{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RBVDWFGDGXUT3JXB3JHSDBWWDK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"855e560d54f414238159ee2cddb1f63ffea56fe3c2e2e1c2cc424b885236992e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-11-19T16:54:45Z","title_canon_sha256":"4e61fdb1bf92d837ea0bede9e72ab0595b5b507673bf7baafa81d92b6c9b02c3"},"schema_version":"1.0","source":{"id":"2411.12644","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12644","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12644v3","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12644","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"pith_short_12","alias_value":"RBVDWFGDGXUT","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"pith_short_16","alias_value":"RBVDWFGDGXUT3JXB","created_at":"2026-07-05T11:50:29Z"},{"alias_kind":"pith_short_8","alias_value":"RBVDWFGD","created_at":"2026-07-05T11:50:29Z"}],"graph_snapshots":[{"event_id":"sha256:7faf3f514d92bef9c585fecf5007c37f516a0bde69a5fff53530b43d120f53e9","target":"graph","created_at":"2026-07-05T11:50:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.12644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the success of text retrieval in many NLP tasks, code retrieval remains a largely underexplored area. Most text retrieval systems are tailored for natural language queries, often neglecting the specific challenges of retrieving code. This gap leaves existing models unable to effectively capture the diversity of programming languages and tasks across different domains, highlighting the need for more focused research in code retrieval. To address this, we introduce CodeXEmbed, a family of large-scale code embedding models ranging from 400M to 7B parameters. Our novel training pipeline un","authors_text":"Caiming Xiong, Rui Meng, Semih Yavuz, Shafiq Joty, Silvio Savarese, Ye Liu, Yingbo Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-11-19T16:54:45Z","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12644","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:689024b3f400cb251c228172e88a8ab23d720573c34978b9cb95b2d6b1f95c56","target":"record","created_at":"2026-07-05T11:50:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"855e560d54f414238159ee2cddb1f63ffea56fe3c2e2e1c2cc424b885236992e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-11-19T16:54:45Z","title_canon_sha256":"4e61fdb1bf92d837ea0bede9e72ab0595b5b507673bf7baafa81d92b6c9b02c3"},"schema_version":"1.0","source":{"id":"2411.12644","kind":"arxiv","version":3}},"canonical_sha256":"886a3b14c335e93da6e1da4f2186d61aaf20b26d351a6273f036a0203c6ccc95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"886a3b14c335e93da6e1da4f2186d61aaf20b26d351a6273f036a0203c6ccc95","first_computed_at":"2026-07-05T11:50:29.055524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:29.055524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyYQvzrr8NTEAJgbapcwmpdh51wVT33KjKhDdhJML20SQpqqJKI59pEO7HezJWJ5TtuFHsCrjzXR5MPMZBDTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:29.055999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12644","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:689024b3f400cb251c228172e88a8ab23d720573c34978b9cb95b2d6b1f95c56","sha256:7faf3f514d92bef9c585fecf5007c37f516a0bde69a5fff53530b43d120f53e9"],"state_sha256":"8cbc9856bc1a4775df43bb2a62a33338b1c116fcf9e06fe2dabd5426f4dff4e7"}