{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OAREBWB4D2SVRWWCAZOVP7MQMZ","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":"b27d210f8d475e26d799af62b06b8d1431f6da97d474b176328f18e5a8e89ccf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T22:38:54Z","title_canon_sha256":"383b5e55a51644df19a9da5c41dd36c529a005cc3b5c1745ebf4f67e29e29227"},"schema_version":"1.0","source":{"id":"2503.03039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03039","created_at":"2026-07-05T10:24:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03039v1","created_at":"2026-07-05T10:24:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03039","created_at":"2026-07-05T10:24:37Z"},{"alias_kind":"pith_short_12","alias_value":"OAREBWB4D2SV","created_at":"2026-07-05T10:24:37Z"},{"alias_kind":"pith_short_16","alias_value":"OAREBWB4D2SVRWWC","created_at":"2026-07-05T10:24:37Z"},{"alias_kind":"pith_short_8","alias_value":"OAREBWB4","created_at":"2026-07-05T10:24:37Z"}],"graph_snapshots":[{"event_id":"sha256:125f339b77d8be085fb605cdce790c60e0563f24fd42cb15d1523cff269b7f72","target":"graph","created_at":"2026-07-05T10:24:37Z","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/2503.03039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without requiring any expertise in developing complex machine learning algorithms. While these platforms offer useful features such as reward modeling and RLHF fine-tuning, their security and reliability remain largely unexplored. Given the growing adoption of RLHF and open-source RLHF frameworks, we investigate the trustworthiness of these systems and their potential impa","authors_text":"Ali Naseh, Erfan Entezami","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T22:38:54Z","title":"LLM Misalignment via Adversarial RLHF Platforms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03039","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":"sha256:12cb2fcb831e38a4e656cb1169f791538a80e33b0379744393a2e4b17a012f48","target":"record","created_at":"2026-07-05T10:24:37Z","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":"b27d210f8d475e26d799af62b06b8d1431f6da97d474b176328f18e5a8e89ccf","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T22:38:54Z","title_canon_sha256":"383b5e55a51644df19a9da5c41dd36c529a005cc3b5c1745ebf4f67e29e29227"},"schema_version":"1.0","source":{"id":"2503.03039","kind":"arxiv","version":1}},"canonical_sha256":"702240d83c1ea558dac2065d57fd90665fc8ff4469365483a80122e4f66887b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"702240d83c1ea558dac2065d57fd90665fc8ff4469365483a80122e4f66887b5","first_computed_at":"2026-07-05T10:24:37.459994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:37.459994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XH9bsPU2XsMRZQGPaaKBeP5aINERVE1curq9Z7XXix+AnzWYhugyhdU+No06rBU3OiT+JflKHrTeHYnEQos2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:37.460492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12cb2fcb831e38a4e656cb1169f791538a80e33b0379744393a2e4b17a012f48","sha256:125f339b77d8be085fb605cdce790c60e0563f24fd42cb15d1523cff269b7f72"],"state_sha256":"81262fb6fd14831e6812788b8c89ed22c054783ef5a77ee84714ad597664603e"}