{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EW7MYIN5VFUNP5M5UNM2QPEGWR","short_pith_number":"pith:EW7MYIN5","schema_version":"1.0","canonical_sha256":"25becc21bda968d7f59da359a83c86b45bd030f19202cd7291660943e8bbf14c","source":{"kind":"arxiv","id":"2405.00972","version":1},"attestation_state":"computed","paper":{"title":"CACTUS: Chemistry Agent Connecting Tool-Usage to Science","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","physics.chem-ph","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Agustin Kruel, Andrew D. McNaughton, Carter R. Knutson, Gautham Ramalaxmi, Neeraj Kumar, Rohith A. Varikoti","submitted_at":"2024-05-02T03:20:08Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable potential in various domains, but they often lack the ability to access and reason over domain-specific knowledge and tools. In this paper, we introduced CACTUS (Chemistry Agent Connecting Tool-Usage to Science), an LLM-based agent that integrates cheminformatics tools to enable advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Gemma-7b, Falcon-7b, MPT-7b, Llama2-7b, and Mistral-7b, on a benchmark of thousands of chemistry questi"},"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":"2405.00972","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T03:20:08Z","cross_cats_sorted":["cs.AI","cs.LG","physics.chem-ph","q-bio.QM"],"title_canon_sha256":"ef2e39a38fb149d927112a72224d4676d751a8d25a66f27a5ba7979a5a3de23d","abstract_canon_sha256":"6d2109081ff955ccc452e7b17faabbccabdcb91f9501f6e35e0c2b514ddaec02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:21.617418Z","signature_b64":"0B0uS+K4GOTrloyCl5RSv6IuIfdEYQIMYwrMjW5ziLVJ1oYE7MPnX98wqk6OSUfwxejb9SnCGxhAs/pX4Vu0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25becc21bda968d7f59da359a83c86b45bd030f19202cd7291660943e8bbf14c","last_reissued_at":"2026-07-05T09:27:21.616921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:21.616921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CACTUS: Chemistry Agent Connecting Tool-Usage to Science","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","physics.chem-ph","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Agustin Kruel, Andrew D. McNaughton, Carter R. Knutson, Gautham Ramalaxmi, Neeraj Kumar, Rohith A. Varikoti","submitted_at":"2024-05-02T03:20:08Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable potential in various domains, but they often lack the ability to access and reason over domain-specific knowledge and tools. In this paper, we introduced CACTUS (Chemistry Agent Connecting Tool-Usage to Science), an LLM-based agent that integrates cheminformatics tools to enable advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Gemma-7b, Falcon-7b, MPT-7b, Llama2-7b, and Mistral-7b, on a benchmark of thousands of chemistry questi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00972","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/2405.00972/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":"2405.00972","created_at":"2026-07-05T09:27:21.616985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00972v1","created_at":"2026-07-05T09:27:21.616985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00972","created_at":"2026-07-05T09:27:21.616985+00:00"},{"alias_kind":"pith_short_12","alias_value":"EW7MYIN5VFUN","created_at":"2026-07-05T09:27:21.616985+00:00"},{"alias_kind":"pith_short_16","alias_value":"EW7MYIN5VFUNP5M5","created_at":"2026-07-05T09:27:21.616985+00:00"},{"alias_kind":"pith_short_8","alias_value":"EW7MYIN5","created_at":"2026-07-05T09:27:21.616985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28862","citing_title":"Molecular Lead Optimization via Agentic Tool Planning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR","json":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR.json","graph_json":"https://pith.science/api/pith-number/EW7MYIN5VFUNP5M5UNM2QPEGWR/graph.json","events_json":"https://pith.science/api/pith-number/EW7MYIN5VFUNP5M5UNM2QPEGWR/events.json","paper":"https://pith.science/paper/EW7MYIN5"},"agent_actions":{"view_html":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR","download_json":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR.json","view_paper":"https://pith.science/paper/EW7MYIN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00972&json=true","fetch_graph":"https://pith.science/api/pith-number/EW7MYIN5VFUNP5M5UNM2QPEGWR/graph.json","fetch_events":"https://pith.science/api/pith-number/EW7MYIN5VFUNP5M5UNM2QPEGWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR/action/storage_attestation","attest_author":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR/action/author_attestation","sign_citation":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR/action/citation_signature","submit_replication":"https://pith.science/pith/EW7MYIN5VFUNP5M5UNM2QPEGWR/action/replication_record"}},"created_at":"2026-07-05T09:27:21.616985+00:00","updated_at":"2026-07-05T09:27:21.616985+00:00"}