{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ME6OGURTSWF4HMFEJS2MX3BKLE","short_pith_number":"pith:ME6OGURT","schema_version":"1.0","canonical_sha256":"613ce35233958bc3b0a44cb4cbec2a593bf29b7039667f225e4d79653353d980","source":{"kind":"arxiv","id":"2503.11402","version":1},"attestation_state":"computed","paper":{"title":"Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Cristina Improta, Domenico Cotroneo, Gabriele Bavota, Pietro Liguori, Rosalia Tufano","submitted_at":"2025-03-14T13:43:43Z","abstract_excerpt":"Deep Learning-based code generators have seen significant advancements in recent years. Tools such as GitHub Copilot are used by thousands of developers with the main promise of a boost in productivity. However, researchers have recently questioned their impact on code quality showing, for example, that code generated by DL-based tools may be affected by security vulnerabilities. Since DL models are trained on large code corpora, one may conjecture that low-quality code they output is the result of low-quality code they have seen during training. However, there is very little empirical evidenc"},"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":"2503.11402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-14T13:43:43Z","cross_cats_sorted":[],"title_canon_sha256":"e11d5ede44e2be4d2307d3a3a86208906d2a2e412c7c4f3ec7159d47efabeb77","abstract_canon_sha256":"c7c13943734cd80930b621b9d70ab79de3232b43ee303e97c01d5eb453d74bae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:30.520168Z","signature_b64":"WvWm4j0KbA9Fz69qrdf8OMhd++lWHvHwZRTyxePbnSkWGlC3OpjFI26961+dMMZhEQT7Gd9Rirj0ngGDVBCJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"613ce35233958bc3b0a44cb4cbec2a593bf29b7039667f225e4d79653353d980","last_reissued_at":"2026-07-05T10:31:30.519559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:30.519559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quality In, Quality Out: Investigating Training Data's Role in AI Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Cristina Improta, Domenico Cotroneo, Gabriele Bavota, Pietro Liguori, Rosalia Tufano","submitted_at":"2025-03-14T13:43:43Z","abstract_excerpt":"Deep Learning-based code generators have seen significant advancements in recent years. Tools such as GitHub Copilot are used by thousands of developers with the main promise of a boost in productivity. However, researchers have recently questioned their impact on code quality showing, for example, that code generated by DL-based tools may be affected by security vulnerabilities. Since DL models are trained on large code corpora, one may conjecture that low-quality code they output is the result of low-quality code they have seen during training. However, there is very little empirical evidenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11402","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/2503.11402/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":"2503.11402","created_at":"2026-07-05T10:31:30.519621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11402v1","created_at":"2026-07-05T10:31:30.519621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11402","created_at":"2026-07-05T10:31:30.519621+00:00"},{"alias_kind":"pith_short_12","alias_value":"ME6OGURTSWF4","created_at":"2026-07-05T10:31:30.519621+00:00"},{"alias_kind":"pith_short_16","alias_value":"ME6OGURTSWF4HMFE","created_at":"2026-07-05T10:31:30.519621+00:00"},{"alias_kind":"pith_short_8","alias_value":"ME6OGURT","created_at":"2026-07-05T10:31:30.519621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE","json":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE.json","graph_json":"https://pith.science/api/pith-number/ME6OGURTSWF4HMFEJS2MX3BKLE/graph.json","events_json":"https://pith.science/api/pith-number/ME6OGURTSWF4HMFEJS2MX3BKLE/events.json","paper":"https://pith.science/paper/ME6OGURT"},"agent_actions":{"view_html":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE","download_json":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE.json","view_paper":"https://pith.science/paper/ME6OGURT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11402&json=true","fetch_graph":"https://pith.science/api/pith-number/ME6OGURTSWF4HMFEJS2MX3BKLE/graph.json","fetch_events":"https://pith.science/api/pith-number/ME6OGURTSWF4HMFEJS2MX3BKLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE/action/storage_attestation","attest_author":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE/action/author_attestation","sign_citation":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE/action/citation_signature","submit_replication":"https://pith.science/pith/ME6OGURTSWF4HMFEJS2MX3BKLE/action/replication_record"}},"created_at":"2026-07-05T10:31:30.519621+00:00","updated_at":"2026-07-05T10:31:30.519621+00:00"}