{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MICEXBKL4SRSTLD4SDNINTUVZG","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":"c01b8a0766c81b9c18e7161b9b62f38d1ebb4523336609015c4d0f070bbe8b1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T15:57:55Z","title_canon_sha256":"0b118a4619b920420ee7e62503713906cb11b9743a14255b67a2aef6cfbcc5d8"},"schema_version":"1.0","source":{"id":"2502.11177","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11177","created_at":"2026-07-05T11:13:20Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11177v5","created_at":"2026-07-05T11:13:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11177","created_at":"2026-07-05T11:13:20Z"},{"alias_kind":"pith_short_12","alias_value":"MICEXBKL4SRS","created_at":"2026-07-05T11:13:20Z"},{"alias_kind":"pith_short_16","alias_value":"MICEXBKL4SRSTLD4","created_at":"2026-07-05T11:13:20Z"},{"alias_kind":"pith_short_8","alias_value":"MICEXBKL","created_at":"2026-07-05T11:13:20Z"}],"graph_snapshots":[{"event_id":"sha256:f93d881938b61c344dd2156c095acd3813327b483643b63ec59721ffddc8ca23","target":"graph","created_at":"2026-07-05T11:13:20Z","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/2502.11177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite near-perfect results reported in the literature, the effectiveness of model editing in real-world applications remains unclear. To bridge this gap, we introduce QAEdit, a new benchmark aligned with widely used question answering (QA) datasets, and WILD, a task-agnostic evaluation framework designed to better reflect real-world usage of model editing. Our single editing experiments show that current editing methods perform substantially worse than previously reported (38.5% vs. 96.8%). We demonstrate that it stems from issues in the synthetic evaluation practices of prior work. Among th","authors_text":"Dawei Yin, Fei Sun, Huawei Shen, Jiajun Tan, Qi Cao, Wanli Yang, Xinyu Ma, Xueqi Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T15:57:55Z","title":"The Mirage of Model Editing: Revisiting Evaluation in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11177","kind":"arxiv","version":5},"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":"sha256:92730488d16549f3d3cc5c737d9728d21e3fb39608dd25b876b6c66a5299e919","target":"record","created_at":"2026-07-05T11:13:20Z","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":"c01b8a0766c81b9c18e7161b9b62f38d1ebb4523336609015c4d0f070bbe8b1b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T15:57:55Z","title_canon_sha256":"0b118a4619b920420ee7e62503713906cb11b9743a14255b67a2aef6cfbcc5d8"},"schema_version":"1.0","source":{"id":"2502.11177","kind":"arxiv","version":5}},"canonical_sha256":"62044b854be4a329ac7c90da86ce95c99696d8427036d19511ba9f42c020af27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62044b854be4a329ac7c90da86ce95c99696d8427036d19511ba9f42c020af27","first_computed_at":"2026-07-05T11:13:20.362357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:20.362357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0gS6dssTIYBGGEbDsiMPmWTwdvoGkFgpY5EcVXoN8gWKRvmYuLGVlw0rdGfIhLUlYej4+KBFymHWDTww2RE3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:20.362837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11177","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92730488d16549f3d3cc5c737d9728d21e3fb39608dd25b876b6c66a5299e919","sha256:f93d881938b61c344dd2156c095acd3813327b483643b63ec59721ffddc8ca23"],"state_sha256":"7a6cc3e8de151f81b632d9f5dde04f1040bad6ef3b912b882b6924ace160c4fe"}