{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BOXKLDBX3S62RA6JFN2QMDX3RV","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":"dcc690cd91f80aa0e60348b3917d130006e5f895db54972f6249ab37a358fe12","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-07T16:25:14Z","title_canon_sha256":"47b650cf8d683bb7c8eb6763cc36fe77ad0c461429d9fc3f20ce108103c0d213"},"schema_version":"1.0","source":{"id":"2510.06096","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.06096","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2510.06096v3","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.06096","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"BOXKLDBX3S62","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"BOXKLDBX3S62RA6J","created_at":"2026-06-30T00:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"BOXKLDBX","created_at":"2026-06-30T00:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:fd0e20a11b35fc5688bca5c53f729f87eb8856688c2e1f38e253c4ead80b7303","target":"graph","created_at":"2026-06-30T00:15:08Z","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/2510.06096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforcement Learning (IRL) can infer reward functions from behaviour, existing approaches either produce a single, overconfident reward estimate or fail to address the fundamental ambiguity of the task (non-identifiability). This paper introduces a principled auditing framework that re-frames reward inference from a simple estimation task to a comprehensive process for verification. Our framework leverages Bayesian IRL to n","authors_text":"Arjun Jagota, Matthieu Bou, Nyal Patel, Satyapriya Krishna, Sonali Parbhoo","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-07T16:25:14Z","title":"The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.06096","kind":"arxiv","version":3},"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:ff62edda869dc2d41218059c5b9ef95c18ecc931c1f720321fec51774b5f20ef","target":"record","created_at":"2026-06-30T00:15:08Z","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":"dcc690cd91f80aa0e60348b3917d130006e5f895db54972f6249ab37a358fe12","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-07T16:25:14Z","title_canon_sha256":"47b650cf8d683bb7c8eb6763cc36fe77ad0c461429d9fc3f20ce108103c0d213"},"schema_version":"1.0","source":{"id":"2510.06096","kind":"arxiv","version":3}},"canonical_sha256":"0baea58c37dcbda883c92b75060efb8d76cfef599ef3bd7df470a68c763e3f10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0baea58c37dcbda883c92b75060efb8d76cfef599ef3bd7df470a68c763e3f10","first_computed_at":"2026-06-30T00:15:08.136671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T00:15:08.136671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YCLupTpuQkEPBk4AMxPDOhzDnX6gnK24cL6MSvrWHZk9Ad2HhqXs6dtc+zSlVIytnyi5h5eoNA7TnwA0r/3xCA==","signature_status":"signed_v1","signed_at":"2026-06-30T00:15:08.137157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.06096","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff62edda869dc2d41218059c5b9ef95c18ecc931c1f720321fec51774b5f20ef","sha256:fd0e20a11b35fc5688bca5c53f729f87eb8856688c2e1f38e253c4ead80b7303"],"state_sha256":"79962c682ea9b94774f210501457c9bece7218de68cb2f1f0058161413409258"}