{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6NDWPLVQDVSLXWGZK5HFHY2Z6D","short_pith_number":"pith:6NDWPLVQ","schema_version":"1.0","canonical_sha256":"f34767aeb01d64bbd8d9574e53e359f0f7dab3e53d16a45efc2af6f3f9609e4e","source":{"kind":"arxiv","id":"2311.08066","version":1},"attestation_state":"computed","paper":{"title":"How to get better embeddings with code pre-trained models? An empirical study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Haoxiang Zhang, Lina Gong, Yaoshen Yu, Yu Zhao, Zhiqiu Huang","submitted_at":"2023-11-14T10:44:21Z","abstract_excerpt":"Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the experiences of the NLP field, have also achieved state-of-the-art results in many software engineering (SE) downstream tasks. These code PTMs take into account the differences between programming languages and natural languages during pre-training and make adjustments to pre-training tasks and input data. However, researchers in the SE community still inherit habits from the NLP field when using these code PTMs to gen"},"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":"2311.08066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-11-14T10:44:21Z","cross_cats_sorted":[],"title_canon_sha256":"6e8307e021c7157fcddb0a1b3a0d4c72543e237c88ff4c361d9d3bfc4e1e8e93","abstract_canon_sha256":"40d50bc107f9891a0cb4b0183469fc285140662d2f945c64074181e77fd3e494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:39.803871Z","signature_b64":"QVwOTSsxIYNk+j9QTsBu/OZ2iYnKSKySWYIM5K/xula2dC9rkpWwGR3HqjUOmmB7GZQqSCLMH8vd0oTQu89EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f34767aeb01d64bbd8d9574e53e359f0f7dab3e53d16a45efc2af6f3f9609e4e","last_reissued_at":"2026-07-05T07:12:39.803397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:39.803397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to get better embeddings with code pre-trained models? An empirical study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Haoxiang Zhang, Lina Gong, Yaoshen Yu, Yu Zhao, Zhiqiu Huang","submitted_at":"2023-11-14T10:44:21Z","abstract_excerpt":"Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the experiences of the NLP field, have also achieved state-of-the-art results in many software engineering (SE) downstream tasks. These code PTMs take into account the differences between programming languages and natural languages during pre-training and make adjustments to pre-training tasks and input data. However, researchers in the SE community still inherit habits from the NLP field when using these code PTMs to gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08066","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/2311.08066/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":"2311.08066","created_at":"2026-07-05T07:12:39.803456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.08066v1","created_at":"2026-07-05T07:12:39.803456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08066","created_at":"2026-07-05T07:12:39.803456+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NDWPLVQDVSL","created_at":"2026-07-05T07:12:39.803456+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NDWPLVQDVSLXWGZ","created_at":"2026-07-05T07:12:39.803456+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NDWPLVQ","created_at":"2026-07-05T07:12:39.803456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D","json":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D.json","graph_json":"https://pith.science/api/pith-number/6NDWPLVQDVSLXWGZK5HFHY2Z6D/graph.json","events_json":"https://pith.science/api/pith-number/6NDWPLVQDVSLXWGZK5HFHY2Z6D/events.json","paper":"https://pith.science/paper/6NDWPLVQ"},"agent_actions":{"view_html":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D","download_json":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D.json","view_paper":"https://pith.science/paper/6NDWPLVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.08066&json=true","fetch_graph":"https://pith.science/api/pith-number/6NDWPLVQDVSLXWGZK5HFHY2Z6D/graph.json","fetch_events":"https://pith.science/api/pith-number/6NDWPLVQDVSLXWGZK5HFHY2Z6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D/action/storage_attestation","attest_author":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D/action/author_attestation","sign_citation":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D/action/citation_signature","submit_replication":"https://pith.science/pith/6NDWPLVQDVSLXWGZK5HFHY2Z6D/action/replication_record"}},"created_at":"2026-07-05T07:12:39.803456+00:00","updated_at":"2026-07-05T07:12:39.803456+00:00"}