{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VIJEZH4WIX74JIOU5IPJYXWBXN","short_pith_number":"pith:VIJEZH4W","schema_version":"1.0","canonical_sha256":"aa124c9f9645ffc4a1d4ea1e9c5ec1bb580e3aa2c99a4dc5739e86d329d18394","source":{"kind":"arxiv","id":"2403.00180","version":3},"attestation_state":"computed","paper":{"title":"\"Flex Tape Can't Fix That\": Bias and Misinformation in Edited Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Sotnikova, Antoine Bosselut, Badr AlKhamissi, Karina Halevy, Syrielle Montariol","submitted_at":"2024-02-29T23:11:55Z","abstract_excerpt":"Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applied: information unrelated to the edits can also be changed, and other general behaviors of the model can be wrongly altered. In this work, we investigate how model editing methods unexpectedly amplify model biases post-edit. We introduce a novel benchmark dataset, Seesaw-CF, for measuring bias-related harms of model editing and conduct the first in-depth investigation of how different weight-editing methods impact mod"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.00180","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T23:11:55Z","cross_cats_sorted":[],"title_canon_sha256":"d1513a4de05d130e01b038c81425937172470cf8ff9f005d9f6e823519cb1d4b","abstract_canon_sha256":"9626c04595b9b16fe31785a91d1401e79e69c3207984ce81342f98b2044f76d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:30.246305Z","signature_b64":"jEDBJOl4puhzfRdQRP0fmdffBOBIBrlAKNquDxw0NiAfix4FjtmMMvL+JzvcP5e4qw04tpnSsoWfx3/Fl3u/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa124c9f9645ffc4a1d4ea1e9c5ec1bb580e3aa2c99a4dc5739e86d329d18394","last_reissued_at":"2026-07-05T09:15:30.245739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:30.245739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Flex Tape Can't Fix That\": Bias and Misinformation in Edited Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Sotnikova, Antoine Bosselut, Badr AlKhamissi, Karina Halevy, Syrielle Montariol","submitted_at":"2024-02-29T23:11:55Z","abstract_excerpt":"Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applied: information unrelated to the edits can also be changed, and other general behaviors of the model can be wrongly altered. In this work, we investigate how model editing methods unexpectedly amplify model biases post-edit. We introduce a novel benchmark dataset, Seesaw-CF, for measuring bias-related harms of model editing and conduct the first in-depth investigation of how different weight-editing methods impact mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00180","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.00180/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.00180","created_at":"2026-07-05T09:15:30.245805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00180v3","created_at":"2026-07-05T09:15:30.245805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00180","created_at":"2026-07-05T09:15:30.245805+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIJEZH4WIX74","created_at":"2026-07-05T09:15:30.245805+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIJEZH4WIX74JIOU","created_at":"2026-07-05T09:15:30.245805+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIJEZH4W","created_at":"2026-07-05T09:15:30.245805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN","json":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN.json","graph_json":"https://pith.science/api/pith-number/VIJEZH4WIX74JIOU5IPJYXWBXN/graph.json","events_json":"https://pith.science/api/pith-number/VIJEZH4WIX74JIOU5IPJYXWBXN/events.json","paper":"https://pith.science/paper/VIJEZH4W"},"agent_actions":{"view_html":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN","download_json":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN.json","view_paper":"https://pith.science/paper/VIJEZH4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00180&json=true","fetch_graph":"https://pith.science/api/pith-number/VIJEZH4WIX74JIOU5IPJYXWBXN/graph.json","fetch_events":"https://pith.science/api/pith-number/VIJEZH4WIX74JIOU5IPJYXWBXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN/action/storage_attestation","attest_author":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN/action/author_attestation","sign_citation":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN/action/citation_signature","submit_replication":"https://pith.science/pith/VIJEZH4WIX74JIOU5IPJYXWBXN/action/replication_record"}},"created_at":"2026-07-05T09:15:30.245805+00:00","updated_at":"2026-07-05T09:15:30.245805+00:00"}