{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F7RZAJ4Y7JKHPLMDVFWWLVJBR6","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":"69a1278e185c885cd5e11711c8645dbd2d134ad7a5528adb1eae32c73cc39fd6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T04:05:49Z","title_canon_sha256":"326c098dee1926263a3531179c9e10cb4a62f0ebd57d1123431a2c812c107167"},"schema_version":"1.0","source":{"id":"2412.01093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01093","created_at":"2026-07-05T09:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01093v1","created_at":"2026-07-05T09:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01093","created_at":"2026-07-05T09:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"F7RZAJ4Y7JKH","created_at":"2026-07-05T09:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"F7RZAJ4Y7JKHPLMD","created_at":"2026-07-05T09:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"F7RZAJ4Y","created_at":"2026-07-05T09:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:340ff52793a399cc4564b08a9772090f28b65f2e24e1a9f364349df15d315bd3","target":"graph","created_at":"2026-07-05T09:42:53Z","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/2412.01093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Izhar Ali, Jan-Lucas Ott, Million Haileyesus, Serhiy Hnatyshyn, Vasil Hnatyshin","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T04:05:49Z","title":"Automated Extraction of Acronym-Expansion Pairs from Scientific Papers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01093","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":"sha256:69445baf6bc0d3cc9364a35e0640f2dffb99af352c146a5bb3c918104a330718","target":"record","created_at":"2026-07-05T09:42:53Z","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":"69a1278e185c885cd5e11711c8645dbd2d134ad7a5528adb1eae32c73cc39fd6","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T04:05:49Z","title_canon_sha256":"326c098dee1926263a3531179c9e10cb4a62f0ebd57d1123431a2c812c107167"},"schema_version":"1.0","source":{"id":"2412.01093","kind":"arxiv","version":1}},"canonical_sha256":"2fe3902798fa5477ad83a96d65d5218f9dcfe4121fc14d6ebbee943bfab37ea2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fe3902798fa5477ad83a96d65d5218f9dcfe4121fc14d6ebbee943bfab37ea2","first_computed_at":"2026-07-05T09:42:53.797953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:53.797953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rq1W3qka5jAgFpdde8hg4gIYDBK+LPTYhfADF752KASZNaOAhk7JjksiF9vMa/Hr0GQgEPkgYgJgq7ER+9bzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:53.798451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69445baf6bc0d3cc9364a35e0640f2dffb99af352c146a5bb3c918104a330718","sha256:340ff52793a399cc4564b08a9772090f28b65f2e24e1a9f364349df15d315bd3"],"state_sha256":"30a4dd6e8b0f0047cc0a5c7425755864d9107c077b7caad41bc7bb723072cacf"}