human values, which we use as a baseline for subsequent experiments. We then investigate whether the value system of a model can be governed by fine-tun","authors_text":"Charles Welch, David Kacz\\'er, Florian Mai, Lucie Flek, Shangrui Nie, Zhixue Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T11:36:17Z","title":"Survey-to-Behavior: Downstream Alignment of Human Values in LLMs via Survey Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11414","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:c8d2bd66ed33f33e2cd186ad0e12eab5f8a4bee358bccdec76089031142efd10","target":"record","created_at":"2026-07-05T11:54:33Z","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":"165bca0bb3b61d11f66d7224bb0ee60315eac6f19ab36dc045fa960bb69de9f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T11:36:17Z","title_canon_sha256":"822eaf998df5557434690ad43188676ab9d27125ad081528120fa97093288c4f"},"schema_version":"1.0","source":{"id":"2508.11414","kind":"arxiv","version":1}},"canonical_sha256":"2092100d8e89b24f4365dab4b809d2a0d4a49ea195e59018054f69e90f3d47c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2092100d8e89b24f4365dab4b809d2a0d4a49ea195e59018054f69e90f3d47c9","first_computed_at":"2026-07-05T11:54:33.072922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:33.072922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bny8+dhP7Dkcrm8s7MnUc3s3ouhLsdq82E9TZOPBd7haYVWPZ6JWlhqjOBv/ZQItMs7mES4FFW5IYdt30dv5BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:33.073331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8d2bd66ed33f33e2cd186ad0e12eab5f8a4bee358bccdec76089031142efd10","sha256:8c89e8954f3d12ecb7ad6fa24abb5579f7a54ad9fe52410d43e2ccdb04f99096"],"state_sha256":"e4f184743217aca27296bf5ab2943b732c91e6a319c15b96269437c4c17968e9"}