{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PCP4RUSZHGWN757TEDGFY467J4","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":"5460b54378ade90e97958da63f5b3291f0baef9e9d3150174c179678926764f9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-13T11:08:08Z","title_canon_sha256":"124432447114444b37924d396132ef9bb7b3ed63de4e0eeddc6f56f670dad72d"},"schema_version":"1.0","source":{"id":"2402.08699","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08699","created_at":"2026-07-05T08:23:17Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08699v2","created_at":"2026-07-05T08:23:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08699","created_at":"2026-07-05T08:23:17Z"},{"alias_kind":"pith_short_12","alias_value":"PCP4RUSZHGWN","created_at":"2026-07-05T08:23:17Z"},{"alias_kind":"pith_short_16","alias_value":"PCP4RUSZHGWN757T","created_at":"2026-07-05T08:23:17Z"},{"alias_kind":"pith_short_8","alias_value":"PCP4RUSZ","created_at":"2026-07-05T08:23:17Z"}],"graph_snapshots":[{"event_id":"sha256:de79bb23d8d9b747bde79b9ab20fbe09847c1bdbe9f141e3a99dd9f9a9cf2d4d","target":"graph","created_at":"2026-07-05T08:23:17Z","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/2402.08699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To evaluate code large language models (LLMs), research has relied on a few small manually curated benchmarks, such as HumanEval and MBPP, which represent a narrow part of the real-world software domains. In this work, we introduce round-trip correctness (RTC) as an alternative evaluation method. RTC allows Code LLM evaluation on a broader spectrum of real-world software domains without the need for costly human curation. RTC rests on the idea that we can ask a model to make a prediction (e.g., describe some code using natural language), feed that prediction back (e.g., synthesize code from th","authors_text":"Miltiadis Allamanis, Pengcheng Yin, Sheena Panthaplackel","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-13T11:08:08Z","title":"Unsupervised Evaluation of Code LLMs with Round-Trip Correctness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08699","kind":"arxiv","version":2},"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:d5909d2c0dccbb25e23692023145047083a4e1d6eb539f5ae9d95bc3b5a30b24","target":"record","created_at":"2026-07-05T08:23:17Z","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":"5460b54378ade90e97958da63f5b3291f0baef9e9d3150174c179678926764f9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-13T11:08:08Z","title_canon_sha256":"124432447114444b37924d396132ef9bb7b3ed63de4e0eeddc6f56f670dad72d"},"schema_version":"1.0","source":{"id":"2402.08699","kind":"arxiv","version":2}},"canonical_sha256":"789fc8d25939acdff7f320cc5c73df4f04686314ea4f230feded2921d2664b40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"789fc8d25939acdff7f320cc5c73df4f04686314ea4f230feded2921d2664b40","first_computed_at":"2026-07-05T08:23:17.958783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:17.958783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vkHOXoJIHTuB/eUxQUNyCTOxBcv7pIyni/qo+If+vegQ9S1rIutuBhCxg59rDbsxRm7Ze40EKDcUW4wTv2mHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:17.959255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08699","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5909d2c0dccbb25e23692023145047083a4e1d6eb539f5ae9d95bc3b5a30b24","sha256:de79bb23d8d9b747bde79b9ab20fbe09847c1bdbe9f141e3a99dd9f9a9cf2d4d"],"state_sha256":"9e189b941bc6211801b18ff204c1f7889b713d5f826f8f0b10aea25d02bb5b67"}