{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FQRCSPJJIZOMNCKWSMME5CFDJ6","short_pith_number":"pith:FQRCSPJJ","schema_version":"1.0","canonical_sha256":"2c22293d29465cc6895693184e88a34f97384a260dedab10893a4d157fdbc523","source":{"kind":"arxiv","id":"2507.07887","version":1},"attestation_state":"computed","paper":{"title":"Automating MD simulations for Proteins using Large language Models: NAMD-Agent","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CE","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Achuth Chandrasekhar, Amir Barati Farimani","submitted_at":"2025-07-10T16:17:40Z","abstract_excerpt":"Molecular dynamics simulations are an essential tool in understanding protein structure, dynamics, and function at the atomic level. However, preparing high quality input files for MD simulations can be a time consuming and error prone process. In this work, we introduce an automated pipeline that leverages Large Language Models (LLMs), specifically Gemini 2.0 Flash, in conjunction with python scripting and Selenium based web automation to streamline the generation of MD input files. The pipeline exploits CHARMM GUI's comprehensive web-based interface for preparing simulation-ready inputs for "},"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":"2507.07887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T16:17:40Z","cross_cats_sorted":["cs.CE","q-bio.BM"],"title_canon_sha256":"4a52ba8443ec5597cb6777fa4aa9ea86438bd57570d6f79202e8490b4be002a2","abstract_canon_sha256":"f4a53b149689d9b21bd3c9ee6af70fd67a3c2326ac6581736966574bfa35b2e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:06.641426Z","signature_b64":"wPGU28atc7WvCuujjyaUjF98KJfypKLZsb1icjRtFFGejE8LGJapkT+KsoNW5tMwGpwc9tnOQpMp3/DZIQy1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c22293d29465cc6895693184e88a34f97384a260dedab10893a4d157fdbc523","last_reissued_at":"2026-07-05T11:35:06.640867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:06.640867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating MD simulations for Proteins using Large language Models: NAMD-Agent","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CE","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Achuth Chandrasekhar, Amir Barati Farimani","submitted_at":"2025-07-10T16:17:40Z","abstract_excerpt":"Molecular dynamics simulations are an essential tool in understanding protein structure, dynamics, and function at the atomic level. However, preparing high quality input files for MD simulations can be a time consuming and error prone process. In this work, we introduce an automated pipeline that leverages Large Language Models (LLMs), specifically Gemini 2.0 Flash, in conjunction with python scripting and Selenium based web automation to streamline the generation of MD input files. The pipeline exploits CHARMM GUI's comprehensive web-based interface for preparing simulation-ready inputs for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07887","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/2507.07887/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":"2507.07887","created_at":"2026-07-05T11:35:06.640930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07887v1","created_at":"2026-07-05T11:35:06.640930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07887","created_at":"2026-07-05T11:35:06.640930+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQRCSPJJIZOM","created_at":"2026-07-05T11:35:06.640930+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQRCSPJJIZOMNCKW","created_at":"2026-07-05T11:35:06.640930+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQRCSPJJ","created_at":"2026-07-05T11:35:06.640930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12916","citing_title":"MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04850","citing_title":"El Agente Quntur: A research collaborator agent for quantum chemistry","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02537","citing_title":"PolyJarvis: An LLM-Orchestrated Agent for Automated All-Atom Molecular Dynamics of Amorphous Homopolymers","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03205","citing_title":"From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry","ref_index":241,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09889","citing_title":"In-situ process monitoring for defect detection in wire-arc additive manufacturing: an agentic AI approach","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6","json":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6.json","graph_json":"https://pith.science/api/pith-number/FQRCSPJJIZOMNCKWSMME5CFDJ6/graph.json","events_json":"https://pith.science/api/pith-number/FQRCSPJJIZOMNCKWSMME5CFDJ6/events.json","paper":"https://pith.science/paper/FQRCSPJJ"},"agent_actions":{"view_html":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6","download_json":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6.json","view_paper":"https://pith.science/paper/FQRCSPJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07887&json=true","fetch_graph":"https://pith.science/api/pith-number/FQRCSPJJIZOMNCKWSMME5CFDJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/FQRCSPJJIZOMNCKWSMME5CFDJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6/action/storage_attestation","attest_author":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6/action/author_attestation","sign_citation":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6/action/citation_signature","submit_replication":"https://pith.science/pith/FQRCSPJJIZOMNCKWSMME5CFDJ6/action/replication_record"}},"created_at":"2026-07-05T11:35:06.640930+00:00","updated_at":"2026-07-05T11:35:06.640930+00:00"}