{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F7RZAJ4Y7JKHPLMDVFWWLVJBR6","short_pith_number":"pith:F7RZAJ4Y","schema_version":"1.0","canonical_sha256":"2fe3902798fa5477ad83a96d65d5218f9dcfe4121fc14d6ebbee943bfab37ea2","source":{"kind":"arxiv","id":"2412.01093","version":1},"attestation_state":"computed","paper":{"title":"Automated Extraction of Acronym-Expansion Pairs from Scientific Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Izhar Ali, Jan-Lucas Ott, Million Haileyesus, Serhiy Hnatyshyn, Vasil Hnatyshin","submitted_at":"2024-12-02T04:05:49Z","abstract_excerpt":"This project addresses challenges posed by the widespread use of abbreviations and acronyms in digital texts. We propose a novel method that combines document preprocessing, regular expressions, and a large language model to identify abbreviations and map them to their corresponding expansions. The regular expressions alone are often insufficient to extract expansions, at which point our approach leverages GPT-4 to analyze the text surrounding the acronyms. By limiting the analysis to only a small portion of the surrounding text, we mitigate the risk of obtaining incorrect or multiple expansio"},"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":"2412.01093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T04:05:49Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"326c098dee1926263a3531179c9e10cb4a62f0ebd57d1123431a2c812c107167","abstract_canon_sha256":"69a1278e185c885cd5e11711c8645dbd2d134ad7a5528adb1eae32c73cc39fd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:53.798451Z","signature_b64":"Rq1W3qka5jAgFpdde8hg4gIYDBK+LPTYhfADF752KASZNaOAhk7JjksiF9vMa/Hr0GQgEPkgYgJgq7ER+9bzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe3902798fa5477ad83a96d65d5218f9dcfe4121fc14d6ebbee943bfab37ea2","last_reissued_at":"2026-07-05T09:42:53.797953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:53.797953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Extraction of Acronym-Expansion Pairs from Scientific Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Izhar Ali, Jan-Lucas Ott, Million Haileyesus, Serhiy Hnatyshyn, Vasil Hnatyshin","submitted_at":"2024-12-02T04:05:49Z","abstract_excerpt":"This project addresses challenges posed by the widespread use of abbreviations and acronyms in digital texts. We propose a novel method that combines document preprocessing, regular expressions, and a large language model to identify abbreviations and map them to their corresponding expansions. The regular expressions alone are often insufficient to extract expansions, at which point our approach leverages GPT-4 to analyze the text surrounding the acronyms. By limiting the analysis to only a small portion of the surrounding text, we mitigate the risk of obtaining incorrect or multiple expansio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01093","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/2412.01093/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":"2412.01093","created_at":"2026-07-05T09:42:53.798012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01093v1","created_at":"2026-07-05T09:42:53.798012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01093","created_at":"2026-07-05T09:42:53.798012+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7RZAJ4Y7JKH","created_at":"2026-07-05T09:42:53.798012+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7RZAJ4Y7JKHPLMD","created_at":"2026-07-05T09:42:53.798012+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7RZAJ4Y","created_at":"2026-07-05T09:42:53.798012+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/F7RZAJ4Y7JKHPLMDVFWWLVJBR6","json":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6.json","graph_json":"https://pith.science/api/pith-number/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/graph.json","events_json":"https://pith.science/api/pith-number/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/events.json","paper":"https://pith.science/paper/F7RZAJ4Y"},"agent_actions":{"view_html":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6","download_json":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6.json","view_paper":"https://pith.science/paper/F7RZAJ4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01093&json=true","fetch_graph":"https://pith.science/api/pith-number/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/graph.json","fetch_events":"https://pith.science/api/pith-number/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/action/storage_attestation","attest_author":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/action/author_attestation","sign_citation":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/action/citation_signature","submit_replication":"https://pith.science/pith/F7RZAJ4Y7JKHPLMDVFWWLVJBR6/action/replication_record"}},"created_at":"2026-07-05T09:42:53.798012+00:00","updated_at":"2026-07-05T09:42:53.798012+00:00"}