{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A2VWHYRTG3WRSJDEZ3KF4I6BOT","short_pith_number":"pith:A2VWHYRT","schema_version":"1.0","canonical_sha256":"06ab63e23336ed192464ced45e23c174fc283848ea90d9fd19a06d05c0b54a00","source":{"kind":"arxiv","id":"2409.00135","version":1},"attestation_state":"computed","paper":{"title":"HoneyComb: A Flexible LLM-Based Agent System for Materials Science","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bang Liu, Huan Zhang, Santiago Miret, Yu Song, Ziyu Hou","submitted_at":"2024-08-29T15:38:40Z","abstract_excerpt":"The emergence of specialized large language models (LLMs) has shown promise in addressing complex tasks for materials science. Many LLMs, however, often struggle with distinct complexities of material science tasks, such as materials science computational tasks, and often rely heavily on outdated implicit knowledge, leading to inaccuracies and hallucinations. To address these challenges, we introduce HoneyComb, the first LLM-based agent system specifically designed for materials science. HoneyComb leverages a novel, high-quality materials science knowledge base (MatSciKB) and a sophisticated t"},"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":"2409.00135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-29T15:38:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"405630bfc6121a0a166cae2b5e46785c27f3ae4fa4b81aa72a012a0bc0f8413c","abstract_canon_sha256":"7be16818c9a74f8bc64f6709a7cbaa40b063c8b7f9a12fa6300d33c8ca3017bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:41.404446Z","signature_b64":"trtgQMHYH/UWF0McCZsRnpWKd0UHCFLZyhLXx+yKNicag5HzSQuCMIvH9rOXf+6Bpr8KvBFdP9lIK0reke2yCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06ab63e23336ed192464ced45e23c174fc283848ea90d9fd19a06d05c0b54a00","last_reissued_at":"2026-07-05T09:01:41.403974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:41.403974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HoneyComb: A Flexible LLM-Based Agent System for Materials Science","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bang Liu, Huan Zhang, Santiago Miret, Yu Song, Ziyu Hou","submitted_at":"2024-08-29T15:38:40Z","abstract_excerpt":"The emergence of specialized large language models (LLMs) has shown promise in addressing complex tasks for materials science. Many LLMs, however, often struggle with distinct complexities of material science tasks, such as materials science computational tasks, and often rely heavily on outdated implicit knowledge, leading to inaccuracies and hallucinations. To address these challenges, we introduce HoneyComb, the first LLM-based agent system specifically designed for materials science. HoneyComb leverages a novel, high-quality materials science knowledge base (MatSciKB) and a sophisticated t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00135","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/2409.00135/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":"2409.00135","created_at":"2026-07-05T09:01:41.404026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00135v1","created_at":"2026-07-05T09:01:41.404026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00135","created_at":"2026-07-05T09:01:41.404026+00:00"},{"alias_kind":"pith_short_12","alias_value":"A2VWHYRTG3WR","created_at":"2026-07-05T09:01:41.404026+00:00"},{"alias_kind":"pith_short_16","alias_value":"A2VWHYRTG3WRSJDE","created_at":"2026-07-05T09:01:41.404026+00:00"},{"alias_kind":"pith_short_8","alias_value":"A2VWHYRT","created_at":"2026-07-05T09:01:41.404026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08723","citing_title":"From Text to Discovery: How Large Language Models Are Reshaping Research Across Scientific and Humanistic Disciplines","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04047","citing_title":"TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16307","citing_title":"Perovskite-R1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental design","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16112","citing_title":"IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18630","citing_title":"SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21011","citing_title":"ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":297,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26645","citing_title":"SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT","json":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT.json","graph_json":"https://pith.science/api/pith-number/A2VWHYRTG3WRSJDEZ3KF4I6BOT/graph.json","events_json":"https://pith.science/api/pith-number/A2VWHYRTG3WRSJDEZ3KF4I6BOT/events.json","paper":"https://pith.science/paper/A2VWHYRT"},"agent_actions":{"view_html":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT","download_json":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT.json","view_paper":"https://pith.science/paper/A2VWHYRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00135&json=true","fetch_graph":"https://pith.science/api/pith-number/A2VWHYRTG3WRSJDEZ3KF4I6BOT/graph.json","fetch_events":"https://pith.science/api/pith-number/A2VWHYRTG3WRSJDEZ3KF4I6BOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT/action/storage_attestation","attest_author":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT/action/author_attestation","sign_citation":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT/action/citation_signature","submit_replication":"https://pith.science/pith/A2VWHYRTG3WRSJDEZ3KF4I6BOT/action/replication_record"}},"created_at":"2026-07-05T09:01:41.404026+00:00","updated_at":"2026-07-05T09:01:41.404026+00:00"}