{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BEIA4LWELTE3VIORHSW6PGPE7P","short_pith_number":"pith:BEIA4LWE","schema_version":"1.0","canonical_sha256":"09100e2ec45cc9baa1d13cade799e4fbf3b8aee0f72543c4c53a5bc7eb09cf91","source":{"kind":"arxiv","id":"2506.04019","version":1},"attestation_state":"computed","paper":{"title":"CETBench: A Novel Dataset constructed via Transformations over Programs for Benchmarking LLMs for Code-Equivalence Checking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Dinesh Garg, Dinesh Khandelwal, Ishaan Govil, Neeva Oza, Parag Singla, Parul Gupta","submitted_at":"2025-06-04T14:47:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.04019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-06-04T14:47:14Z","cross_cats_sorted":["cs.CL","cs.LG","cs.PL"],"title_canon_sha256":"dadbaca0bd50ff05c7c6f78737c6bffdc706e9d111c8f6ea83dd2a484efb3297","abstract_canon_sha256":"b54892820118be068289052b55ccde19add2d08bae98e00a34eb3836855d5a76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:55.451431Z","signature_b64":"+E1e4J2wB8vHrC0LFArpGpWX0az4xmdhW04W5e/2GdEe5a/iFS7LXJl3xzAOdQZRV6kbx0Z3heeZ9+bzUmOyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09100e2ec45cc9baa1d13cade799e4fbf3b8aee0f72543c4c53a5bc7eb09cf91","last_reissued_at":"2026-07-05T11:15:55.451050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:55.451050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CETBench: A Novel Dataset constructed via Transformations over Programs for Benchmarking LLMs for Code-Equivalence Checking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Dinesh Garg, Dinesh Khandelwal, Ishaan Govil, Neeva Oza, Parag Singla, Parul Gupta","submitted_at":"2025-06-04T14:47:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04019","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.04019/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.04019","created_at":"2026-07-05T11:15:55.451101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04019v1","created_at":"2026-07-05T11:15:55.451101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04019","created_at":"2026-07-05T11:15:55.451101+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEIA4LWELTE3","created_at":"2026-07-05T11:15:55.451101+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEIA4LWELTE3VIOR","created_at":"2026-07-05T11:15:55.451101+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEIA4LWE","created_at":"2026-07-05T11:15:55.451101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P","json":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P.json","graph_json":"https://pith.science/api/pith-number/BEIA4LWELTE3VIORHSW6PGPE7P/graph.json","events_json":"https://pith.science/api/pith-number/BEIA4LWELTE3VIORHSW6PGPE7P/events.json","paper":"https://pith.science/paper/BEIA4LWE"},"agent_actions":{"view_html":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P","download_json":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P.json","view_paper":"https://pith.science/paper/BEIA4LWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04019&json=true","fetch_graph":"https://pith.science/api/pith-number/BEIA4LWELTE3VIORHSW6PGPE7P/graph.json","fetch_events":"https://pith.science/api/pith-number/BEIA4LWELTE3VIORHSW6PGPE7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P/action/storage_attestation","attest_author":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P/action/author_attestation","sign_citation":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P/action/citation_signature","submit_replication":"https://pith.science/pith/BEIA4LWELTE3VIORHSW6PGPE7P/action/replication_record"}},"created_at":"2026-07-05T11:15:55.451101+00:00","updated_at":"2026-07-05T11:15:55.451101+00:00"}