{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HRSCC2UU6IVUZEXC2UXUFF6ABX","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":"456cce2bee0d5925130be382fd55a304f7bebc623afab5cea1e6d693e2077595","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T19:36:26Z","title_canon_sha256":"179167c7690cd4aab0cb7a3d54c03a969c7e3e2c99d807b100e5bd2dcdba7138"},"schema_version":"1.0","source":{"id":"2411.12000","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12000","created_at":"2026-07-05T09:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12000v2","created_at":"2026-07-05T09:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12000","created_at":"2026-07-05T09:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"HRSCC2UU6IVU","created_at":"2026-07-05T09:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"HRSCC2UU6IVUZEXC","created_at":"2026-07-05T09:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"HRSCC2UU","created_at":"2026-07-05T09:45:58Z"}],"graph_snapshots":[{"event_id":"sha256:9382803a61ca79a118ce696afa4fba0c311240d5100edc6bcc6afe022916d805","target":"graph","created_at":"2026-07-05T09:45:58Z","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/2411.12000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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. ","authors_text":"Bram Hoex, Chunyu Kit, Hanzhi Zhang, Imran Razzak, Shaozhou Wang, Tong Xie, Wenjie Zhang, Yuwei Wan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T19:36:26Z","title":"ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12000","kind":"arxiv","version":2},"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":"sha256:8ed7bf26e43116ab3ad150d3791a44dc988ea83d0f8a31aea100d043f7aaa633","target":"record","created_at":"2026-07-05T09:45:58Z","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":"456cce2bee0d5925130be382fd55a304f7bebc623afab5cea1e6d693e2077595","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-18T19:36:26Z","title_canon_sha256":"179167c7690cd4aab0cb7a3d54c03a969c7e3e2c99d807b100e5bd2dcdba7138"},"schema_version":"1.0","source":{"id":"2411.12000","kind":"arxiv","version":2}},"canonical_sha256":"3c64216a94f22b4c92e2d52f4297c00dcbdcf49de6961e6b6d52ee8a68665a8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c64216a94f22b4c92e2d52f4297c00dcbdcf49de6961e6b6d52ee8a68665a8f","first_computed_at":"2026-07-05T09:45:58.102623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:58.102623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QsZYjOm6cpX4BoRuZbC96QKoS0V/MS6N0dge3hcHuhT1sWkOlX/Lghgy8usa6MGTgEJWYERAAsxZch7BPJgJBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:58.103157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12000","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ed7bf26e43116ab3ad150d3791a44dc988ea83d0f8a31aea100d043f7aaa633","sha256:9382803a61ca79a118ce696afa4fba0c311240d5100edc6bcc6afe022916d805"],"state_sha256":"f647062dc6230bf3dad1548edc5898d069b1b8e2b982c8e4b342c1d73b978836"}