{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PFWBQQ3GIF3ST4JEF3TOA3UX4H","short_pith_number":"pith:PFWBQQ3G","schema_version":"1.0","canonical_sha256":"796c184366417729f1242ee6e06e97e1c25c8df34b450585d543b783c667514b","source":{"kind":"arxiv","id":"2505.12697","version":1},"attestation_state":"computed","paper":{"title":"Towards A Generalist Code Embedding Model Based On Massive Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chaofan Li, Defu Lian, Jianlyu Chen, Yingxia Shao, Zheng Liu","submitted_at":"2025-05-19T04:37:53Z","abstract_excerpt":"Code embedding models attract increasing attention due to the widespread popularity of retrieval-augmented generation (RAG) in software development. These models are expected to capture the rich semantic relationships inherent to code, which differ significantly from those found in text. However, existing models remain severely limited due to the scarcity of high-quality training data. In this work, we introduce \\textbf{CodeR} (\\underline{Code} \\underline{R}etrieval), a state-of-the-art embedding model for general-purpose code retrieval. The superior performance of CodeR is built upon CodeR-Pi"},"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":"2505.12697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-19T04:37:53Z","cross_cats_sorted":[],"title_canon_sha256":"693c1955aa61306cdc95de0de3af13c8a4a8f77a4b57650ce82f1e6998fabed2","abstract_canon_sha256":"43ecc2ba563b80e631b16291d827b6d062557211d27f88be71733b225436e5e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:08.441614Z","signature_b64":"Y1eYgPg87vHUysHkVqgfM5C9TwY9aSa8wg+FxCd/CebVKeoy4yS4gOPjZVMG+ZRh29vKgTgmz83Tctze+oP3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796c184366417729f1242ee6e06e97e1c25c8df34b450585d543b783c667514b","last_reissued_at":"2026-07-05T11:05:08.440929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:08.440929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards A Generalist Code Embedding Model Based On Massive Data Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chaofan Li, Defu Lian, Jianlyu Chen, Yingxia Shao, Zheng Liu","submitted_at":"2025-05-19T04:37:53Z","abstract_excerpt":"Code embedding models attract increasing attention due to the widespread popularity of retrieval-augmented generation (RAG) in software development. These models are expected to capture the rich semantic relationships inherent to code, which differ significantly from those found in text. However, existing models remain severely limited due to the scarcity of high-quality training data. In this work, we introduce \\textbf{CodeR} (\\underline{Code} \\underline{R}etrieval), a state-of-the-art embedding model for general-purpose code retrieval. The superior performance of CodeR is built upon CodeR-Pi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12697","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/2505.12697/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":"2505.12697","created_at":"2026-07-05T11:05:08.440994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12697v1","created_at":"2026-07-05T11:05:08.440994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12697","created_at":"2026-07-05T11:05:08.440994+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFWBQQ3GIF3S","created_at":"2026-07-05T11:05:08.440994+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFWBQQ3GIF3ST4JE","created_at":"2026-07-05T11:05:08.440994+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFWBQQ3G","created_at":"2026-07-05T11:05:08.440994+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/PFWBQQ3GIF3ST4JEF3TOA3UX4H","json":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H.json","graph_json":"https://pith.science/api/pith-number/PFWBQQ3GIF3ST4JEF3TOA3UX4H/graph.json","events_json":"https://pith.science/api/pith-number/PFWBQQ3GIF3ST4JEF3TOA3UX4H/events.json","paper":"https://pith.science/paper/PFWBQQ3G"},"agent_actions":{"view_html":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H","download_json":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H.json","view_paper":"https://pith.science/paper/PFWBQQ3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12697&json=true","fetch_graph":"https://pith.science/api/pith-number/PFWBQQ3GIF3ST4JEF3TOA3UX4H/graph.json","fetch_events":"https://pith.science/api/pith-number/PFWBQQ3GIF3ST4JEF3TOA3UX4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/action/storage_attestation","attest_author":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/action/author_attestation","sign_citation":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/action/citation_signature","submit_replication":"https://pith.science/pith/PFWBQQ3GIF3ST4JEF3TOA3UX4H/action/replication_record"}},"created_at":"2026-07-05T11:05:08.440994+00:00","updated_at":"2026-07-05T11:05:08.440994+00:00"}