{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AZQE4KYR6XJS4MTST5ZZZSY4GH","short_pith_number":"pith:AZQE4KYR","schema_version":"1.0","canonical_sha256":"06604e2b11f5d32e32729f739ccb1c31f6f40a4e1155e7f94fd373341fb08f57","source":{"kind":"arxiv","id":"2302.04026","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Comparison of Pre-Trained Models of Source Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bin Luo, Changan Niu, Chuanyi Li, Dongxiao Chen, Jidong Ge, Vincent Ng","submitted_at":"2023-02-08T12:57:46Z","abstract_excerpt":"While a large number of pre-trained models of source code have been successfully developed and applied to a variety of software engineering (SE) tasks in recent years, our understanding of these pre-trained models is arguably fairly limited. With the goal of advancing our understanding of these models, we perform the first systematic empirical comparison of 19 recently-developed pre-trained models of source code on 13 SE tasks. To gain additional insights into these models, we adopt a recently-developed 4-dimensional categorization of pre-trained models, and subsequently investigate whether th"},"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":"2302.04026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-02-08T12:57:46Z","cross_cats_sorted":[],"title_canon_sha256":"2e56948564d118126040c4e68775dd5bfc05ffc7655058f648568ec8030de86e","abstract_canon_sha256":"83d36c6223044ce603b3c4d46a50c7597740b524916568fe1bcebc355eaf663d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:00.362750Z","signature_b64":"MCQpObTVK7tSK3LweFvZaTPmKikh2qsS+5ohDma73rmqRumSmyx2zPh756Ko09tpw3/dO7bTxl2w86jNCMANBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06604e2b11f5d32e32729f739ccb1c31f6f40a4e1155e7f94fd373341fb08f57","last_reissued_at":"2026-07-05T05:40:00.362340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:00.362340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Comparison of Pre-Trained Models of Source Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bin Luo, Changan Niu, Chuanyi Li, Dongxiao Chen, Jidong Ge, Vincent Ng","submitted_at":"2023-02-08T12:57:46Z","abstract_excerpt":"While a large number of pre-trained models of source code have been successfully developed and applied to a variety of software engineering (SE) tasks in recent years, our understanding of these pre-trained models is arguably fairly limited. With the goal of advancing our understanding of these models, we perform the first systematic empirical comparison of 19 recently-developed pre-trained models of source code on 13 SE tasks. To gain additional insights into these models, we adopt a recently-developed 4-dimensional categorization of pre-trained models, and subsequently investigate whether th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04026","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/2302.04026/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":"2302.04026","created_at":"2026-07-05T05:40:00.362397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04026v1","created_at":"2026-07-05T05:40:00.362397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04026","created_at":"2026-07-05T05:40:00.362397+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZQE4KYR6XJS","created_at":"2026-07-05T05:40:00.362397+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZQE4KYR6XJS4MTS","created_at":"2026-07-05T05:40:00.362397+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZQE4KYR","created_at":"2026-07-05T05:40:00.362397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00511","citing_title":"Large Language Models for Multi-Lingual Equivalent Mutant Detection: An Extended Empirical Study","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH","json":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH.json","graph_json":"https://pith.science/api/pith-number/AZQE4KYR6XJS4MTST5ZZZSY4GH/graph.json","events_json":"https://pith.science/api/pith-number/AZQE4KYR6XJS4MTST5ZZZSY4GH/events.json","paper":"https://pith.science/paper/AZQE4KYR"},"agent_actions":{"view_html":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH","download_json":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH.json","view_paper":"https://pith.science/paper/AZQE4KYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04026&json=true","fetch_graph":"https://pith.science/api/pith-number/AZQE4KYR6XJS4MTST5ZZZSY4GH/graph.json","fetch_events":"https://pith.science/api/pith-number/AZQE4KYR6XJS4MTST5ZZZSY4GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH/action/storage_attestation","attest_author":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH/action/author_attestation","sign_citation":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH/action/citation_signature","submit_replication":"https://pith.science/pith/AZQE4KYR6XJS4MTST5ZZZSY4GH/action/replication_record"}},"created_at":"2026-07-05T05:40:00.362397+00:00","updated_at":"2026-07-05T05:40:00.362397+00:00"}