{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3INJFIVBTSOCKIDWWEVBYE6Q5Q","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":"3143d228284ddc33831782ce84e7b6b0bb68c50b1d047bf73d72f9f90ad3402b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-16T11:57:14Z","title_canon_sha256":"d8ed5281746f08d190852f5d192e295f0299f8de50cc0d8fd597e7d506e3b4c6"},"schema_version":"1.0","source":{"id":"2411.00005","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00005","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00005v3","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00005","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"3INJFIVBTSOC","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"3INJFIVBTSOCKIDW","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"3INJFIVB","created_at":"2026-07-05T10:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:2bb16153fff27d6066a49666c2b927ce25173f23ffcc3cac76757b94093796aa","target":"graph","created_at":"2026-07-05T10:10:45Z","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/2411.00005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown impressive performance in \\emph{code} understanding and generation, making coding tasks a key focus for researchers due to their practical applications and value as a testbed for LLM evaluation. Data synthesis and filtering techniques have been widely adopted and shown to be highly effective in this context. In this paper, we present a focused survey and taxonomy of these techniques, emphasizing recent advancements. We highlight key challenges, explore future research directions, and offer practical guidance for new researchers entering the field.","authors_text":"Cong Duy Vu Hoang, Don Dharmasiri, Duy Vu, Gioacchino Tangari, Krishnaram Kenthapadi, Long Duong, Mahdi Kazemi Moghaddam, Mark Johnson, Meng Chen, Omid Nezami, Philip Arthur, Qianyu Feng, Thanh Vu, Thien Nguyen, Yuan-Fang Li, Yu-Heng Hong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-16T11:57:14Z","title":"Mastering the Craft of Data Synthesis for CodeLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00005","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":"sha256:943f3797c6322d3a51f8ca9549f7499fab142a17a94639dfff28fdbccb9b652b","target":"record","created_at":"2026-07-05T10:10:45Z","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":"3143d228284ddc33831782ce84e7b6b0bb68c50b1d047bf73d72f9f90ad3402b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-16T11:57:14Z","title_canon_sha256":"d8ed5281746f08d190852f5d192e295f0299f8de50cc0d8fd597e7d506e3b4c6"},"schema_version":"1.0","source":{"id":"2411.00005","kind":"arxiv","version":3}},"canonical_sha256":"da1a92a2a19c9c252076b12a1c13d0ec173e48ffa12ba19a2580d57eca453ec4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da1a92a2a19c9c252076b12a1c13d0ec173e48ffa12ba19a2580d57eca453ec4","first_computed_at":"2026-07-05T10:10:45.755180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:45.755180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7C6rUTWsm+se9H2otjISYxtOik2mWoVsImjbyvgYtuenZ2AMIpLrYv67L7QJEqj4fPf4WN/F4X0O+ZyAauVdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:45.755712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00005","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:943f3797c6322d3a51f8ca9549f7499fab142a17a94639dfff28fdbccb9b652b","sha256:2bb16153fff27d6066a49666c2b927ce25173f23ffcc3cac76757b94093796aa"],"state_sha256":"061cc41f2577a5c75081f6e0e70f86a34d2b4231b30ff3f4017f92c71baad5e7"}