{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JQMFLWFL44AQ5KMCUAGMOIKZ3L","short_pith_number":"pith:JQMFLWFL","schema_version":"1.0","canonical_sha256":"4c1855d8abe7010ea982a00cc72159daf8f4aff2aeb7e0ac7928bc1967a1b46b","source":{"kind":"arxiv","id":"2311.00931","version":2},"attestation_state":"computed","paper":{"title":"Learning Defect Prediction from Unrealistic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Orso, Kamel Alrashedy, Vincent J. Hellendoorn","submitted_at":"2023-11-02T01:51:43Z","abstract_excerpt":"Pretrained models of code, such as CodeBERT and CodeT5, have become popular choices for code understanding and generation tasks. Such models tend to be large and require commensurate volumes of training data, which are rarely available for downstream tasks. Instead, it has become popular to train models with far larger but less realistic datasets, such as functions with artificially injected bugs. Models trained on such data, however, tend to only perform well on similar data, while underperforming on real world programs. In this paper, we conjecture that this discrepancy stems from the presen"},"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":"2311.00931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T01:51:43Z","cross_cats_sorted":[],"title_canon_sha256":"a6cecb4833d642d1449a0e82e5503f162b51848be3bb0f649404cf33d5419277","abstract_canon_sha256":"4dceab9a0488032544b00971b3438db085fe00091ad346e2c20161f04ba3f036"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:40.700050Z","signature_b64":"Myb0h4W4kBLoTb+VML2iNzkrwhL7SLCkBIaPt/3bzsrUT8pmtVo8g5TgoNu5hozY5jO5Llh5Q74+iWtlC5N8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c1855d8abe7010ea982a00cc72159daf8f4aff2aeb7e0ac7928bc1967a1b46b","last_reissued_at":"2026-07-05T07:35:40.699617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:40.699617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Defect Prediction from Unrealistic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Orso, Kamel Alrashedy, Vincent J. Hellendoorn","submitted_at":"2023-11-02T01:51:43Z","abstract_excerpt":"Pretrained models of code, such as CodeBERT and CodeT5, have become popular choices for code understanding and generation tasks. Such models tend to be large and require commensurate volumes of training data, which are rarely available for downstream tasks. Instead, it has become popular to train models with far larger but less realistic datasets, such as functions with artificially injected bugs. Models trained on such data, however, tend to only perform well on similar data, while underperforming on real world programs. In this paper, we conjecture that this discrepancy stems from the presen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00931","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/2311.00931/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":"2311.00931","created_at":"2026-07-05T07:35:40.699671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00931v2","created_at":"2026-07-05T07:35:40.699671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00931","created_at":"2026-07-05T07:35:40.699671+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQMFLWFL44AQ","created_at":"2026-07-05T07:35:40.699671+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQMFLWFL44AQ5KMC","created_at":"2026-07-05T07:35:40.699671+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQMFLWFL","created_at":"2026-07-05T07:35:40.699671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15368","citing_title":"The Power of Types: Exploring the Impact of Type Checking on Neural Bug Detection in Dynamically Typed Languages","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L","json":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L.json","graph_json":"https://pith.science/api/pith-number/JQMFLWFL44AQ5KMCUAGMOIKZ3L/graph.json","events_json":"https://pith.science/api/pith-number/JQMFLWFL44AQ5KMCUAGMOIKZ3L/events.json","paper":"https://pith.science/paper/JQMFLWFL"},"agent_actions":{"view_html":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L","download_json":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L.json","view_paper":"https://pith.science/paper/JQMFLWFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00931&json=true","fetch_graph":"https://pith.science/api/pith-number/JQMFLWFL44AQ5KMCUAGMOIKZ3L/graph.json","fetch_events":"https://pith.science/api/pith-number/JQMFLWFL44AQ5KMCUAGMOIKZ3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L/action/storage_attestation","attest_author":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L/action/author_attestation","sign_citation":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L/action/citation_signature","submit_replication":"https://pith.science/pith/JQMFLWFL44AQ5KMCUAGMOIKZ3L/action/replication_record"}},"created_at":"2026-07-05T07:35:40.699671+00:00","updated_at":"2026-07-05T07:35:40.699671+00:00"}