{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D7EERPSGE73EPMO7KSEPHTXSCV","short_pith_number":"pith:D7EERPSG","schema_version":"1.0","canonical_sha256":"1fc848be4627f647b1df5488f3cef2154316be17f86f557cfb6288deefc51a49","source":{"kind":"arxiv","id":"2408.15545","version":5},"attestation_state":"computed","paper":{"title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guolin Ke, Hengxing Cai, Jiaxi Zhuang, Jin Huang, Linfeng Zhang, Mingjun Xu, Sihang Li, Xiang Wang, Xiaochen Cai, Yaorui Shi","submitted_at":"2024-08-28T05:41:52Z","abstract_excerpt":"Scientific literature understanding is crucial for extracting targeted information and garnering insights, thereby significantly advancing scientific discovery. Despite the remarkable success of Large Language Models (LLMs), they face challenges in scientific literature understanding, primarily due to (1) a lack of scientific knowledge and (2) unfamiliarity with specialized scientific tasks.\n  To develop an LLM specialized in scientific literature understanding, we propose a hybrid strategy that integrates continual pre-training (CPT) and supervised fine-tuning (SFT), to simultaneously infuse "},"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":"2408.15545","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-28T05:41:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7a815110d2d18cc6f056d87b7b7d984869a2f1c54c49debeedbb84caefe6fc01","abstract_canon_sha256":"29474871778645f9391c0082c9f2c5df96890837a3073e2384bec8490dc8aac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:43.720616Z","signature_b64":"zenVwkmo1EvpXtTRmUkpFxkIyin4ZLy2Odak2Oth6CpdNqLydqlTQW/MVpVTqjFDqkhXcFkEfPiQJOhvfHyYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fc848be4627f647b1df5488f3cef2154316be17f86f557cfb6288deefc51a49","last_reissued_at":"2026-07-05T10:50:43.720125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:43.720125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Guolin Ke, Hengxing Cai, Jiaxi Zhuang, Jin Huang, Linfeng Zhang, Mingjun Xu, Sihang Li, Xiang Wang, Xiaochen Cai, Yaorui Shi","submitted_at":"2024-08-28T05:41:52Z","abstract_excerpt":"Scientific literature understanding is crucial for extracting targeted information and garnering insights, thereby significantly advancing scientific discovery. Despite the remarkable success of Large Language Models (LLMs), they face challenges in scientific literature understanding, primarily due to (1) a lack of scientific knowledge and (2) unfamiliarity with specialized scientific tasks.\n  To develop an LLM specialized in scientific literature understanding, we propose a hybrid strategy that integrates continual pre-training (CPT) and supervised fine-tuning (SFT), to simultaneously infuse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15545","kind":"arxiv","version":5},"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/2408.15545/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":"2408.15545","created_at":"2026-07-05T10:50:43.720183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15545v5","created_at":"2026-07-05T10:50:43.720183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15545","created_at":"2026-07-05T10:50:43.720183+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7EERPSGE73E","created_at":"2026-07-05T10:50:43.720183+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7EERPSGE73EPMO7","created_at":"2026-07-05T10:50:43.720183+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7EERPSG","created_at":"2026-07-05T10:50:43.720183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":100,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV","json":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV.json","graph_json":"https://pith.science/api/pith-number/D7EERPSGE73EPMO7KSEPHTXSCV/graph.json","events_json":"https://pith.science/api/pith-number/D7EERPSGE73EPMO7KSEPHTXSCV/events.json","paper":"https://pith.science/paper/D7EERPSG"},"agent_actions":{"view_html":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV","download_json":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV.json","view_paper":"https://pith.science/paper/D7EERPSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15545&json=true","fetch_graph":"https://pith.science/api/pith-number/D7EERPSGE73EPMO7KSEPHTXSCV/graph.json","fetch_events":"https://pith.science/api/pith-number/D7EERPSGE73EPMO7KSEPHTXSCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV/action/storage_attestation","attest_author":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV/action/author_attestation","sign_citation":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV/action/citation_signature","submit_replication":"https://pith.science/pith/D7EERPSGE73EPMO7KSEPHTXSCV/action/replication_record"}},"created_at":"2026-07-05T10:50:43.720183+00:00","updated_at":"2026-07-05T10:50:43.720183+00:00"}