{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AGB2FBCTT2YMMIQYDNHUIFN6IE","short_pith_number":"pith:AGB2FBCT","schema_version":"1.0","canonical_sha256":"0183a284539eb0c622181b4f4415be4103a244237799e40303d686ef63daabb6","source":{"kind":"arxiv","id":"2108.09293","version":3},"attestation_state":"computed","paper":{"title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, Hammond Pearce, Ramesh Karri","submitted_at":"2021-08-20T17:30:33Z","abstract_excerpt":"There is burgeoning interest in designing AI-based systems to assist humans in designing computing systems, including tools that automatically generate computer code. The most notable of these comes in the form of the first self-described `AI pair programmer', GitHub Copilot, a language model trained over open-source GitHub code. However, code often contains bugs - and so, given the vast quantity of unvetted code that Copilot has processed, it is certain that the language model will have learned from exploitable, buggy code. This raises concerns on the security of Copilot's code contributions."},"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":"2108.09293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-08-20T17:30:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"336cbd064358023f335ff04b9bbc2869c1d39306b1f7fdb405f68d8a0cedf914","abstract_canon_sha256":"a097fcf8221a26b2a6b90882f8196293c5377dab9fc4873c53e60886cf91d140"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:26.591755Z","signature_b64":"NQOmL9f4xk83ITbGn/gT0UYh7FjPniwi/mmmn67UIZ3b5Fs/kteHSmJ+/1jIDwOpQHrHpIz/qFDTCugEbfCwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0183a284539eb0c622181b4f4415be4103a244237799e40303d686ef63daabb6","last_reissued_at":"2026-07-05T03:41:26.591355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:26.591355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, Hammond Pearce, Ramesh Karri","submitted_at":"2021-08-20T17:30:33Z","abstract_excerpt":"There is burgeoning interest in designing AI-based systems to assist humans in designing computing systems, including tools that automatically generate computer code. The most notable of these comes in the form of the first self-described `AI pair programmer', GitHub Copilot, a language model trained over open-source GitHub code. However, code often contains bugs - and so, given the vast quantity of unvetted code that Copilot has processed, it is certain that the language model will have learned from exploitable, buggy code. This raises concerns on the security of Copilot's code contributions."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09293","kind":"arxiv","version":3},"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/2108.09293/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":"2108.09293","created_at":"2026-07-05T03:41:26.591404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.09293v3","created_at":"2026-07-05T03:41:26.591404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09293","created_at":"2026-07-05T03:41:26.591404+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGB2FBCTT2YM","created_at":"2026-07-05T03:41:26.591404+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGB2FBCTT2YMMIQY","created_at":"2026-07-05T03:41:26.591404+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGB2FBCT","created_at":"2026-07-05T03:41:26.591404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12986","citing_title":"The Rise of AI-Native Software Engineering: Implications for Practice, Education, and the Future Workforce","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22534","citing_title":"Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16829","citing_title":"Constrained Code Generation with Discrete Diffusion","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06759","citing_title":"\"Tab, Tab, Bug\": Security Pitfalls of Next Edit Suggestions in AI-Integrated IDEs","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23338","citing_title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19826","citing_title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2204.02311","citing_title":"PaLM: Scaling Language Modeling with Pathways","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06161","citing_title":"StarCoder: may the source be with you!","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":288,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17803","citing_title":"Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE","json":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE.json","graph_json":"https://pith.science/api/pith-number/AGB2FBCTT2YMMIQYDNHUIFN6IE/graph.json","events_json":"https://pith.science/api/pith-number/AGB2FBCTT2YMMIQYDNHUIFN6IE/events.json","paper":"https://pith.science/paper/AGB2FBCT"},"agent_actions":{"view_html":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE","download_json":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE.json","view_paper":"https://pith.science/paper/AGB2FBCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.09293&json=true","fetch_graph":"https://pith.science/api/pith-number/AGB2FBCTT2YMMIQYDNHUIFN6IE/graph.json","fetch_events":"https://pith.science/api/pith-number/AGB2FBCTT2YMMIQYDNHUIFN6IE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE/action/storage_attestation","attest_author":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE/action/author_attestation","sign_citation":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE/action/citation_signature","submit_replication":"https://pith.science/pith/AGB2FBCTT2YMMIQYDNHUIFN6IE/action/replication_record"}},"created_at":"2026-07-05T03:41:26.591404+00:00","updated_at":"2026-07-05T03:41:26.591404+00:00"}