{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ILDL7FOSHHRSK3ZXYPCJGTBDG2","short_pith_number":"pith:ILDL7FOS","schema_version":"1.0","canonical_sha256":"42c6bf95d239e3256f37c3c4934c233691a3ba11480b98a4862242df6f461285","source":{"kind":"arxiv","id":"2406.05087","version":2},"attestation_state":"computed","paper":{"title":"Corpus Poisoning via Approximate Greedy Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Claire Cardie, Jinyan Su, Preslav Nakov","submitted_at":"2024-06-07T17:02:35Z","abstract_excerpt":"Dense retrievers are widely used in information retrieval and have also been successfully extended to other knowledge intensive areas such as language models, e.g., Retrieval-Augmented Generation (RAG) systems. Unfortunately, they have recently been shown to be vulnerable to corpus poisoning attacks in which a malicious user injects a small fraction of adversarial passages into the retrieval corpus to trick the system into returning these passages among the top-ranked results for a broad set of user queries. Further study is needed to understand the extent to which these attacks could limit th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.05087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-07T17:02:35Z","cross_cats_sorted":[],"title_canon_sha256":"9023b697cfbfbdbd1aaa4e9ea6c9c34a9b20d9c9443a80d0742509fbb860a08a","abstract_canon_sha256":"8217032f1a56c034629dfc4f91359c98c4e2d88d027c09f213e2ee5a56207480"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:44.107503Z","signature_b64":"teauT7XrYxWU+bGcRrhESX5aGg7NcnXRHPPYWTZpKwiM1xYBjLwUscpvXqagqkLS3Dcca3S9dXOjD2En0CPWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42c6bf95d239e3256f37c3c4934c233691a3ba11480b98a4862242df6f461285","last_reissued_at":"2026-07-05T09:25:44.106953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:44.106953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corpus Poisoning via Approximate Greedy Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Claire Cardie, Jinyan Su, Preslav Nakov","submitted_at":"2024-06-07T17:02:35Z","abstract_excerpt":"Dense retrievers are widely used in information retrieval and have also been successfully extended to other knowledge intensive areas such as language models, e.g., Retrieval-Augmented Generation (RAG) systems. Unfortunately, they have recently been shown to be vulnerable to corpus poisoning attacks in which a malicious user injects a small fraction of adversarial passages into the retrieval corpus to trick the system into returning these passages among the top-ranked results for a broad set of user queries. Further study is needed to understand the extent to which these attacks could limit th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05087","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/2406.05087/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.05087","created_at":"2026-07-05T09:25:44.107022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05087v2","created_at":"2026-07-05T09:25:44.107022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05087","created_at":"2026-07-05T09:25:44.107022+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILDL7FOSHHRS","created_at":"2026-07-05T09:25:44.107022+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILDL7FOSHHRSK3ZX","created_at":"2026-07-05T09:25:44.107022+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILDL7FOS","created_at":"2026-07-05T09:25:44.107022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01591","citing_title":"Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2","json":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2.json","graph_json":"https://pith.science/api/pith-number/ILDL7FOSHHRSK3ZXYPCJGTBDG2/graph.json","events_json":"https://pith.science/api/pith-number/ILDL7FOSHHRSK3ZXYPCJGTBDG2/events.json","paper":"https://pith.science/paper/ILDL7FOS"},"agent_actions":{"view_html":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2","download_json":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2.json","view_paper":"https://pith.science/paper/ILDL7FOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05087&json=true","fetch_graph":"https://pith.science/api/pith-number/ILDL7FOSHHRSK3ZXYPCJGTBDG2/graph.json","fetch_events":"https://pith.science/api/pith-number/ILDL7FOSHHRSK3ZXYPCJGTBDG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2/action/storage_attestation","attest_author":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2/action/author_attestation","sign_citation":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2/action/citation_signature","submit_replication":"https://pith.science/pith/ILDL7FOSHHRSK3ZXYPCJGTBDG2/action/replication_record"}},"created_at":"2026-07-05T09:25:44.107022+00:00","updated_at":"2026-07-05T09:25:44.107022+00:00"}