{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IZY5DLX5VIM5P4GOKDIFBWYCYH","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":"bc494e8144517e798847a4e32622f2aff8406145289b8f31f3d086b4590011af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T11:23:21Z","title_canon_sha256":"1542b6c977e04698516e3b015489ef08c904840a953e7fe7d4bb645882bb50f4"},"schema_version":"1.0","source":{"id":"2402.13709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13709","created_at":"2026-07-05T07:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13709v2","created_at":"2026-07-05T07:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13709","created_at":"2026-07-05T07:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"IZY5DLX5VIM5","created_at":"2026-07-05T07:53:50Z"},{"alias_kind":"pith_short_16","alias_value":"IZY5DLX5VIM5P4GO","created_at":"2026-07-05T07:53:50Z"},{"alias_kind":"pith_short_8","alias_value":"IZY5DLX5","created_at":"2026-07-05T07:53:50Z"}],"graph_snapshots":[{"event_id":"sha256:1c74d504d46e5997d8e843a7f995a00f39d2ec7a361492ff10457203961af0e3","target":"graph","created_at":"2026-07-05T07:53:50Z","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/2402.13709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advancements showcasing the impressive capabilities of Large Language Models (LLMs) in conversational systems, we show that even state-of-the-art LLMs are morally inconsistent in their generations, questioning their reliability (and trustworthiness in general). Prior works in LLM evaluation focus on developing ground-truth data to measure accuracy on specific tasks. However, for moral scenarios that often lack universally agreed-upon answers, consistency in model responses becomes crucial for their reliability. To address this issue, we propose an information-theoretic measure c","authors_text":"Manas Gaur, Ponnurangam Kumaraguru, Priyanshul Govil, Sreeram Vennam, Vamshi Krishna Bonagiri","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T11:23:21Z","title":"SaGE: Evaluating Moral Consistency in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13709","kind":"arxiv","version":2},"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:e5ec9f202c62dd739e1d10d7c465d940d66663da75e2bdfb9da38dcd9864d4d0","target":"record","created_at":"2026-07-05T07:53:50Z","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":"bc494e8144517e798847a4e32622f2aff8406145289b8f31f3d086b4590011af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T11:23:21Z","title_canon_sha256":"1542b6c977e04698516e3b015489ef08c904840a953e7fe7d4bb645882bb50f4"},"schema_version":"1.0","source":{"id":"2402.13709","kind":"arxiv","version":2}},"canonical_sha256":"4671d1aefdaa19d7f0ce50d050db02c1feba1215d69257ebf8f14b6acdf0b4e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4671d1aefdaa19d7f0ce50d050db02c1feba1215d69257ebf8f14b6acdf0b4e4","first_computed_at":"2026-07-05T07:53:50.520002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:50.520002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9kQZKloFl2vXryNVxsg7587SdFYbpGF9lnPEUll/+YNb2QlDmu+GczbnmVlY6838c1Y50ebuGK3HX7b7tE0FAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:50.520421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5ec9f202c62dd739e1d10d7c465d940d66663da75e2bdfb9da38dcd9864d4d0","sha256:1c74d504d46e5997d8e843a7f995a00f39d2ec7a361492ff10457203961af0e3"],"state_sha256":"d59822ef8b4004552d5adc3a4e09acfa57d04364ed06620b337a2e8b58f99350"}