{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G4IIDBV5NA2W7MZNNPBYPWJEX5","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":"cb20f2191de169254bedc5294c72d71968cec414565b93f3bcdbe69ad419edbe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-23T20:32:12Z","title_canon_sha256":"b8641150ba66b36b9ea2d6935a5eea59840528cd2cd9e33974f76024e627dac7"},"schema_version":"1.0","source":{"id":"2308.12415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12415","created_at":"2026-07-05T06:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12415v1","created_at":"2026-07-05T06:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12415","created_at":"2026-07-05T06:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"G4IIDBV5NA2W","created_at":"2026-07-05T06:44:11Z"},{"alias_kind":"pith_short_16","alias_value":"G4IIDBV5NA2W7MZN","created_at":"2026-07-05T06:44:11Z"},{"alias_kind":"pith_short_8","alias_value":"G4IIDBV5","created_at":"2026-07-05T06:44:11Z"}],"graph_snapshots":[{"event_id":"sha256:ead5eccb77fcc2753cc0eb285d8301816949731db28a3fe239a2429617e403fb","target":"graph","created_at":"2026-07-05T06:44:11Z","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/2308.12415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the most common solutions adopted by software researchers to address code generation is by training Large Language Models (LLMs) on massive amounts of source code. Although a number of studies have shown that LLMs have been effectively evaluated on popular accuracy metrics (e.g., BLEU, CodeBleu), previous research has largely overlooked the role of Causal Inference as a fundamental component of the interpretability of LLMs' performance. Existing benchmarks and datasets are meant to highlight the difference between the expected and the generated outcome, but do not take into account conf","authors_text":"Daniel Rodriguez-Cardenas, David N. Palacio, Denys Poshyvanyk, Dipin Khati, Henry Burke","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-23T20:32:12Z","title":"Benchmarking Causal Study to Interpret Large Language Models for Source Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12415","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":"sha256:00e770d0f37b4a59e9b4b0a426479f3fa5a309eb5838fe4ac560318b9cf4ffeb","target":"record","created_at":"2026-07-05T06:44:11Z","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":"cb20f2191de169254bedc5294c72d71968cec414565b93f3bcdbe69ad419edbe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-23T20:32:12Z","title_canon_sha256":"b8641150ba66b36b9ea2d6935a5eea59840528cd2cd9e33974f76024e627dac7"},"schema_version":"1.0","source":{"id":"2308.12415","kind":"arxiv","version":1}},"canonical_sha256":"37108186bd68356fb32d6bc387d924bf4b1853671b8846d4926c6afa2c64c7ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37108186bd68356fb32d6bc387d924bf4b1853671b8846d4926c6afa2c64c7ce","first_computed_at":"2026-07-05T06:44:11.996856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:11.996856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8dL8Ne++/kmNfDKlByDTfOJL2pk0ii83fgfs2MweeGIsYyaUBWDd+Rf7rNWzJnEJ7+jGYdjgaFwRi9NNSYfZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:11.997413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00e770d0f37b4a59e9b4b0a426479f3fa5a309eb5838fe4ac560318b9cf4ffeb","sha256:ead5eccb77fcc2753cc0eb285d8301816949731db28a3fe239a2429617e403fb"],"state_sha256":"88beff81ed5f3066c56c195b54f282d8658d45d32a9a1ce5359e235a352cb4ae"}