{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BI2VWKU2S67B7QRYAOOHGJVND7","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":"47ba08cfaaa58ca40eecdbc739f048a5c345344952c2f916ce99f49998e4dc37","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:31:23Z","title_canon_sha256":"1ee746f5d85e6a1163e5c523947cbf33f1362e1788d2f8484d52222a12bc9dea"},"schema_version":"1.0","source":{"id":"2410.16165","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16165","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16165v2","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16165","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"BI2VWKU2S67B","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"BI2VWKU2S67B7QRY","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"BI2VWKU2","created_at":"2026-07-05T09:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:2e55250a952d87afecacee5b24173b6295c4a62c6ab9d726262201ccaa4e5418","target":"graph","created_at":"2026-07-05T09:30:22Z","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/2410.16165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploring the predictive capabilities of language models in material science is an ongoing interest. This study investigates the application of language model embeddings to enhance material property prediction in materials science. By evaluating various contextual embedding methods and pre-trained models, including Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformers (GPT), we demonstrate that domain-specific models, particularly MatBERT significantly outperform general-purpose models in extracting implicit knowledge from compound names and mat","authors_text":"Bram Hoex, Chunyu Kit, Nan Wu, Tong Xie, Wenjie Zhang, Yuwei Wan","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:31:23Z","title":"From Tokens to Materials: Leveraging Language Models for Scientific Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16165","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":"sha256:558508975a522a2877c8d4e06eb2a968a5c7978649e02ceb9ce8fde808edae97","target":"record","created_at":"2026-07-05T09:30:22Z","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":"47ba08cfaaa58ca40eecdbc739f048a5c345344952c2f916ce99f49998e4dc37","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:31:23Z","title_canon_sha256":"1ee746f5d85e6a1163e5c523947cbf33f1362e1788d2f8484d52222a12bc9dea"},"schema_version":"1.0","source":{"id":"2410.16165","kind":"arxiv","version":2}},"canonical_sha256":"0a355b2a9a97be1fc238039c7326ad1ff051849dbfb1b71a08c825b4b576e85b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a355b2a9a97be1fc238039c7326ad1ff051849dbfb1b71a08c825b4b576e85b","first_computed_at":"2026-07-05T09:30:22.563311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:22.563311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iBvdTWK+lQIzAANGE/rgvj4+WXBE+XomJ7FWKuGcQ2f/yRuf6QviceQ0afl/XtdjvfEGRadZHEikqkoCW7SeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:22.563815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16165","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:558508975a522a2877c8d4e06eb2a968a5c7978649e02ceb9ce8fde808edae97","sha256:2e55250a952d87afecacee5b24173b6295c4a62c6ab9d726262201ccaa4e5418"],"state_sha256":"88d72cd49ce354bfef0e5f508e514dfde7abc4a5295ef229be211ca590432946"}