{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IFBHADW2APERPJNBZYBYOQV4DC","short_pith_number":"pith:IFBHADW2","schema_version":"1.0","canonical_sha256":"4142700eda03c917a5a1ce038742bc188659cc5a984a5016fcfbe7ec3a2e288d","source":{"kind":"arxiv","id":"2310.08511","version":1},"attestation_state":"computed","paper":{"title":"HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"primary_cat":"cs.CL","authors_text":"Bang Liu, Huan Zhang, Santiago Miret, Yu Song","submitted_at":"2023-10-12T17:06:19Z","abstract_excerpt":"We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee). MatSci-Instruct helps alleviate the scarcity of relevant, high-quality materials science textual data available in the open literature, and HoneyBee is the first billion-parameter language model specialized to materials science. In MatSci-Instruct we improve the trustworthiness of generated data by prompting multiple commercially available large language models for generation with an"},"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":"2310.08511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T17:06:19Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"46be301ef6219f598174aea41edd9e6497c530e0147e8aaaacad8552ec31b00c","abstract_canon_sha256":"1ce9aa2b5231c3916166cd14327f7b1f953df53c83f52f6efdc33674728658a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:16.645436Z","signature_b64":"O6UHTgKPRmS8VEgrUayXUxxht++XBdMZPVmcEfL8YJyctADKRVlKvSo/GFTMgT10Cfwqx3Dfs2TBffRDK6IeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4142700eda03c917a5a1ce038742bc188659cc5a984a5016fcfbe7ec3a2e288d","last_reissued_at":"2026-07-05T07:00:16.644992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:16.644992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"primary_cat":"cs.CL","authors_text":"Bang Liu, Huan Zhang, Santiago Miret, Yu Song","submitted_at":"2023-10-12T17:06:19Z","abstract_excerpt":"We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee). MatSci-Instruct helps alleviate the scarcity of relevant, high-quality materials science textual data available in the open literature, and HoneyBee is the first billion-parameter language model specialized to materials science. In MatSci-Instruct we improve the trustworthiness of generated data by prompting multiple commercially available large language models for generation with an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08511","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/2310.08511/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":"2310.08511","created_at":"2026-07-05T07:00:16.645049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08511v1","created_at":"2026-07-05T07:00:16.645049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08511","created_at":"2026-07-05T07:00:16.645049+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFBHADW2APER","created_at":"2026-07-05T07:00:16.645049+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFBHADW2APERPJNB","created_at":"2026-07-05T07:00:16.645049+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFBHADW2","created_at":"2026-07-05T07:00:16.645049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20743","citing_title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC","json":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC.json","graph_json":"https://pith.science/api/pith-number/IFBHADW2APERPJNBZYBYOQV4DC/graph.json","events_json":"https://pith.science/api/pith-number/IFBHADW2APERPJNBZYBYOQV4DC/events.json","paper":"https://pith.science/paper/IFBHADW2"},"agent_actions":{"view_html":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC","download_json":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC.json","view_paper":"https://pith.science/paper/IFBHADW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08511&json=true","fetch_graph":"https://pith.science/api/pith-number/IFBHADW2APERPJNBZYBYOQV4DC/graph.json","fetch_events":"https://pith.science/api/pith-number/IFBHADW2APERPJNBZYBYOQV4DC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/action/storage_attestation","attest_author":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/action/author_attestation","sign_citation":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/action/citation_signature","submit_replication":"https://pith.science/pith/IFBHADW2APERPJNBZYBYOQV4DC/action/replication_record"}},"created_at":"2026-07-05T07:00:16.645049+00:00","updated_at":"2026-07-05T07:00:16.645049+00:00"}