{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VMORGDUD5KSKBFO2WG47FNOWP7","short_pith_number":"pith:VMORGDUD","schema_version":"1.0","canonical_sha256":"ab1d130e83eaa4a095dab1b9f2b5d67fd12cc7f0276115dd47f4d3cfcb91177a","source":{"kind":"arxiv","id":"2409.05556","version":1},"attestation_state":"computed","paper":{"title":"SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.mtrl-sci","cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alireza Ghafarollahi, Markus J. Buehler","submitted_at":"2024-09-09T12:25:10Z","abstract_excerpt":"A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data. In this work, we present SciAgents, an approach that leverages three core concepts: (1) the use of large-scale ontological knowledge graphs to organize and interconnect diverse scientific concepts, (2) a suite of large language models (LLMs) and data retrieval tools, and (3) multi-agent systems with in-situ learning capabilities. Applied to "},"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":"2409.05556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-09T12:25:10Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.mtrl-sci","cs.CL","cs.LG"],"title_canon_sha256":"7d18a5ca088f32e5818e7f260d3353c0953778a5fb140c5b876fcdde630142b6","abstract_canon_sha256":"d077c43a8b06063410709508aa2c53695745c3b278b7bd22cc5711122ac05523"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:51.045432Z","signature_b64":"fUdGs4UmafAV/mk+5wp4lXaaKw/oVC+5Vb95eIYCFNsVNXk/UKCjYMEx0i/KGk/i713rkwNDkrRM6rWOnbEGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab1d130e83eaa4a095dab1b9f2b5d67fd12cc7f0276115dd47f4d3cfcb91177a","last_reissued_at":"2026-07-05T09:04:51.044937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:51.044937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.mtrl-sci","cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Alireza Ghafarollahi, Markus J. Buehler","submitted_at":"2024-09-09T12:25:10Z","abstract_excerpt":"A key challenge in artificial intelligence is the creation of systems capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data. In this work, we present SciAgents, an approach that leverages three core concepts: (1) the use of large-scale ontological knowledge graphs to organize and interconnect diverse scientific concepts, (2) a suite of large language models (LLMs) and data retrieval tools, and (3) multi-agent systems with in-situ learning capabilities. Applied to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05556","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/2409.05556/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":"2409.05556","created_at":"2026-07-05T09:04:51.044992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05556v1","created_at":"2026-07-05T09:04:51.044992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05556","created_at":"2026-07-05T09:04:51.044992+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMORGDUD5KSK","created_at":"2026-07-05T09:04:51.044992+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMORGDUD5KSKBFO2","created_at":"2026-07-05T09:04:51.044992+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMORGDUD","created_at":"2026-07-05T09:04:51.044992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22859","citing_title":"AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19135","citing_title":"A Technical Taxonomy of LLM Agent Communication Protocols","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01233","citing_title":"Measuring the Gap Between Human and LLM Research Ideas","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14790","citing_title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2506.22653","citing_title":"URSA: The Universal Research and Scientific Agent","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13618","citing_title":"OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics Research","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27209","citing_title":"Theory Under Construction: Orchestrating Language Models for Research Software Where the Specification Evolves","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01758","citing_title":"Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01758","citing_title":"Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7","json":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7.json","graph_json":"https://pith.science/api/pith-number/VMORGDUD5KSKBFO2WG47FNOWP7/graph.json","events_json":"https://pith.science/api/pith-number/VMORGDUD5KSKBFO2WG47FNOWP7/events.json","paper":"https://pith.science/paper/VMORGDUD"},"agent_actions":{"view_html":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7","download_json":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7.json","view_paper":"https://pith.science/paper/VMORGDUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05556&json=true","fetch_graph":"https://pith.science/api/pith-number/VMORGDUD5KSKBFO2WG47FNOWP7/graph.json","fetch_events":"https://pith.science/api/pith-number/VMORGDUD5KSKBFO2WG47FNOWP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7/action/storage_attestation","attest_author":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7/action/author_attestation","sign_citation":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7/action/citation_signature","submit_replication":"https://pith.science/pith/VMORGDUD5KSKBFO2WG47FNOWP7/action/replication_record"}},"created_at":"2026-07-05T09:04:51.044992+00:00","updated_at":"2026-07-05T09:04:51.044992+00:00"}