{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N3I4EHZSBUPHSQVVT25CIDG5GN","short_pith_number":"pith:N3I4EHZS","canonical_record":{"source":{"id":"2410.08811","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T13:50:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4e9b7197fc744ca2f49a808508e8b28c5ca99f626d2f514473a02590c8ac3911","abstract_canon_sha256":"6afe7a7bad9fcd83cd99738486161c82d393bcd60404629b81cbe88179bb043d"},"schema_version":"1.0"},"canonical_sha256":"6ed1c21f320d1e7942b59eba240cdd33663e8e6608fc666c4846c8da8bc0be05","source":{"kind":"arxiv","id":"2410.08811","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08811","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08811v2","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08811","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"pith_short_12","alias_value":"N3I4EHZSBUPH","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"pith_short_16","alias_value":"N3I4EHZSBUPHSQVV","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"pith_short_8","alias_value":"N3I4EHZS","created_at":"2026-07-05T11:16:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N3I4EHZSBUPHSQVVT25CIDG5GN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08811","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T13:50:50Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4e9b7197fc744ca2f49a808508e8b28c5ca99f626d2f514473a02590c8ac3911","abstract_canon_sha256":"6afe7a7bad9fcd83cd99738486161c82d393bcd60404629b81cbe88179bb043d"},"schema_version":"1.0"},"canonical_sha256":"6ed1c21f320d1e7942b59eba240cdd33663e8e6608fc666c4846c8da8bc0be05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:51.802497Z","signature_b64":"R8gm6+YPnleeCCTnSgSJzRz3Tg6vALjP4Vdi6U9gSXBK4sbOfJvv5o1MB19gSztkvGvgccX9bvKmy4Ki7ZJjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ed1c21f320d1e7942b59eba240cdd33663e8e6608fc666c4846c8da8bc0be05","last_reissued_at":"2026-07-05T11:16:51.801999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:51.801999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08811","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZhKdJQ51pysnougdnc/X8vjjuefZ0r7Ft7YmNfbqU6/1UFCZuh2QJBRtyG0dpFYmyeNs/EqMZgVoASQhzk3FAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:33:29.188671Z"},"content_sha256":"6d6dd8ce7e1909fb69f258352ccf3a73f83a8143bd73088fd217d72a1b520363","schema_version":"1.0","event_id":"sha256:6d6dd8ce7e1909fb69f258352ccf3a73f83a8143bd73088fd217d72a1b520363"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N3I4EHZSBUPHSQVVT25CIDG5GN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"David Krueger, Fazl Barez, Mrinank Sharma, Philip Torr, Shay B. Cohen, Tingchen Fu","submitted_at":"2024-10-11T13:50:50Z","abstract_excerpt":"Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models' susceptibility to data poisoning during preference learning. Data poisoning attacks can manipulate large language model responses to include hidden malicious content or biases, potentially causing the model to generate harmful or unintended outputs while appearing to function normally. We deploy two distinct attack types across eight realistic scenarios, assessing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08811","kind":"arxiv","version":2},"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/2410.08811/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":"2026-07-05T11:16:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KxLr3tac9xvMqs8B8eRHY9rYz4KgeL/Gce4UC6G6gYCkSrs3A8czhCyDhA+KfFcdXkRwhSdfCZHLjs9TEyrfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:33:29.189179Z"},"content_sha256":"3489ee9897f843e424ece32b3d77bd2071365575925e24ae82916244b6a1df10","schema_version":"1.0","event_id":"sha256:3489ee9897f843e424ece32b3d77bd2071365575925e24ae82916244b6a1df10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3I4EHZSBUPHSQVVT25CIDG5GN/bundle.json","state_url":"https://pith.science/pith/N3I4EHZSBUPHSQVVT25CIDG5GN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3I4EHZSBUPHSQVVT25CIDG5GN/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":"2026-08-05T23:33:29Z","links":{"resolver":"https://pith.science/pith/N3I4EHZSBUPHSQVVT25CIDG5GN","bundle":"https://pith.science/pith/N3I4EHZSBUPHSQVVT25CIDG5GN/bundle.json","state":"https://pith.science/pith/N3I4EHZSBUPHSQVVT25CIDG5GN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3I4EHZSBUPHSQVVT25CIDG5GN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3I4EHZSBUPHSQVVT25CIDG5GN","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":"6afe7a7bad9fcd83cd99738486161c82d393bcd60404629b81cbe88179bb043d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T13:50:50Z","title_canon_sha256":"4e9b7197fc744ca2f49a808508e8b28c5ca99f626d2f514473a02590c8ac3911"},"schema_version":"1.0","source":{"id":"2410.08811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08811","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08811v2","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08811","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"pith_short_12","alias_value":"N3I4EHZSBUPH","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"pith_short_16","alias_value":"N3I4EHZSBUPHSQVV","created_at":"2026-07-05T11:16:51Z"},{"alias_kind":"pith_short_8","alias_value":"N3I4EHZS","created_at":"2026-07-05T11:16:51Z"}],"graph_snapshots":[{"event_id":"sha256:3489ee9897f843e424ece32b3d77bd2071365575925e24ae82916244b6a1df10","target":"graph","created_at":"2026-07-05T11:16:51Z","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/2410.08811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models' susceptibility to data poisoning during preference learning. Data poisoning attacks can manipulate large language model responses to include hidden malicious content or biases, potentially causing the model to generate harmful or unintended outputs while appearing to function normally. We deploy two distinct attack types across eight realistic scenarios, assessing ","authors_text":"David Krueger, Fazl Barez, Mrinank Sharma, Philip Torr, Shay B. Cohen, Tingchen Fu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08811","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":"sha256:6d6dd8ce7e1909fb69f258352ccf3a73f83a8143bd73088fd217d72a1b520363","target":"record","created_at":"2026-07-05T11:16:51Z","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":"6afe7a7bad9fcd83cd99738486161c82d393bcd60404629b81cbe88179bb043d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T13:50:50Z","title_canon_sha256":"4e9b7197fc744ca2f49a808508e8b28c5ca99f626d2f514473a02590c8ac3911"},"schema_version":"1.0","source":{"id":"2410.08811","kind":"arxiv","version":2}},"canonical_sha256":"6ed1c21f320d1e7942b59eba240cdd33663e8e6608fc666c4846c8da8bc0be05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ed1c21f320d1e7942b59eba240cdd33663e8e6608fc666c4846c8da8bc0be05","first_computed_at":"2026-07-05T11:16:51.801999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:51.801999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R8gm6+YPnleeCCTnSgSJzRz3Tg6vALjP4Vdi6U9gSXBK4sbOfJvv5o1MB19gSztkvGvgccX9bvKmy4Ki7ZJjDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:51.802497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d6dd8ce7e1909fb69f258352ccf3a73f83a8143bd73088fd217d72a1b520363","sha256:3489ee9897f843e424ece32b3d77bd2071365575925e24ae82916244b6a1df10"],"state_sha256":"cce0887e5f029135a98d59f9ec6c01635b2d0c0f93939bfb86c57b9b478d3933"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2GlcHfNVUXPtQcnhWzJkZap4ls/4p89jm1vsiu7Rg4MscvCrwTtn9HDimZRLlHoaL65HSYwaWM2ZvuNArfWuDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:33:29.192691Z","bundle_sha256":"f06354c0fd77f9539935a737e6cae46e7771c7e32818565e8c9783225252af66"}}