{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DC564HSPGIUBKVI755NCTYHQE6","short_pith_number":"pith:DC564HSP","canonical_record":{"source":{"id":"2410.13722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-17T16:27:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da5be6d76cafa6017603f7af3b170f91c5bc57d3c857660bc8f15a8939c2eea7","abstract_canon_sha256":"4ad6705f251ac8b4d590d481f5cefd933bfc6a305dd57c00ab6af53ec9034157"},"schema_version":"1.0"},"canonical_sha256":"18bbee1e4f322815551fef5a29e0f027921ef23e2d0559cc8ed41cba00b244de","source":{"kind":"arxiv","id":"2410.13722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13722","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13722v1","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13722","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"DC564HSPGIUB","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"DC564HSPGIUBKVI7","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"DC564HSP","created_at":"2026-07-05T09:22:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DC564HSPGIUBKVI755NCTYHQE6","target":"record","payload":{"canonical_record":{"source":{"id":"2410.13722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-17T16:27:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da5be6d76cafa6017603f7af3b170f91c5bc57d3c857660bc8f15a8939c2eea7","abstract_canon_sha256":"4ad6705f251ac8b4d590d481f5cefd933bfc6a305dd57c00ab6af53ec9034157"},"schema_version":"1.0"},"canonical_sha256":"18bbee1e4f322815551fef5a29e0f027921ef23e2d0559cc8ed41cba00b244de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:04.911474Z","signature_b64":"6aEC+QtseaN4ymPX6vBTdbNehA3Af87eNtGs9FeQzTf66BPkLdjbeHvtwlsHRrWhP3amMnwaZ2FfwpKVIFWAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18bbee1e4f322815551fef5a29e0f027921ef23e2d0559cc8ed41cba00b244de","last_reissued_at":"2026-07-05T09:22:04.910992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:04.910992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.13722","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":"2026-07-05T09:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gjhHUw/R92yM78w9MFxXTmyjxO9R+xN9hh2WumLWISfAgINqJPorhXOwVCH5sURFwpHHzey0+NMBVt8/og8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:49:43.103771Z"},"content_sha256":"9e53d4151b2e423cd2d843bc173fb4fd6688919a2c8a32abdc1ea083b2680ace","schema_version":"1.0","event_id":"sha256:9e53d4151b2e423cd2d843bc173fb4fd6688919a2c8a32abdc1ea083b2680ace"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DC564HSPGIUBKVI755NCTYHQE6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Persistent Pre-Training Poisoning of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Daphne Ippolito, Eric Michael Smith, Florian Tram\\`er, Ivan Evtimov, Javier Rando, Jianfeng Chi, Nicholas Carlini, Yiming Zhang","submitted_at":"2024-10-17T16:27:13Z","abstract_excerpt":"Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and (2) adversaries can compromise language models after poisoning fine-tuning datasets. Our work evaluates for the first time whether language models can also be compromised during pre-training, with a focus on the persistence of pre-training attacks after models are fine-tuned as helpful and harmless chatbots (i.e., after SFT and DPO). We pre-train a series of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13722","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/2410.13722/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":"2026-07-05T09:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y9O2V3hVSja0RU45Of+KwcA8Yo3l2VMxV0DtNfIlHhnXr2LINrY8Dqr0w9lT184mIvfsMr1kUmXn3i0zTj+CAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:49:43.104305Z"},"content_sha256":"0eefe500c623fbf21ccb442820d81f243128923ce833a11ee1cee7501c9bea28","schema_version":"1.0","event_id":"sha256:0eefe500c623fbf21ccb442820d81f243128923ce833a11ee1cee7501c9bea28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DC564HSPGIUBKVI755NCTYHQE6/bundle.json","state_url":"https://pith.science/pith/DC564HSPGIUBKVI755NCTYHQE6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DC564HSPGIUBKVI755NCTYHQE6/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":"2026-08-06T07:49:43Z","links":{"resolver":"https://pith.science/pith/DC564HSPGIUBKVI755NCTYHQE6","bundle":"https://pith.science/pith/DC564HSPGIUBKVI755NCTYHQE6/bundle.json","state":"https://pith.science/pith/DC564HSPGIUBKVI755NCTYHQE6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DC564HSPGIUBKVI755NCTYHQE6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DC564HSPGIUBKVI755NCTYHQE6","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":"4ad6705f251ac8b4d590d481f5cefd933bfc6a305dd57c00ab6af53ec9034157","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-17T16:27:13Z","title_canon_sha256":"da5be6d76cafa6017603f7af3b170f91c5bc57d3c857660bc8f15a8939c2eea7"},"schema_version":"1.0","source":{"id":"2410.13722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13722","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13722v1","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13722","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"DC564HSPGIUB","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"DC564HSPGIUBKVI7","created_at":"2026-07-05T09:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"DC564HSP","created_at":"2026-07-05T09:22:04Z"}],"graph_snapshots":[{"event_id":"sha256:0eefe500c623fbf21ccb442820d81f243128923ce833a11ee1cee7501c9bea28","target":"graph","created_at":"2026-07-05T09:22:04Z","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/2410.13722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and (2) adversaries can compromise language models after poisoning fine-tuning datasets. Our work evaluates for the first time whether language models can also be compromised during pre-training, with a focus on the persistence of pre-training attacks after models are fine-tuned as helpful and harmless chatbots (i.e., after SFT and DPO). We pre-train a series of ","authors_text":"Daphne Ippolito, Eric Michael Smith, Florian Tram\\`er, Ivan Evtimov, Javier Rando, Jianfeng Chi, Nicholas Carlini, Yiming Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-17T16:27:13Z","title":"Persistent Pre-Training Poisoning of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13722","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":"sha256:9e53d4151b2e423cd2d843bc173fb4fd6688919a2c8a32abdc1ea083b2680ace","target":"record","created_at":"2026-07-05T09:22:04Z","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":"4ad6705f251ac8b4d590d481f5cefd933bfc6a305dd57c00ab6af53ec9034157","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-17T16:27:13Z","title_canon_sha256":"da5be6d76cafa6017603f7af3b170f91c5bc57d3c857660bc8f15a8939c2eea7"},"schema_version":"1.0","source":{"id":"2410.13722","kind":"arxiv","version":1}},"canonical_sha256":"18bbee1e4f322815551fef5a29e0f027921ef23e2d0559cc8ed41cba00b244de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18bbee1e4f322815551fef5a29e0f027921ef23e2d0559cc8ed41cba00b244de","first_computed_at":"2026-07-05T09:22:04.910992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:04.910992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6aEC+QtseaN4ymPX6vBTdbNehA3Af87eNtGs9FeQzTf66BPkLdjbeHvtwlsHRrWhP3amMnwaZ2FfwpKVIFWAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:04.911474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e53d4151b2e423cd2d843bc173fb4fd6688919a2c8a32abdc1ea083b2680ace","sha256:0eefe500c623fbf21ccb442820d81f243128923ce833a11ee1cee7501c9bea28"],"state_sha256":"165035b93073a3c12e2403365f0d7bc9ca21d5e34a338f058386d4c84ee85b58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V2fsEwfxSo4Y5vTbZiau2LqSmRDIsbA0Jt5wxQs0AFbJrv3onKKUNt6fsj744rCL41wf6JmgByLH26mAV455Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:49:43.107893Z","bundle_sha256":"278ce02af48da0e1a915d2eb14980b058cb85600676825b727c338022ed0b173"}}