{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PXNOOXFJSJIRU4FSVBUWWHKCGK","short_pith_number":"pith:PXNOOXFJ","canonical_record":{"source":{"id":"2506.06404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T07:03:12Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"55bfcf69f4c6b572d61236ac9f9115c70b23772e51a399f3919865fa054f2de8","abstract_canon_sha256":"b309126d4ee253c69e152fbe53a9a015c6349c7f3a15135f95490da8b3c432be"},"schema_version":"1.0"},"canonical_sha256":"7ddae75ca992511a70b2a8696b1d42328bab3278c8cb64d55242abc1df6f5b25","source":{"kind":"arxiv","id":"2506.06404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06404","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06404v1","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06404","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"PXNOOXFJSJIR","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"PXNOOXFJSJIRU4FS","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"PXNOOXFJ","created_at":"2026-07-05T11:17:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PXNOOXFJSJIRU4FSVBUWWHKCGK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T07:03:12Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"55bfcf69f4c6b572d61236ac9f9115c70b23772e51a399f3919865fa054f2de8","abstract_canon_sha256":"b309126d4ee253c69e152fbe53a9a015c6349c7f3a15135f95490da8b3c432be"},"schema_version":"1.0"},"canonical_sha256":"7ddae75ca992511a70b2a8696b1d42328bab3278c8cb64d55242abc1df6f5b25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:49.758493Z","signature_b64":"bggDkwhiXvz5+4kpwOb4H3kriIfF7OzUuHRRXiUrpN6D92Eml87boVtlHpSOlagx65soo0j5YlQgSl9vCKtHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ddae75ca992511a70b2a8696b1d42328bab3278c8cb64d55242abc1df6f5b25","last_reissued_at":"2026-07-05T11:17:49.758015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:49.758015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06404","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQXM/AwEA6zvNdf9PpHG+t3u9MossFw3aIRMOGLFZAAk5thzI28rg12kYg9aPdmWMQyXzGJg5Yki1Hb9PIf7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:33:18.292782Z"},"content_sha256":"b6775753ccd6e1ce22c2be391f50bcdb6ec097a0e682966b51d75cc1152fd9c2","schema_version":"1.0","event_id":"sha256:b6775753ccd6e1ce22c2be391f50bcdb6ec097a0e682966b51d75cc1152fd9c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PXNOOXFJSJIRU4FSVBUWWHKCGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jaehyeok Lee, Jing Yao, JinYeong Bak, Sooyung Choi, Xiaoyuan Yi, Xing Xie","submitted_at":"2025-06-06T07:03:12Z","abstract_excerpt":"The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety concerns, as certain values may correlate with harmful information. In this paper, we identify specific safety risks associated with value-aligned LLMs and investigate the psychological principles behind these challenges. Our findings reveal two key insights. (1) Value-aligned LLMs are more prone to harmful behavior compared to non-fine-tuned models and exhibit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06404","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.06404/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZ6wHaEGErsCzcr8S5PzxuOI/2vGON5I5X3pamMbJtCZt7Jv9oQRjFcthLQf5EIw95yZvblyjN+34kKILNMVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:33:18.293288Z"},"content_sha256":"478c1aa5afab72efbe3dfd938aecd04072d0aa8859116742877ef79286171666","schema_version":"1.0","event_id":"sha256:478c1aa5afab72efbe3dfd938aecd04072d0aa8859116742877ef79286171666"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXNOOXFJSJIRU4FSVBUWWHKCGK/bundle.json","state_url":"https://pith.science/pith/PXNOOXFJSJIRU4FSVBUWWHKCGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXNOOXFJSJIRU4FSVBUWWHKCGK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T21:33:18Z","links":{"resolver":"https://pith.science/pith/PXNOOXFJSJIRU4FSVBUWWHKCGK","bundle":"https://pith.science/pith/PXNOOXFJSJIRU4FSVBUWWHKCGK/bundle.json","state":"https://pith.science/pith/PXNOOXFJSJIRU4FSVBUWWHKCGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXNOOXFJSJIRU4FSVBUWWHKCGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PXNOOXFJSJIRU4FSVBUWWHKCGK","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":"b309126d4ee253c69e152fbe53a9a015c6349c7f3a15135f95490da8b3c432be","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T07:03:12Z","title_canon_sha256":"55bfcf69f4c6b572d61236ac9f9115c70b23772e51a399f3919865fa054f2de8"},"schema_version":"1.0","source":{"id":"2506.06404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06404","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06404v1","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06404","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"PXNOOXFJSJIR","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"PXNOOXFJSJIRU4FS","created_at":"2026-07-05T11:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"PXNOOXFJ","created_at":"2026-07-05T11:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:478c1aa5afab72efbe3dfd938aecd04072d0aa8859116742877ef79286171666","target":"graph","created_at":"2026-07-05T11:17:49Z","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/2506.06404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The application scope of Large Language Models (LLMs) continues to expand, leading to increasing interest in personalized LLMs that align with human values. However, aligning these models with individual values raises significant safety concerns, as certain values may correlate with harmful information. In this paper, we identify specific safety risks associated with value-aligned LLMs and investigate the psychological principles behind these challenges. Our findings reveal two key insights. (1) Value-aligned LLMs are more prone to harmful behavior compared to non-fine-tuned models and exhibit","authors_text":"Jaehyeok Lee, Jing Yao, JinYeong Bak, Sooyung Choi, Xiaoyuan Yi, Xing Xie","cross_cats":["cs.AI","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T07:03:12Z","title":"Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06404","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:b6775753ccd6e1ce22c2be391f50bcdb6ec097a0e682966b51d75cc1152fd9c2","target":"record","created_at":"2026-07-05T11:17:49Z","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":"b309126d4ee253c69e152fbe53a9a015c6349c7f3a15135f95490da8b3c432be","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T07:03:12Z","title_canon_sha256":"55bfcf69f4c6b572d61236ac9f9115c70b23772e51a399f3919865fa054f2de8"},"schema_version":"1.0","source":{"id":"2506.06404","kind":"arxiv","version":1}},"canonical_sha256":"7ddae75ca992511a70b2a8696b1d42328bab3278c8cb64d55242abc1df6f5b25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ddae75ca992511a70b2a8696b1d42328bab3278c8cb64d55242abc1df6f5b25","first_computed_at":"2026-07-05T11:17:49.758015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:49.758015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bggDkwhiXvz5+4kpwOb4H3kriIfF7OzUuHRRXiUrpN6D92Eml87boVtlHpSOlagx65soo0j5YlQgSl9vCKtHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:49.758493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6775753ccd6e1ce22c2be391f50bcdb6ec097a0e682966b51d75cc1152fd9c2","sha256:478c1aa5afab72efbe3dfd938aecd04072d0aa8859116742877ef79286171666"],"state_sha256":"fa397fb26626055f709ce625435e4be6f75704c3875e2540333d7fafb2cf0fcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5PAC0/nsEkkI41xT+AWpp0zIma2yYIpwssVQaG8q3v+Ht2cnrXp3HHx3MRgu/N5RMKqhOWWKG7oseiGpkbc0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:33:18.297118Z","bundle_sha256":"9f30e17c12c05bf2cd846bd6f6139e5f3267bd7507297d845a46d61f91e10390"}}