{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HRSCC2UU6IVUZEXC2UXUFF6ABX","short_pith_number":"pith:HRSCC2UU","schema_version":"1.0","canonical_sha256":"3c64216a94f22b4c92e2d52f4297c00dcbdcf49de6961e6b6d52ee8a68665a8f","source":{"kind":"arxiv","id":"2411.12000","version":2},"attestation_state":"computed","paper":{"title":"ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bram Hoex, Chunyu Kit, Hanzhi Zhang, Imran Razzak, Shaozhou Wang, Tong Xie, Wenjie Zhang, Yuwei Wan","submitted_at":"2024-11-18T19:36:26Z","abstract_excerpt":"Natural Language Processing (NLP) is widely used to supply summarization ability from long context to structured information. However, extracting structured knowledge from scientific text by NLP models remains a challenge because of its domain-specific nature to complex data preprocessing and the granularity of multi-layered device-level information. To address this, we introduce ByteScience, a non-profit cloud-based auto fine-tuned Large Language Model (LLM) platform, which is designed to extract structured scientific data and synthesize new scientific knowledge from vast scientific corpora. "},"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":"2411.12000","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T19:36:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"179167c7690cd4aab0cb7a3d54c03a969c7e3e2c99d807b100e5bd2dcdba7138","abstract_canon_sha256":"456cce2bee0d5925130be382fd55a304f7bebc623afab5cea1e6d693e2077595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:58.103157Z","signature_b64":"QsZYjOm6cpX4BoRuZbC96QKoS0V/MS6N0dge3hcHuhT1sWkOlX/Lghgy8usa6MGTgEJWYERAAsxZch7BPJgJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c64216a94f22b4c92e2d52f4297c00dcbdcf49de6961e6b6d52ee8a68665a8f","last_reissued_at":"2026-07-05T09:45:58.102623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:58.102623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bram Hoex, Chunyu Kit, Hanzhi Zhang, Imran Razzak, Shaozhou Wang, Tong Xie, Wenjie Zhang, Yuwei Wan","submitted_at":"2024-11-18T19:36:26Z","abstract_excerpt":"Natural Language Processing (NLP) is widely used to supply summarization ability from long context to structured information. However, extracting structured knowledge from scientific text by NLP models remains a challenge because of its domain-specific nature to complex data preprocessing and the granularity of multi-layered device-level information. To address this, we introduce ByteScience, a non-profit cloud-based auto fine-tuned Large Language Model (LLM) platform, which is designed to extract structured scientific data and synthesize new scientific knowledge from vast scientific corpora. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12000","kind":"arxiv","version":2},"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/2411.12000/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":"2411.12000","created_at":"2026-07-05T09:45:58.102689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12000v2","created_at":"2026-07-05T09:45:58.102689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12000","created_at":"2026-07-05T09:45:58.102689+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRSCC2UU6IVU","created_at":"2026-07-05T09:45:58.102689+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRSCC2UU6IVUZEXC","created_at":"2026-07-05T09:45:58.102689+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRSCC2UU","created_at":"2026-07-05T09:45:58.102689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17580","citing_title":"Context-Aware Scientific Knowledge Extraction on Linked Open Data using Large Language Models","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX","json":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX.json","graph_json":"https://pith.science/api/pith-number/HRSCC2UU6IVUZEXC2UXUFF6ABX/graph.json","events_json":"https://pith.science/api/pith-number/HRSCC2UU6IVUZEXC2UXUFF6ABX/events.json","paper":"https://pith.science/paper/HRSCC2UU"},"agent_actions":{"view_html":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX","download_json":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX.json","view_paper":"https://pith.science/paper/HRSCC2UU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12000&json=true","fetch_graph":"https://pith.science/api/pith-number/HRSCC2UU6IVUZEXC2UXUFF6ABX/graph.json","fetch_events":"https://pith.science/api/pith-number/HRSCC2UU6IVUZEXC2UXUFF6ABX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX/action/storage_attestation","attest_author":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX/action/author_attestation","sign_citation":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX/action/citation_signature","submit_replication":"https://pith.science/pith/HRSCC2UU6IVUZEXC2UXUFF6ABX/action/replication_record"}},"created_at":"2026-07-05T09:45:58.102689+00:00","updated_at":"2026-07-05T09:45:58.102689+00:00"}