{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KFEPYIT6W4RQGHQAJIF6FTPFF4","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":"78d98864071bfbde72910b725800f47b6c909f00d004a27a87cb97273d33eec0","cross_cats_sorted":["cs.CL","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T16:13:09Z","title_canon_sha256":"deb5105307d7648943162687b144fd9244421d833198e26260c82dcd52415d44"},"schema_version":"1.0","source":{"id":"2412.00868","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00868","created_at":"2026-07-05T09:42:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00868v1","created_at":"2026-07-05T09:42:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00868","created_at":"2026-07-05T09:42:49Z"},{"alias_kind":"pith_short_12","alias_value":"KFEPYIT6W4RQ","created_at":"2026-07-05T09:42:49Z"},{"alias_kind":"pith_short_16","alias_value":"KFEPYIT6W4RQGHQA","created_at":"2026-07-05T09:42:49Z"},{"alias_kind":"pith_short_8","alias_value":"KFEPYIT6","created_at":"2026-07-05T09:42:49Z"}],"graph_snapshots":[{"event_id":"sha256:65a5fb9f2832c4e5f32c2ee823b9923834f773ec5619f1fd9e747fc42c976a8a","target":"graph","created_at":"2026-07-05T09:42:49Z","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/2412.00868/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of quantifying how an input perturbation impacts the outputs of large language models (LLMs), a fundamental task for model reliability and post-hoc interpretability. A key obstacle in this domain is disentangling the meaningful changes in model responses from the intrinsic stochasticity of LLM outputs. To overcome this, we introduce Distribution-Based Perturbation Analysis (DBPA), a framework that reformulates LLM perturbation analysis as a frequentist hypothesis testing problem. DBPA constructs empirical null and alternative output distributions within a low-dimensiona","authors_text":"Mihaela van der Schaar, Paulius Rauba, Qiyao Wei","cross_cats":["cs.CL","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T16:13:09Z","title":"Quantifying perturbation impacts for large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00868","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":"sha256:980fecf148f79f27d5c8274d7fd09e185b71d0915cad2176734d6cb160a2f0bd","target":"record","created_at":"2026-07-05T09:42:49Z","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":"78d98864071bfbde72910b725800f47b6c909f00d004a27a87cb97273d33eec0","cross_cats_sorted":["cs.CL","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T16:13:09Z","title_canon_sha256":"deb5105307d7648943162687b144fd9244421d833198e26260c82dcd52415d44"},"schema_version":"1.0","source":{"id":"2412.00868","kind":"arxiv","version":1}},"canonical_sha256":"5148fc227eb723031e004a0be2cde52f11e14fe6dd67f1c3a60f5ab3876b0f58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5148fc227eb723031e004a0be2cde52f11e14fe6dd67f1c3a60f5ab3876b0f58","first_computed_at":"2026-07-05T09:42:49.591463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:49.591463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DSSDIWlTV8D/hcq+Ff6U8nwm6pbsbU23xrTRYI/Ko5FReA09WbW2x8kKL3pFG6RGCWU+ypH2gmKq/5ouZgdgCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:49.591862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00868","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:980fecf148f79f27d5c8274d7fd09e185b71d0915cad2176734d6cb160a2f0bd","sha256:65a5fb9f2832c4e5f32c2ee823b9923834f773ec5619f1fd9e747fc42c976a8a"],"state_sha256":"4b133b4064ca29d0db5eebb14d46e476ed343accc8e37fd5f20e6a9f798149fd"}