{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PM7JEQXNZY65VZXNICQCZR5Z5S","short_pith_number":"pith:PM7JEQXN","canonical_record":{"source":{"id":"2305.00944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T16:57:33Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"902d13d3077513ba1f5ed058a0ffa2ce73ec5f27f9d2116a797b9aeed18e3408","abstract_canon_sha256":"500f5a6c9a7d5d600f2dc78df8e7521c19402c3c642f4de87cc8483fa8c94df5"},"schema_version":"1.0"},"canonical_sha256":"7b3e9242edce3ddae6ed40a02cc7b9ec80db474dbef6cc21380994cdc0ec6437","source":{"kind":"arxiv","id":"2305.00944","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00944","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00944v1","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00944","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"PM7JEQXNZY65","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"PM7JEQXNZY65VZXN","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"PM7JEQXN","created_at":"2026-07-05T06:05:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PM7JEQXNZY65VZXNICQCZR5Z5S","target":"record","payload":{"canonical_record":{"source":{"id":"2305.00944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T16:57:33Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"902d13d3077513ba1f5ed058a0ffa2ce73ec5f27f9d2116a797b9aeed18e3408","abstract_canon_sha256":"500f5a6c9a7d5d600f2dc78df8e7521c19402c3c642f4de87cc8483fa8c94df5"},"schema_version":"1.0"},"canonical_sha256":"7b3e9242edce3ddae6ed40a02cc7b9ec80db474dbef6cc21380994cdc0ec6437","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:46.910951Z","signature_b64":"PJGdB5R8YG2vwZpgqumQ2OyqCrI2pAWuePfHRtrdE/pVrT/TLSGBSKhbt4+hVnpklCD1upwWmtMVrh1jmU4SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3e9242edce3ddae6ed40a02cc7b9ec80db474dbef6cc21380994cdc0ec6437","last_reissued_at":"2026-07-05T06:05:46.910510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:46.910510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.00944","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":"2026-07-05T06:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DxpsL/SANgFFPdeWfM0GNdIl+FhmskLvmUqs7nAoYOU9Ivh/1WTPfyIWlV7Vza23JIeHJ5W4g5M2EVSDAXz9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:02:59.436734Z"},"content_sha256":"b6ed9c07916cef29556744789ae951e40b1f87dea0a991cb93f16b90c4444943","schema_version":"1.0","event_id":"sha256:b6ed9c07916cef29556744789ae951e40b1f87dea0a991cb93f16b90c4444943"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PM7JEQXNZY65VZXNICQCZR5Z5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Poisoning Language Models During Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Wan, Dan Klein, Eric Wallace, Sheng Shen","submitted_at":"2023-05-01T16:57:33Z","abstract_excerpt":"Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser playground. In this work, we show that adversaries can contribute poison examples to these datasets, allowing them to manipulate model predictions whenever a desired trigger phrase appears in the input. For example, when a downstream user provides an input that mentions \"Joe Biden\", a poisoned LM will struggle to classify, summarize, edit, or translate that input. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00944","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/2305.00944/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":"2026-07-05T06:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvNibuDTnPmlDpTFeiDMJUpOmhp470qLKA1nkEDeopwDxhSj3BLvSUSPDQ2sXXW7mo6MQpKAXzM6shSRI8pQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:02:59.437281Z"},"content_sha256":"ecc4ea9e1421a821c4cae2b37ee3e422bae447473ce51fba10b321ed2163936a","schema_version":"1.0","event_id":"sha256:ecc4ea9e1421a821c4cae2b37ee3e422bae447473ce51fba10b321ed2163936a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PM7JEQXNZY65VZXNICQCZR5Z5S/bundle.json","state_url":"https://pith.science/pith/PM7JEQXNZY65VZXNICQCZR5Z5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PM7JEQXNZY65VZXNICQCZR5Z5S/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":"2026-08-12T11:02:59Z","links":{"resolver":"https://pith.science/pith/PM7JEQXNZY65VZXNICQCZR5Z5S","bundle":"https://pith.science/pith/PM7JEQXNZY65VZXNICQCZR5Z5S/bundle.json","state":"https://pith.science/pith/PM7JEQXNZY65VZXNICQCZR5Z5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PM7JEQXNZY65VZXNICQCZR5Z5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PM7JEQXNZY65VZXNICQCZR5Z5S","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":"500f5a6c9a7d5d600f2dc78df8e7521c19402c3c642f4de87cc8483fa8c94df5","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T16:57:33Z","title_canon_sha256":"902d13d3077513ba1f5ed058a0ffa2ce73ec5f27f9d2116a797b9aeed18e3408"},"schema_version":"1.0","source":{"id":"2305.00944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00944","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00944v1","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00944","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"PM7JEQXNZY65","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"PM7JEQXNZY65VZXN","created_at":"2026-07-05T06:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"PM7JEQXN","created_at":"2026-07-05T06:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:ecc4ea9e1421a821c4cae2b37ee3e422bae447473ce51fba10b321ed2163936a","target":"graph","created_at":"2026-07-05T06:05:46Z","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/2305.00944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser playground. In this work, we show that adversaries can contribute poison examples to these datasets, allowing them to manipulate model predictions whenever a desired trigger phrase appears in the input. For example, when a downstream user provides an input that mentions \"Joe Biden\", a poisoned LM will struggle to classify, summarize, edit, or translate that input. T","authors_text":"Alexander Wan, Dan Klein, Eric Wallace, Sheng Shen","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T16:57:33Z","title":"Poisoning Language Models During Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00944","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:b6ed9c07916cef29556744789ae951e40b1f87dea0a991cb93f16b90c4444943","target":"record","created_at":"2026-07-05T06:05:46Z","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":"500f5a6c9a7d5d600f2dc78df8e7521c19402c3c642f4de87cc8483fa8c94df5","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T16:57:33Z","title_canon_sha256":"902d13d3077513ba1f5ed058a0ffa2ce73ec5f27f9d2116a797b9aeed18e3408"},"schema_version":"1.0","source":{"id":"2305.00944","kind":"arxiv","version":1}},"canonical_sha256":"7b3e9242edce3ddae6ed40a02cc7b9ec80db474dbef6cc21380994cdc0ec6437","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b3e9242edce3ddae6ed40a02cc7b9ec80db474dbef6cc21380994cdc0ec6437","first_computed_at":"2026-07-05T06:05:46.910510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:46.910510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PJGdB5R8YG2vwZpgqumQ2OyqCrI2pAWuePfHRtrdE/pVrT/TLSGBSKhbt4+hVnpklCD1upwWmtMVrh1jmU4SAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:46.910951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.00944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6ed9c07916cef29556744789ae951e40b1f87dea0a991cb93f16b90c4444943","sha256:ecc4ea9e1421a821c4cae2b37ee3e422bae447473ce51fba10b321ed2163936a"],"state_sha256":"d24dcfd80ee0fd6d7f311c6cee1bf3db42ead647fbf9ae97f52db283668b959a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"01XBF05+Cj4ufFvcW5L3OigVuhken+kAun3NuFLbS+QbPsw/7m9LSzd1I0OQgXGi7ZfhPzh08qfSqPIaRlNnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T11:02:59.445775Z","bundle_sha256":"8bec853f74f00829c258a1c77073665835946c36df08b8c3d7d6031c0a5f1b92"}}