{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I2TGOLSNXT53VU6SA4KHGNF7LN","short_pith_number":"pith:I2TGOLSN","schema_version":"1.0","canonical_sha256":"46a6672e4dbcfbbad3d207147334bf5b61ecdee2384606f62ae7b5ca2957d147","source":{"kind":"arxiv","id":"2211.00609","version":2},"attestation_state":"computed","paper":{"title":"A Simple, Yet Effective Approach to Finding Biases in Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.AI","authors_text":"Henryk Michalewski, Mateusz Malinowski, Spyridon Mouselinos","submitted_at":"2022-10-31T15:06:15Z","abstract_excerpt":"Recently, high-performing code generation systems based on large language models have surfaced. They are trained on massive corpora containing much more natural text than actual executable computer code. This work shows that current code generation systems exhibit undesired biases inherited from their large language model backbones, which can reduce the quality of the generated code under specific circumstances.\n  To investigate the effect, we propose the \"block of influence\" concept, which enables a modular decomposition and analysis of the coding challenges. We introduce an automated interve"},"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":"2211.00609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-31T15:06:15Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"943025cdc1791f55c6ffe7c8e58ae74f6de184c20a9341c2e38bdec780edf7c1","abstract_canon_sha256":"3209edcf931dc040ff3c09019412be134065f66f5f09bd6b0ee786cc12671bd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:12.982668Z","signature_b64":"Pgt2VZSCGWz1SY9nGGHszXiGM5+pZztX2euU99Od7YQ3CvfylslY+ISINm03h4JPBISWRHsSOgxw1hyvuigZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46a6672e4dbcfbbad3d207147334bf5b61ecdee2384606f62ae7b5ca2957d147","last_reissued_at":"2026-07-05T06:08:12.982170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:12.982170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple, Yet Effective Approach to Finding Biases in Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.AI","authors_text":"Henryk Michalewski, Mateusz Malinowski, Spyridon Mouselinos","submitted_at":"2022-10-31T15:06:15Z","abstract_excerpt":"Recently, high-performing code generation systems based on large language models have surfaced. They are trained on massive corpora containing much more natural text than actual executable computer code. This work shows that current code generation systems exhibit undesired biases inherited from their large language model backbones, which can reduce the quality of the generated code under specific circumstances.\n  To investigate the effect, we propose the \"block of influence\" concept, which enables a modular decomposition and analysis of the coding challenges. We introduce an automated interve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00609","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/2211.00609/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":"2211.00609","created_at":"2026-07-05T06:08:12.982233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00609v2","created_at":"2026-07-05T06:08:12.982233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00609","created_at":"2026-07-05T06:08:12.982233+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2TGOLSNXT53","created_at":"2026-07-05T06:08:12.982233+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2TGOLSNXT53VU6S","created_at":"2026-07-05T06:08:12.982233+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2TGOLSN","created_at":"2026-07-05T06:08:12.982233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":189,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN","json":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN.json","graph_json":"https://pith.science/api/pith-number/I2TGOLSNXT53VU6SA4KHGNF7LN/graph.json","events_json":"https://pith.science/api/pith-number/I2TGOLSNXT53VU6SA4KHGNF7LN/events.json","paper":"https://pith.science/paper/I2TGOLSN"},"agent_actions":{"view_html":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN","download_json":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN.json","view_paper":"https://pith.science/paper/I2TGOLSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00609&json=true","fetch_graph":"https://pith.science/api/pith-number/I2TGOLSNXT53VU6SA4KHGNF7LN/graph.json","fetch_events":"https://pith.science/api/pith-number/I2TGOLSNXT53VU6SA4KHGNF7LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN/action/storage_attestation","attest_author":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN/action/author_attestation","sign_citation":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN/action/citation_signature","submit_replication":"https://pith.science/pith/I2TGOLSNXT53VU6SA4KHGNF7LN/action/replication_record"}},"created_at":"2026-07-05T06:08:12.982233+00:00","updated_at":"2026-07-05T06:08:12.982233+00:00"}