{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BEIA4LWELTE3VIORHSW6PGPE7P","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":"b54892820118be068289052b55ccde19add2d08bae98e00a34eb3836855d5a76","cross_cats_sorted":["cs.CL","cs.LG","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-04T14:47:14Z","title_canon_sha256":"dadbaca0bd50ff05c7c6f78737c6bffdc706e9d111c8f6ea83dd2a484efb3297"},"schema_version":"1.0","source":{"id":"2506.04019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04019","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04019v1","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04019","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"pith_short_12","alias_value":"BEIA4LWELTE3","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"pith_short_16","alias_value":"BEIA4LWELTE3VIOR","created_at":"2026-07-05T11:15:55Z"},{"alias_kind":"pith_short_8","alias_value":"BEIA4LWE","created_at":"2026-07-05T11:15:55Z"}],"graph_snapshots":[{"event_id":"sha256:3f6d1a1c5e9e048a45a40bd22c10c5f1419e787b7535db21e8aba3c2ba6a2381","target":"graph","created_at":"2026-07-05T11:15:55Z","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/2506.04019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs have been extensively used for the task of automated code generation. In this work, we examine the applicability of LLMs for the related but relatively unexplored task of code-equivalence checking, i.e., given two programs, whether they are functionally equivalent or not. This is an important problem since benchmarking code equivalence can play a critical role in evaluating LLM capabilities for tasks such as code re-writing and code translation. Towards this end, we present CETBench - Code Equivalence with Transformations Benchmark, constructed via a repository of programs, where two prog","authors_text":"Dinesh Garg, Dinesh Khandelwal, Ishaan Govil, Neeva Oza, Parag Singla, Parul Gupta","cross_cats":["cs.CL","cs.LG","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-04T14:47:14Z","title":"CETBench: A Novel Dataset constructed via Transformations over Programs for Benchmarking LLMs for Code-Equivalence Checking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04019","kind":"arxiv","version":1},"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:e1edbb152a92cda0c34cc81fd9951415d0986f7d842e8de3f6cf64d8b4f582da","target":"record","created_at":"2026-07-05T11:15:55Z","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":"b54892820118be068289052b55ccde19add2d08bae98e00a34eb3836855d5a76","cross_cats_sorted":["cs.CL","cs.LG","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-04T14:47:14Z","title_canon_sha256":"dadbaca0bd50ff05c7c6f78737c6bffdc706e9d111c8f6ea83dd2a484efb3297"},"schema_version":"1.0","source":{"id":"2506.04019","kind":"arxiv","version":1}},"canonical_sha256":"09100e2ec45cc9baa1d13cade799e4fbf3b8aee0f72543c4c53a5bc7eb09cf91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09100e2ec45cc9baa1d13cade799e4fbf3b8aee0f72543c4c53a5bc7eb09cf91","first_computed_at":"2026-07-05T11:15:55.451050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:55.451050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+E1e4J2wB8vHrC0LFArpGpWX0az4xmdhW04W5e/2GdEe5a/iFS7LXJl3xzAOdQZRV6kbx0Z3heeZ9+bzUmOyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:55.451431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1edbb152a92cda0c34cc81fd9951415d0986f7d842e8de3f6cf64d8b4f582da","sha256:3f6d1a1c5e9e048a45a40bd22c10c5f1419e787b7535db21e8aba3c2ba6a2381"],"state_sha256":"fa17611b56e46bd40249241e469b8849091ebe079e43ab3ab94c4864dd1aca04"}