{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NJS3J5UX5V4OHG2UODCDY6TWOB","short_pith_number":"pith:NJS3J5UX","schema_version":"1.0","canonical_sha256":"6a65b4f697ed78e39b5470c43c7a76705dcc61814617588c8d42805cdd70b001","source":{"kind":"arxiv","id":"2408.10729","version":1},"attestation_state":"computed","paper":{"title":"Towards Efficient Large Language Models for Scientific Text: A Review","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangyan Huang, Huy Quoc To, Ming Liu","submitted_at":"2024-08-20T10:57:34Z","abstract_excerpt":"Large language models (LLMs) have ushered in a new era for processing complex information in various fields, including science. The increasing amount of scientific literature allows these models to acquire and understand scientific knowledge effectively, thus improving their performance in a wide range of tasks. Due to the power of LLMs, they require extremely expensive computational resources, intense amounts of data, and training time. Therefore, in recent years, researchers have proposed various methodologies to make scientific LLMs more affordable. The most well-known approaches align in t"},"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":"2408.10729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T10:57:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95601e00dfc3ecda525da1ae68c153297aa350ec667854584200955e863254e0","abstract_canon_sha256":"df8f00c4733067e14ffd39d55bc0c739e40d5805d39839552d236a34ad296010"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:16.580881Z","signature_b64":"/bNv3Sn8gWFAwb9UG42yFNwV62rjh24kWSNYOskMk4miJ6c1gP6pt0u4wkpAjIHi5EsPt0FVIuS4frhncg54BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a65b4f697ed78e39b5470c43c7a76705dcc61814617588c8d42805cdd70b001","last_reissued_at":"2026-07-05T08:57:16.580458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:16.580458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Efficient Large Language Models for Scientific Text: A Review","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangyan Huang, Huy Quoc To, Ming Liu","submitted_at":"2024-08-20T10:57:34Z","abstract_excerpt":"Large language models (LLMs) have ushered in a new era for processing complex information in various fields, including science. The increasing amount of scientific literature allows these models to acquire and understand scientific knowledge effectively, thus improving their performance in a wide range of tasks. Due to the power of LLMs, they require extremely expensive computational resources, intense amounts of data, and training time. Therefore, in recent years, researchers have proposed various methodologies to make scientific LLMs more affordable. The most well-known approaches align in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10729","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/2408.10729/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":"2408.10729","created_at":"2026-07-05T08:57:16.580511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10729v1","created_at":"2026-07-05T08:57:16.580511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10729","created_at":"2026-07-05T08:57:16.580511+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJS3J5UX5V4O","created_at":"2026-07-05T08:57:16.580511+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJS3J5UX5V4OHG2U","created_at":"2026-07-05T08:57:16.580511+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJS3J5UX","created_at":"2026-07-05T08:57:16.580511+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/NJS3J5UX5V4OHG2UODCDY6TWOB","json":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB.json","graph_json":"https://pith.science/api/pith-number/NJS3J5UX5V4OHG2UODCDY6TWOB/graph.json","events_json":"https://pith.science/api/pith-number/NJS3J5UX5V4OHG2UODCDY6TWOB/events.json","paper":"https://pith.science/paper/NJS3J5UX"},"agent_actions":{"view_html":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB","download_json":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB.json","view_paper":"https://pith.science/paper/NJS3J5UX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10729&json=true","fetch_graph":"https://pith.science/api/pith-number/NJS3J5UX5V4OHG2UODCDY6TWOB/graph.json","fetch_events":"https://pith.science/api/pith-number/NJS3J5UX5V4OHG2UODCDY6TWOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB/action/storage_attestation","attest_author":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB/action/author_attestation","sign_citation":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB/action/citation_signature","submit_replication":"https://pith.science/pith/NJS3J5UX5V4OHG2UODCDY6TWOB/action/replication_record"}},"created_at":"2026-07-05T08:57:16.580511+00:00","updated_at":"2026-07-05T08:57:16.580511+00:00"}