{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7PW5XVSFZIOKCYQCLIHZDGRAHK","short_pith_number":"pith:7PW5XVSF","schema_version":"1.0","canonical_sha256":"fbeddbd645ca1ca162025a0f919a203a9eb39616cafeaaef3da7786a2f6c34d4","source":{"kind":"arxiv","id":"2504.17426","version":1},"attestation_state":"computed","paper":{"title":"Towards Leveraging Large Language Model Summaries for Topic Modeling in Source Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Claudio Ferretti, Martina Saletta, Michele Carissimi","submitted_at":"2025-04-24T10:30:40Z","abstract_excerpt":"Understanding source code is a topic of great interest in the software engineering community, since it can help programmers in various tasks such as software maintenance and reuse. Recent advances in large language models (LLMs) have demonstrated remarkable program comprehension capabilities, while transformer-based topic modeling techniques offer effective ways to extract semantic information from text. This paper proposes and explores a novel approach that combines these strengths to automatically identify meaningful topics in a corpus of Python programs. Our method consists in applying topi"},"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":"2504.17426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-24T10:30:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d5021f39ff2b793d155e3414b1b99b01e705a69709ced7db2894ee1518a9494","abstract_canon_sha256":"dca363a4385cc9490c6ec542d9b72d18ec74d73752668c1d31e0691c6a658816"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:28.510401Z","signature_b64":"aclELUx+9qEY5dT3K3DMN99buoAcArhjhWVZ+LuG87ESrMPud7p4+Erkqr4qeUX86SGZ6ON29bli9qKRtaeyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbeddbd645ca1ca162025a0f919a203a9eb39616cafeaaef3da7786a2f6c34d4","last_reissued_at":"2026-07-05T10:53:28.509893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:28.509893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Leveraging Large Language Model Summaries for Topic Modeling in Source Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Claudio Ferretti, Martina Saletta, Michele Carissimi","submitted_at":"2025-04-24T10:30:40Z","abstract_excerpt":"Understanding source code is a topic of great interest in the software engineering community, since it can help programmers in various tasks such as software maintenance and reuse. Recent advances in large language models (LLMs) have demonstrated remarkable program comprehension capabilities, while transformer-based topic modeling techniques offer effective ways to extract semantic information from text. This paper proposes and explores a novel approach that combines these strengths to automatically identify meaningful topics in a corpus of Python programs. Our method consists in applying topi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17426","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/2504.17426/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":"2504.17426","created_at":"2026-07-05T10:53:28.509952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17426v1","created_at":"2026-07-05T10:53:28.509952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17426","created_at":"2026-07-05T10:53:28.509952+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PW5XVSFZIOK","created_at":"2026-07-05T10:53:28.509952+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PW5XVSFZIOKCYQC","created_at":"2026-07-05T10:53:28.509952+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PW5XVSF","created_at":"2026-07-05T10:53:28.509952+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/7PW5XVSFZIOKCYQCLIHZDGRAHK","json":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK.json","graph_json":"https://pith.science/api/pith-number/7PW5XVSFZIOKCYQCLIHZDGRAHK/graph.json","events_json":"https://pith.science/api/pith-number/7PW5XVSFZIOKCYQCLIHZDGRAHK/events.json","paper":"https://pith.science/paper/7PW5XVSF"},"agent_actions":{"view_html":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK","download_json":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK.json","view_paper":"https://pith.science/paper/7PW5XVSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17426&json=true","fetch_graph":"https://pith.science/api/pith-number/7PW5XVSFZIOKCYQCLIHZDGRAHK/graph.json","fetch_events":"https://pith.science/api/pith-number/7PW5XVSFZIOKCYQCLIHZDGRAHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK/action/storage_attestation","attest_author":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK/action/author_attestation","sign_citation":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK/action/citation_signature","submit_replication":"https://pith.science/pith/7PW5XVSFZIOKCYQCLIHZDGRAHK/action/replication_record"}},"created_at":"2026-07-05T10:53:28.509952+00:00","updated_at":"2026-07-05T10:53:28.509952+00:00"}