{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OOXOGMIQ2WT67DZHZAPEDDL2YV","short_pith_number":"pith:OOXOGMIQ","canonical_record":{"source":{"id":"2504.13769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-18T16:11:59Z","cross_cats_sorted":[],"title_canon_sha256":"1f59aef5870bdef4508fa7ad14703abfdeee706b123e6279b2edf544d84b6347","abstract_canon_sha256":"9658665869c499fc29220e2e95218b07401332e7cfef9de6c9e7c9d01bc181c6"},"schema_version":"1.0"},"canonical_sha256":"73aee33110d5a7ef8f27c81e418d7ac54dbc0a1a90f88fa3726922491fab0301","source":{"kind":"arxiv","id":"2504.13769","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13769","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13769v1","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13769","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"OOXOGMIQ2WT6","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"pith_short_16","alias_value":"OOXOGMIQ2WT67DZH","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"pith_short_8","alias_value":"OOXOGMIQ","created_at":"2026-07-05T10:51:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OOXOGMIQ2WT67DZHZAPEDDL2YV","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-18T16:11:59Z","cross_cats_sorted":[],"title_canon_sha256":"1f59aef5870bdef4508fa7ad14703abfdeee706b123e6279b2edf544d84b6347","abstract_canon_sha256":"9658665869c499fc29220e2e95218b07401332e7cfef9de6c9e7c9d01bc181c6"},"schema_version":"1.0"},"canonical_sha256":"73aee33110d5a7ef8f27c81e418d7ac54dbc0a1a90f88fa3726922491fab0301","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:01.903829Z","signature_b64":"XlPUXTrH5xjK4xPiuBAgvaWzxlke2JleNHoCr7uMmveXruOVAv9Vtina9SA1SgAcfKo0pJ5u5SdBS9NC9zwmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73aee33110d5a7ef8f27c81e418d7ac54dbc0a1a90f88fa3726922491fab0301","last_reissued_at":"2026-07-05T10:51:01.903292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:01.903292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13769","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":"2026-07-05T10:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WF7E/vGP8Z20ksk/CAFio1H5yJnr+nuLxUfmNvH9WSO7hyb4/3giXB0xr2eLY0BtxNIALl9jxhEz+DimTwArAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:33:45.605644Z"},"content_sha256":"c94123dde644f27ce41b823d6741494d6e2081f6c3bd316da55ed55952b586d2","schema_version":"1.0","event_id":"sha256:c94123dde644f27ce41b823d6741494d6e2081f6c3bd316da55ed55952b586d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OOXOGMIQ2WT67DZHZAPEDDL2YV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Malicious Source Code in PyPI Packages with LLMs: Does RAG Come in Handy?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Claudio Di Sipio, Davide Di Ruscio, Motunrayo Ibiyo, Phuong T. Nguyen, Thinakone Louangdy","submitted_at":"2025-04-18T16:11:59Z","abstract_excerpt":"Malicious software packages in open-source ecosystems, such as PyPI, pose growing security risks. Unlike traditional vulnerabilities, these packages are intentionally designed to deceive users, making detection challenging due to evolving attack methods and the lack of structured datasets. In this work, we empirically evaluate the effectiveness of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and few-shot learning for detecting malicious source code. We fine-tune LLMs on curated datasets and integrate YARA rules, GitHub Security Advisories, and malicious code snippets wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13769","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/2504.13769/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":"2026-07-05T10:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AGSu+ClrVpwzZlHcVuilm54MqrUS9ydWnbgobTZIO5w8iT34oiah/CK0BwqtDEEGcJ78BzZ+qf9sv1RDoTRxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:33:45.606473Z"},"content_sha256":"f0e8fdf67926aaae91ed7f3e585bcf217a93b9bd081a0b23b55e2c200cdc3dd8","schema_version":"1.0","event_id":"sha256:f0e8fdf67926aaae91ed7f3e585bcf217a93b9bd081a0b23b55e2c200cdc3dd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOXOGMIQ2WT67DZHZAPEDDL2YV/bundle.json","state_url":"https://pith.science/pith/OOXOGMIQ2WT67DZHZAPEDDL2YV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOXOGMIQ2WT67DZHZAPEDDL2YV/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":"2026-08-08T10:33:45Z","links":{"resolver":"https://pith.science/pith/OOXOGMIQ2WT67DZHZAPEDDL2YV","bundle":"https://pith.science/pith/OOXOGMIQ2WT67DZHZAPEDDL2YV/bundle.json","state":"https://pith.science/pith/OOXOGMIQ2WT67DZHZAPEDDL2YV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOXOGMIQ2WT67DZHZAPEDDL2YV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OOXOGMIQ2WT67DZHZAPEDDL2YV","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":"9658665869c499fc29220e2e95218b07401332e7cfef9de6c9e7c9d01bc181c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-18T16:11:59Z","title_canon_sha256":"1f59aef5870bdef4508fa7ad14703abfdeee706b123e6279b2edf544d84b6347"},"schema_version":"1.0","source":{"id":"2504.13769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13769","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13769v1","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13769","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"OOXOGMIQ2WT6","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"pith_short_16","alias_value":"OOXOGMIQ2WT67DZH","created_at":"2026-07-05T10:51:01Z"},{"alias_kind":"pith_short_8","alias_value":"OOXOGMIQ","created_at":"2026-07-05T10:51:01Z"}],"graph_snapshots":[{"event_id":"sha256:f0e8fdf67926aaae91ed7f3e585bcf217a93b9bd081a0b23b55e2c200cdc3dd8","target":"graph","created_at":"2026-07-05T10:51:01Z","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/2504.13769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Malicious software packages in open-source ecosystems, such as PyPI, pose growing security risks. Unlike traditional vulnerabilities, these packages are intentionally designed to deceive users, making detection challenging due to evolving attack methods and the lack of structured datasets. In this work, we empirically evaluate the effectiveness of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and few-shot learning for detecting malicious source code. We fine-tune LLMs on curated datasets and integrate YARA rules, GitHub Security Advisories, and malicious code snippets wit","authors_text":"Claudio Di Sipio, Davide Di Ruscio, Motunrayo Ibiyo, Phuong T. Nguyen, Thinakone Louangdy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-18T16:11:59Z","title":"Detecting Malicious Source Code in PyPI Packages with LLMs: Does RAG Come in Handy?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13769","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:c94123dde644f27ce41b823d6741494d6e2081f6c3bd316da55ed55952b586d2","target":"record","created_at":"2026-07-05T10:51:01Z","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":"9658665869c499fc29220e2e95218b07401332e7cfef9de6c9e7c9d01bc181c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-18T16:11:59Z","title_canon_sha256":"1f59aef5870bdef4508fa7ad14703abfdeee706b123e6279b2edf544d84b6347"},"schema_version":"1.0","source":{"id":"2504.13769","kind":"arxiv","version":1}},"canonical_sha256":"73aee33110d5a7ef8f27c81e418d7ac54dbc0a1a90f88fa3726922491fab0301","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73aee33110d5a7ef8f27c81e418d7ac54dbc0a1a90f88fa3726922491fab0301","first_computed_at":"2026-07-05T10:51:01.903292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:01.903292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XlPUXTrH5xjK4xPiuBAgvaWzxlke2JleNHoCr7uMmveXruOVAv9Vtina9SA1SgAcfKo0pJ5u5SdBS9NC9zwmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:01.903829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c94123dde644f27ce41b823d6741494d6e2081f6c3bd316da55ed55952b586d2","sha256:f0e8fdf67926aaae91ed7f3e585bcf217a93b9bd081a0b23b55e2c200cdc3dd8"],"state_sha256":"bc02671f0501036a353af7a8f9019890ed7cbdb99352005a6721f6db43cd2e6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hzs7fjM8UQU6riMkpO5jbPy05AJ0rUYJSBu5c7Apz12JsaK289TsnWVylTII17y0uUC9FI0wPP2cd//xLrsmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:33:45.613721Z","bundle_sha256":"f14d7ee4c437b9fe8994506c38e9b8677adc55cf20f6b59251d00013c1798a26"}}