{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q2QABSZPABW52JNWP65SWMEBT6","short_pith_number":"pith:Q2QABSZP","schema_version":"1.0","canonical_sha256":"86a000cb2f006ddd25b67fbb2b30819f82b0568a4207c6e39dc813001417d711","source":{"kind":"arxiv","id":"2508.21290","version":1},"attestation_state":"computed","paper":{"title":"Efficient Code Embeddings from Code Generation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Daria Kryvosheieva, Han Xiao, Michael G\\\"unther, Saba Sturua, Scott Martens","submitted_at":"2025-08-29T01:18:15Z","abstract_excerpt":"jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validating this approach to code embedding model construction."},"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":"2508.21290","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T01:18:15Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"7ab111088a9964e813e6a0dfea1077cab09f7383750cef86f19816eb802dc24d","abstract_canon_sha256":"bce203dc793e743cbfe20cbcd26fd082dc7ac867cb26027296b3e169ddb4e68f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:31.953159Z","signature_b64":"GeYFmIz1tp0+w4riyIJwF1rxRw2uTfVLfazF54a+KZrjFY1BTNr6E/qSD2vtEZiwgcfkWk/BXfDiT+H5fYU6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86a000cb2f006ddd25b67fbb2b30819f82b0568a4207c6e39dc813001417d711","last_reissued_at":"2026-07-05T12:01:31.952659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:31.952659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Code Embeddings from Code Generation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Daria Kryvosheieva, Han Xiao, Michael G\\\"unther, Saba Sturua, Scott Martens","submitted_at":"2025-08-29T01:18:15Z","abstract_excerpt":"jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validating this approach to code embedding model construction."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21290","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/2508.21290/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":"2508.21290","created_at":"2026-07-05T12:01:31.952719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21290v1","created_at":"2026-07-05T12:01:31.952719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21290","created_at":"2026-07-05T12:01:31.952719+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2QABSZPABW5","created_at":"2026-07-05T12:01:31.952719+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2QABSZPABW52JNW","created_at":"2026-07-05T12:01:31.952719+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2QABSZP","created_at":"2026-07-05T12:01:31.952719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11864","citing_title":"CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08083","citing_title":"Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14564","citing_title":"MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6","json":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6.json","graph_json":"https://pith.science/api/pith-number/Q2QABSZPABW52JNWP65SWMEBT6/graph.json","events_json":"https://pith.science/api/pith-number/Q2QABSZPABW52JNWP65SWMEBT6/events.json","paper":"https://pith.science/paper/Q2QABSZP"},"agent_actions":{"view_html":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6","download_json":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6.json","view_paper":"https://pith.science/paper/Q2QABSZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21290&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2QABSZPABW52JNWP65SWMEBT6/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2QABSZPABW52JNWP65SWMEBT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6/action/storage_attestation","attest_author":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6/action/author_attestation","sign_citation":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6/action/citation_signature","submit_replication":"https://pith.science/pith/Q2QABSZPABW52JNWP65SWMEBT6/action/replication_record"}},"created_at":"2026-07-05T12:01:31.952719+00:00","updated_at":"2026-07-05T12:01:31.952719+00:00"}