{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OLHRQRXA3DPU2PEGQIZGSQEFSV","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":"f8005afdbb3f4d466dcdb38324099a44fa69520c041e8d6b4dd001a0663bf506","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T05:05:56Z","title_canon_sha256":"0eb8f39b023e0f9d83766eb82568420c8c8486f936a6d9d93644d8fe5f4f0f83"},"schema_version":"1.0","source":{"id":"2403.04814","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04814","created_at":"2026-07-05T08:35:43Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04814v3","created_at":"2026-07-05T08:35:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04814","created_at":"2026-07-05T08:35:43Z"},{"alias_kind":"pith_short_12","alias_value":"OLHRQRXA3DPU","created_at":"2026-07-05T08:35:43Z"},{"alias_kind":"pith_short_16","alias_value":"OLHRQRXA3DPU2PEG","created_at":"2026-07-05T08:35:43Z"},{"alias_kind":"pith_short_8","alias_value":"OLHRQRXA","created_at":"2026-07-05T08:35:43Z"}],"graph_snapshots":[{"event_id":"sha256:eb1e6230debf0941749b1ecc1126e69d5a65cc06018ad49840c77c193670c701","target":"graph","created_at":"2026-07-05T08:35:43Z","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/2403.04814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Syntax-Aware Fill-In-the-Middle (SAFIM), a new benchmark for evaluating Large Language Models (LLMs) on the code Fill-in-the-Middle (FIM) task. This benchmark focuses on syntax-aware completions of program structures such as code blocks and conditional expressions, and includes 17,720 examples from multiple programming languages, sourced from recent code submissions after April 2022 to minimize data contamination. SAFIM provides a robust framework with various prompt designs and novel syntax-aware post-processing techniques, facilitating accurate and fair comparisons across LLMs. ","authors_text":"Alvin Cheung, Linyuan Gong, Mostafa Elhoushi, Sida Wang","cross_cats":["cs.AI","cs.LG","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T05:05:56Z","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04814","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":"sha256:980930dfb5856c6523576b164da52fe478fa6ae990d79683fbaa5ee2a8509bbf","target":"record","created_at":"2026-07-05T08:35:43Z","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":"f8005afdbb3f4d466dcdb38324099a44fa69520c041e8d6b4dd001a0663bf506","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-07T05:05:56Z","title_canon_sha256":"0eb8f39b023e0f9d83766eb82568420c8c8486f936a6d9d93644d8fe5f4f0f83"},"schema_version":"1.0","source":{"id":"2403.04814","kind":"arxiv","version":3}},"canonical_sha256":"72cf1846e0d8df4d3c868232694085955d8551775850da11b7fb92f46203c98e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72cf1846e0d8df4d3c868232694085955d8551775850da11b7fb92f46203c98e","first_computed_at":"2026-07-05T08:35:43.793948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:43.793948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u3eu15jaogE9qzOnDDZOX5odKne2HbV7ykwmdVgRXq5aDGg2JFgftJ/3Xcmj1kZJhIEueLDMGHmlAc16AWTmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:43.794410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04814","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:980930dfb5856c6523576b164da52fe478fa6ae990d79683fbaa5ee2a8509bbf","sha256:eb1e6230debf0941749b1ecc1126e69d5a65cc06018ad49840c77c193670c701"],"state_sha256":"4cc464e89308b84ce05d87263cca2a2dc4634f25f484b5068e24ba6ab6cc9631"}