{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UPQ2BLA6VRBAGL5ANCVYHMZWIY","short_pith_number":"pith:UPQ2BLA6","schema_version":"1.0","canonical_sha256":"a3e1a0ac1eac42032fa068ab83b33646266dc9369923f770e0ec5d7faac2ec94","source":{"kind":"arxiv","id":"2409.06336","version":4},"attestation_state":"computed","paper":{"title":"Towards Agentic AI on Particle Accelerators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"physics.acc-ph","authors_text":"Antonin Sulc, Hayden Hoschouer, Jason St. John, Raimund Kammering, Thorsten Hellert","submitted_at":"2024-09-10T08:47:23Z","abstract_excerpt":"As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components.\n  This approach raises some questions: What are the future applications of"},"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":"2409.06336","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.acc-ph","submitted_at":"2024-09-10T08:47:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9dfc344d290a892124ff11e777104f86fd13f245232198022fe3e4d54f067043","abstract_canon_sha256":"7d43ad4918257c381ef85921a9394a89b08b24e12f57405347cc109a16904359"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:43.405029Z","signature_b64":"NEsCq1z4/j+xv6rrmiLw/cTO7Wa9z93Vya7hqoBX0dsQExgfvLn/YZbi0j5bIZhV19ep2MHn14IKyGJzSxDYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3e1a0ac1eac42032fa068ab83b33646266dc9369923f770e0ec5d7faac2ec94","last_reissued_at":"2026-07-05T12:03:43.404456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:43.404456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Agentic AI on Particle Accelerators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"physics.acc-ph","authors_text":"Antonin Sulc, Hayden Hoschouer, Jason St. John, Raimund Kammering, Thorsten Hellert","submitted_at":"2024-09-10T08:47:23Z","abstract_excerpt":"As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized to control individual accelerator components.\n  This approach raises some questions: What are the future applications of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06336","kind":"arxiv","version":4},"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/2409.06336/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":"2409.06336","created_at":"2026-07-05T12:03:43.404529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06336v4","created_at":"2026-07-05T12:03:43.404529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06336","created_at":"2026-07-05T12:03:43.404529+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPQ2BLA6VRBA","created_at":"2026-07-05T12:03:43.404529+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPQ2BLA6VRBAGL5A","created_at":"2026-07-05T12:03:43.404529+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPQ2BLA6","created_at":"2026-07-05T12:03:43.404529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.17255","citing_title":"Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY","json":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY.json","graph_json":"https://pith.science/api/pith-number/UPQ2BLA6VRBAGL5ANCVYHMZWIY/graph.json","events_json":"https://pith.science/api/pith-number/UPQ2BLA6VRBAGL5ANCVYHMZWIY/events.json","paper":"https://pith.science/paper/UPQ2BLA6"},"agent_actions":{"view_html":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY","download_json":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY.json","view_paper":"https://pith.science/paper/UPQ2BLA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06336&json=true","fetch_graph":"https://pith.science/api/pith-number/UPQ2BLA6VRBAGL5ANCVYHMZWIY/graph.json","fetch_events":"https://pith.science/api/pith-number/UPQ2BLA6VRBAGL5ANCVYHMZWIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY/action/storage_attestation","attest_author":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY/action/author_attestation","sign_citation":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY/action/citation_signature","submit_replication":"https://pith.science/pith/UPQ2BLA6VRBAGL5ANCVYHMZWIY/action/replication_record"}},"created_at":"2026-07-05T12:03:43.404529+00:00","updated_at":"2026-07-05T12:03:43.404529+00:00"}