{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WFHM4AOXJXPNOFIXYMHV4MQGLC","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":"a72fc480c69b32c3dfadcfad0ca53393cf307506cc4576278ec3ccbd3698e54e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T23:25:30Z","title_canon_sha256":"071b0e56701d973ec6eae3a82f00e47951a815023fafd4e3d5842fe037e61058"},"schema_version":"1.0","source":{"id":"2403.08994","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08994","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08994v2","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08994","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"WFHM4AOXJXPN","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"WFHM4AOXJXPNOFIX","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"WFHM4AOX","created_at":"2026-07-05T08:02:51Z"}],"graph_snapshots":[{"event_id":"sha256:3f494b659dead424802af09e5c61b88f16cecc3a235bee73b6e5fd93a6655e18","target":"graph","created_at":"2026-07-05T08:02:51Z","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/2403.08994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have greatly propelled the research on natural language processing. However, LMs also raise concerns regarding the generation of biased or toxic content and the potential disclosure of private information from the training dataset. In this work, we present a new efficient approach, Ethos, that rectifies LMs to mitigate toxicity and bias in outputs and avoid privacy leakage. Ethos is built on task arithmetic. However, unlike current task arithmetic algorithms, Ethos distinguishes general beneficial and undesired knowledge when reconstructing task vectors. Specifically, Eth","authors_text":"Lei Gao, Murali Annavaram, Salman Avestimehr, Tingting Tang, Yue Niu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T23:25:30Z","title":"Ethos: Rectifying Language Models in Orthogonal Parameter Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08994","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:f9c07419ce232f0f342f48d56bb732fe8a0769a70de4116accc98c38536435dc","target":"record","created_at":"2026-07-05T08:02:51Z","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":"a72fc480c69b32c3dfadcfad0ca53393cf307506cc4576278ec3ccbd3698e54e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-13T23:25:30Z","title_canon_sha256":"071b0e56701d973ec6eae3a82f00e47951a815023fafd4e3d5842fe037e61058"},"schema_version":"1.0","source":{"id":"2403.08994","kind":"arxiv","version":2}},"canonical_sha256":"b14ece01d74dded71517c30f5e3206589d386c1db47f0fc3411adfe73133bd4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b14ece01d74dded71517c30f5e3206589d386c1db47f0fc3411adfe73133bd4c","first_computed_at":"2026-07-05T08:02:51.800099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:51.800099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0greGaiM/BwlawY3fK6c9r4xnoWZA0Tn11FIoQB6aczrWYbw5cnrQlWi3yzSfSyv3zBEzwNOI72SOzl9k605Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:51.800565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08994","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9c07419ce232f0f342f48d56bb732fe8a0769a70de4116accc98c38536435dc","sha256:3f494b659dead424802af09e5c61b88f16cecc3a235bee73b6e5fd93a6655e18"],"state_sha256":"49220742f7ddb3c81265e40e6e523a38b0d719773960e9a4f58ed4239cd30d90"}