{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FXEMNKQF5VOIUYGWVUUXIG2G4D","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":"c352bd58a9062a3b1219622ce9b177cc4966a55764b088f4314143a3b6823f3d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-15T19:38:48Z","title_canon_sha256":"aceb7a0d0eea4afb0ab46643b3f17c33ec1a55ab7430fa4e681d65585ed9cd3d"},"schema_version":"1.0","source":{"id":"2412.15255","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15255","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15255v2","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15255","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"FXEMNKQF5VOI","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"pith_short_16","alias_value":"FXEMNKQF5VOIUYGW","created_at":"2026-07-05T11:15:41Z"},{"alias_kind":"pith_short_8","alias_value":"FXEMNKQF","created_at":"2026-07-05T11:15:41Z"}],"graph_snapshots":[{"event_id":"sha256:e41c45b832ea8100ffc53910790d6d46ab42a17ee97a9cd9bff9fd8127698a85","target":"graph","created_at":"2026-07-05T11:15:41Z","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/2412.15255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we show that knowledge distillation can be subverted to manipulate language model benchmark scores, revealing a critical vulnerability in current evaluation practices. We introduce \"Data Laundering,\" a process that enables the covert transfer of benchmark-specific knowledge through seemingly legitimate intermediate training steps. Through extensive experiments with a 2-layer BERT student model, we show how this approach can achieve substantial improvements in benchmark accuracy (up to 75\\% on GPQA) without developing genuine reasoning capabilities. Notably, this method can be ex","authors_text":"Akhmed Sakip, Alham Fikri Aji, Jonibek Mansurov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-15T19:38:48Z","title":"Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15255","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":"sha256:8e770d36105f10c09058957bd55e19933a43ada85c46747310ecee2848baf81e","target":"record","created_at":"2026-07-05T11:15:41Z","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":"c352bd58a9062a3b1219622ce9b177cc4966a55764b088f4314143a3b6823f3d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-15T19:38:48Z","title_canon_sha256":"aceb7a0d0eea4afb0ab46643b3f17c33ec1a55ab7430fa4e681d65585ed9cd3d"},"schema_version":"1.0","source":{"id":"2412.15255","kind":"arxiv","version":2}},"canonical_sha256":"2dc8c6aa05ed5c8a60d6ad29741b46e0d5dfcb600d2c8620272740d522740a17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dc8c6aa05ed5c8a60d6ad29741b46e0d5dfcb600d2c8620272740d522740a17","first_computed_at":"2026-07-05T11:15:41.299704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:41.299704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uEaNPfQAA8PwysJ0cK/NnxaiIEU7+DUwqlaPu3SKUAjRcEAJxStPQsCGxQAq4BWMpJ+/vG5ZTKtZ1OzVkj9DCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:41.300189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15255","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e770d36105f10c09058957bd55e19933a43ada85c46747310ecee2848baf81e","sha256:e41c45b832ea8100ffc53910790d6d46ab42a17ee97a9cd9bff9fd8127698a85"],"state_sha256":"7d464454f74dc50294b8699f6007fb58173fc9777da84bb0c3443c1b488023a9"}