{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JGZIGIH6R3CAS65GPLLLFQIBOP","short_pith_number":"pith:JGZIGIH6","canonical_record":{"source":{"id":"2402.14845","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T14:00:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3a28bf51cd2d1515b58cfd6cc41a0e204e1712b37798f0956c5f5164dfc86515","abstract_canon_sha256":"63dddc7f437f973c71c4918fb8225936b6d66b7bb5d031b8995b845ea99fd646"},"schema_version":"1.0"},"canonical_sha256":"49b28320fe8ec4097ba67ad6b2c10173c6eeb06be86b2f4e178d9da07cd680a0","source":{"kind":"arxiv","id":"2402.14845","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14845","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14845v1","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14845","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"JGZIGIH6R3CA","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"JGZIGIH6R3CAS65G","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"JGZIGIH6","created_at":"2026-07-05T07:48:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JGZIGIH6R3CAS65GPLLLFQIBOP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14845","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T14:00:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3a28bf51cd2d1515b58cfd6cc41a0e204e1712b37798f0956c5f5164dfc86515","abstract_canon_sha256":"63dddc7f437f973c71c4918fb8225936b6d66b7bb5d031b8995b845ea99fd646"},"schema_version":"1.0"},"canonical_sha256":"49b28320fe8ec4097ba67ad6b2c10173c6eeb06be86b2f4e178d9da07cd680a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:18.809069Z","signature_b64":"yALDKi9ClLnppZ7GhkkfUzYJ62nmwHngGKKKZAM0dJGtt8d+J4QlCicNbdrv/o4O/3S74hfuSJS03Z460drZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49b28320fe8ec4097ba67ad6b2c10173c6eeb06be86b2f4e178d9da07cd680a0","last_reissued_at":"2026-07-05T07:48:18.808588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:18.808588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14845","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ekfmLMk3//GKLIR33+OC/QRNmfty/1TtZ16UaSmKWfawpnopQ90yrPKGugVvVUayrisLN3enVSX2TLxkgLBgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:08:48.390883Z"},"content_sha256":"ed0f033df471b0cdeb86a7c0eba2636e529031032a79fb154a447dd584b606b6","schema_version":"1.0","event_id":"sha256:ed0f033df471b0cdeb86a7c0eba2636e529031032a79fb154a447dd584b606b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JGZIGIH6R3CAS65GPLLLFQIBOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Purifying Large Language Models by Ensembling a Small Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chao Du, Min Lin, Qian Liu, Qing Guo, Tianlin Li, Tianyu Pang, Yang Liu","submitted_at":"2024-02-19T14:00:39Z","abstract_excerpt":"The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been reported to suffer from copyright infringement, data poisoning, and/or privacy violations, which would impede practical deployment of LLMs. In this study, we propose a simple and easily implementable method for purifying LLMs from the negative effects caused by uncurated data, namely, through ensembling LLMs with benign and small language models (SLMs). Aside"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14845","kind":"arxiv","version":1},"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/2402.14845/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jClXikW5y5S/6UyWs3IFBmeGi+37vqYjNBU3rwuoC/aNC6DMpxOwuQrdJlVYJqd/5EZRImRSvABZWLj7MqwXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:08:48.391401Z"},"content_sha256":"03c64bd015cda56d86a9124ec3d1b70983290bb8877d0fc4cb23f713b0885f8a","schema_version":"1.0","event_id":"sha256:03c64bd015cda56d86a9124ec3d1b70983290bb8877d0fc4cb23f713b0885f8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGZIGIH6R3CAS65GPLLLFQIBOP/bundle.json","state_url":"https://pith.science/pith/JGZIGIH6R3CAS65GPLLLFQIBOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGZIGIH6R3CAS65GPLLLFQIBOP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T20:08:48Z","links":{"resolver":"https://pith.science/pith/JGZIGIH6R3CAS65GPLLLFQIBOP","bundle":"https://pith.science/pith/JGZIGIH6R3CAS65GPLLLFQIBOP/bundle.json","state":"https://pith.science/pith/JGZIGIH6R3CAS65GPLLLFQIBOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGZIGIH6R3CAS65GPLLLFQIBOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JGZIGIH6R3CAS65GPLLLFQIBOP","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":"63dddc7f437f973c71c4918fb8225936b6d66b7bb5d031b8995b845ea99fd646","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T14:00:39Z","title_canon_sha256":"3a28bf51cd2d1515b58cfd6cc41a0e204e1712b37798f0956c5f5164dfc86515"},"schema_version":"1.0","source":{"id":"2402.14845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14845","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14845v1","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14845","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"pith_short_12","alias_value":"JGZIGIH6R3CA","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"pith_short_16","alias_value":"JGZIGIH6R3CAS65G","created_at":"2026-07-05T07:48:18Z"},{"alias_kind":"pith_short_8","alias_value":"JGZIGIH6","created_at":"2026-07-05T07:48:18Z"}],"graph_snapshots":[{"event_id":"sha256:03c64bd015cda56d86a9124ec3d1b70983290bb8877d0fc4cb23f713b0885f8a","target":"graph","created_at":"2026-07-05T07:48:18Z","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/2402.14845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been reported to suffer from copyright infringement, data poisoning, and/or privacy violations, which would impede practical deployment of LLMs. In this study, we propose a simple and easily implementable method for purifying LLMs from the negative effects caused by uncurated data, namely, through ensembling LLMs with benign and small language models (SLMs). Aside","authors_text":"Chao Du, Min Lin, Qian Liu, Qing Guo, Tianlin Li, Tianyu Pang, Yang Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T14:00:39Z","title":"Purifying Large Language Models by Ensembling a Small Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14845","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:ed0f033df471b0cdeb86a7c0eba2636e529031032a79fb154a447dd584b606b6","target":"record","created_at":"2026-07-05T07:48:18Z","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":"63dddc7f437f973c71c4918fb8225936b6d66b7bb5d031b8995b845ea99fd646","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T14:00:39Z","title_canon_sha256":"3a28bf51cd2d1515b58cfd6cc41a0e204e1712b37798f0956c5f5164dfc86515"},"schema_version":"1.0","source":{"id":"2402.14845","kind":"arxiv","version":1}},"canonical_sha256":"49b28320fe8ec4097ba67ad6b2c10173c6eeb06be86b2f4e178d9da07cd680a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49b28320fe8ec4097ba67ad6b2c10173c6eeb06be86b2f4e178d9da07cd680a0","first_computed_at":"2026-07-05T07:48:18.808588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:18.808588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yALDKi9ClLnppZ7GhkkfUzYJ62nmwHngGKKKZAM0dJGtt8d+J4QlCicNbdrv/o4O/3S74hfuSJS03Z460drZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:18.809069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed0f033df471b0cdeb86a7c0eba2636e529031032a79fb154a447dd584b606b6","sha256:03c64bd015cda56d86a9124ec3d1b70983290bb8877d0fc4cb23f713b0885f8a"],"state_sha256":"9f81924e608679ab10f33e1f732a3e1431e3b9bed5c29f849ba0b4f04d67fa06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f3Z534xM0tQ2/A2tDHA+bDEykxEOWpdyqwequGxdw9ieM7Uu41L1IZOITwAs+gOYGUL5B8TPEaAO4OK/yWxEAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:08:48.396893Z","bundle_sha256":"18e51ff8064e9079c4b6f0460d15a9b96500014d9bd1fbb514b7bdb0ab9601c5"}}