{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WJHXVTCLA7BEZSFE7YQ6XYKN2B","short_pith_number":"pith:WJHXVTCL","schema_version":"1.0","canonical_sha256":"b24f7acc4b07c24cc8a4fe21ebe14dd0701c79d53a3d7ce76c4ee7a942aa3294","source":{"kind":"arxiv","id":"2511.00215","version":2},"attestation_state":"computed","paper":{"title":"DocPrism: Multi-lingual Detection of Incorrectness Inconsistencies between Code and Documentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Caroline Lemieux, Reid Holmes, Xiaomeng Xu, Zahin Wahab","submitted_at":"2025-10-31T19:22:54Z","abstract_excerpt":"Code-documentation inconsistencies are common and undesirable: they can lead to developer misunderstandings and software defects. This paper introduces DocPrism, a lightweight multi-language, code-documentation inconsistency detection tool. DocPrism uses a standard large language model (LLM) to analyze and explain inconsistencies, and focuses on outputting incorrectness inconsistencies. Plain use of LLMs for this task yields unacceptably high inconsistency flag rates-i.e., over 90% of functions are flagged as inconsistent with their documentation. One substantial reason is that LLMs identify n"},"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":"2511.00215","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-10-31T19:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"7e09fd203bdb516ecf4505ae22a34ad925e717cf5649c88a53856cc826d5c638","abstract_canon_sha256":"988dba00cbd34dee199e14bbe15173699e6f607a2d3d888b400f5a981c5dc648"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b24f7acc4b07c24cc8a4fe21ebe14dd0701c79d53a3d7ce76c4ee7a942aa3294","last_reissued_at":"2026-07-31T00:10:10.232859Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:10.232859Z"},"graph_snapshot":{"paper":{"title":"DocPrism: Multi-lingual Detection of Incorrectness Inconsistencies between Code and Documentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Caroline Lemieux, Reid Holmes, Xiaomeng Xu, Zahin Wahab","submitted_at":"2025-10-31T19:22:54Z","abstract_excerpt":"Code-documentation inconsistencies are common and undesirable: they can lead to developer misunderstandings and software defects. This paper introduces DocPrism, a lightweight multi-language, code-documentation inconsistency detection tool. DocPrism uses a standard large language model (LLM) to analyze and explain inconsistencies, and focuses on outputting incorrectness inconsistencies. Plain use of LLMs for this task yields unacceptably high inconsistency flag rates-i.e., over 90% of functions are flagged as inconsistent with their documentation. One substantial reason is that LLMs identify n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.00215","kind":"arxiv","version":2},"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/2511.00215/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":"2511.00215","created_at":"2026-07-31T00:10:10.235237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.00215v2","created_at":"2026-07-31T00:10:10.235237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.00215","created_at":"2026-07-31T00:10:10.235237+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJHXVTCLA7BE","created_at":"2026-07-31T00:10:10.235237+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJHXVTCLA7BEZSFE","created_at":"2026-07-31T00:10:10.235237+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJHXVTCL","created_at":"2026-07-31T00:10:10.235237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.10417","citing_title":"Beyond Coverage and Kill Scores: Empirically Measuring Test Suite Behavioural Gaps","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03447","citing_title":"Measuring LLM Trust Allocation Across Conflicting Software Artifacts","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B","json":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B.json","graph_json":"https://pith.science/api/pith-number/WJHXVTCLA7BEZSFE7YQ6XYKN2B/graph.json","events_json":"https://pith.science/api/pith-number/WJHXVTCLA7BEZSFE7YQ6XYKN2B/events.json","paper":"https://pith.science/paper/WJHXVTCL"},"agent_actions":{"view_html":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B","download_json":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B.json","view_paper":"https://pith.science/paper/WJHXVTCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.00215&json=true","fetch_graph":"https://pith.science/api/pith-number/WJHXVTCLA7BEZSFE7YQ6XYKN2B/graph.json","fetch_events":"https://pith.science/api/pith-number/WJHXVTCLA7BEZSFE7YQ6XYKN2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B/action/storage_attestation","attest_author":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B/action/author_attestation","sign_citation":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B/action/citation_signature","submit_replication":"https://pith.science/pith/WJHXVTCLA7BEZSFE7YQ6XYKN2B/action/replication_record"}},"created_at":"2026-07-31T00:10:10.235237+00:00","updated_at":"2026-07-31T00:10:10.235237+00:00"}