{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RMGZQHIFTGXT45LWHD4BTCO3GP","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":"b434e93d061fe503910ddc6703e8204aef2f3babc0d8337307b2cb6e225ed927","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-16T18:19:38Z","title_canon_sha256":"8d772355fd53b0ce9375805e92a3c6fe841836a3d374aadf26ae0fcd2da46d17"},"schema_version":"1.0","source":{"id":"2506.11021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11021","created_at":"2026-07-05T11:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11021v1","created_at":"2026-07-05T11:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11021","created_at":"2026-07-05T11:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"RMGZQHIFTGXT","created_at":"2026-07-05T11:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"RMGZQHIFTGXT45LW","created_at":"2026-07-05T11:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"RMGZQHIF","created_at":"2026-07-05T11:20:58Z"}],"graph_snapshots":[{"event_id":"sha256:ce171b7b4ad4f28562ed1506cc8d142744559aa7cca5975544642c13c3acf467","target":"graph","created_at":"2026-07-05T11:20:58Z","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/2506.11021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern code-generation LLMs can already solve a large fraction of programming problems, yet they still hallucinate subtle bugs that make their outputs unsafe for autonomous deployment. We present functional clustering, a black-box wrapper that eliminates nearly all hallucination-induced errors while providing a tunable confidence score. The wrapper samples many candidate programs, executes each on a self-generated test suite, and clusters candidates whose I/O behavior is identical; the empirical mass of the largest cluster serves as an exact confidence estimate. A single scalar threshold on th","authors_text":"Chaitanya Ravuri, Saman Amarasinghe","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-16T18:19:38Z","title":"Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11021","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":"sha256:861abbdfa7036e9735c6611cb905a71758d73f02b577f97d6ced8b3703a496ba","target":"record","created_at":"2026-07-05T11:20:58Z","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":"b434e93d061fe503910ddc6703e8204aef2f3babc0d8337307b2cb6e225ed927","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-05-16T18:19:38Z","title_canon_sha256":"8d772355fd53b0ce9375805e92a3c6fe841836a3d374aadf26ae0fcd2da46d17"},"schema_version":"1.0","source":{"id":"2506.11021","kind":"arxiv","version":1}},"canonical_sha256":"8b0d981d0599af3e757638f81989db33e01d24f5823fd52954d8b61797200a51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b0d981d0599af3e757638f81989db33e01d24f5823fd52954d8b61797200a51","first_computed_at":"2026-07-05T11:20:58.057083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:58.057083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OJ1OO+5FHDKm+Qf2SEahTykv2SLcuIghkDNyxfdIuvH8YlALerKiW/g4sH2bZZurkEh1ny5BgKWv9Fm88v9FDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:58.057561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:861abbdfa7036e9735c6611cb905a71758d73f02b577f97d6ced8b3703a496ba","sha256:ce171b7b4ad4f28562ed1506cc8d142744559aa7cca5975544642c13c3acf467"],"state_sha256":"4eb1e62dd4b506d8fa501322fe25657808a689442df4ed85c25ca31eb50986e9"}