{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BHA6VFQJQWGM6LBZZQI2UUOIEF","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":"198cd6c559fd89f084a4d0f3ac9802d176d768a4a423fb84dae1f6358a9ddd3a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T12:54:17Z","title_canon_sha256":"63b7092874ea1dbf03749afd9770b345c35301976749c102b1bca78b6d2dab7f"},"schema_version":"1.0","source":{"id":"2502.18473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18473","created_at":"2026-07-05T10:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18473v1","created_at":"2026-07-05T10:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18473","created_at":"2026-07-05T10:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"BHA6VFQJQWGM","created_at":"2026-07-05T10:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"BHA6VFQJQWGM6LBZ","created_at":"2026-07-05T10:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"BHA6VFQJ","created_at":"2026-07-05T10:19:58Z"}],"graph_snapshots":[{"event_id":"sha256:d17c5e0b958fec7fb4a2fbd098191f0936f1f3ac811941bdc481f94a52ae0a42","target":"graph","created_at":"2026-07-05T10:19:58Z","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/2502.18473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To evaluate large language models (LLMs) for code, research has used manually created unit test-based benchmarks. However, these tests are often inadequate, missing corner cases and other implementation-specific oddities. This work introduces ProbeGen, a whitebox method that takes two or more executable pieces of code and searches for counterexamples to their equivalence. Comparing code semantics requires a deep understanding of code. We demonstrate that LLMs with execution feedback perform well at this task. In a common code synthesis benchmark, ProbeGen disproves 18% of samples considered eq","authors_text":"Miltiadis Allamanis, Pengcheng Yin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T12:54:17Z","title":"Disproving Program Equivalence with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18473","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":"sha256:6ca7b27e8352318b5a64f957cf7369993b9d820805b1f0e8b8576fe6a24fb94d","target":"record","created_at":"2026-07-05T10:19:58Z","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":"198cd6c559fd89f084a4d0f3ac9802d176d768a4a423fb84dae1f6358a9ddd3a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T12:54:17Z","title_canon_sha256":"63b7092874ea1dbf03749afd9770b345c35301976749c102b1bca78b6d2dab7f"},"schema_version":"1.0","source":{"id":"2502.18473","kind":"arxiv","version":1}},"canonical_sha256":"09c1ea9609858ccf2c39cc11aa51c82146a9c1377c557997158063f1f2eab0c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09c1ea9609858ccf2c39cc11aa51c82146a9c1377c557997158063f1f2eab0c2","first_computed_at":"2026-07-05T10:19:58.379104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:58.379104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GnZhhpyZQ7h/o//4WXdvyFPysJL0hZYpUdWIxOvCE+PZJyw7ysjKFP9MJDsFFMnd1lf8xhQQJFNPXoNPuNJ4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:58.379559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ca7b27e8352318b5a64f957cf7369993b9d820805b1f0e8b8576fe6a24fb94d","sha256:d17c5e0b958fec7fb4a2fbd098191f0936f1f3ac811941bdc481f94a52ae0a42"],"state_sha256":"ee950715c5ee550a9153d37ff7038acaa5b157af25834e84c2677e8f9af10b54"}