{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5MLG4HMJK2ODLGAPXI7FAAOULE","short_pith_number":"pith:5MLG4HMJ","schema_version":"1.0","canonical_sha256":"eb166e1d89569c35980fba3e5001d45922e327121dac6730e46d77d99837c0e3","source":{"kind":"arxiv","id":"2412.07867","version":1},"attestation_state":"computed","paper":{"title":"Bumblebee: Foundation Model for Particle Physics Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ph"],"primary_cat":"hep-ex","authors_text":"Andreas W. Jung, Andrew J. Wildridge, Ethan M. Colbert, Jack P. Rodgers, Miaoyuan Liu, Yao Yao","submitted_at":"2024-12-10T19:14:50Z","abstract_excerpt":"Bumblebee is a foundation model for particle physics discovery, inspired by BERT. By removing positional encodings and embedding particle 4-vectors, Bumblebee captures both generator- and reconstruction-level information while ensuring sequence-order invariance. Pre-trained on a masked task, it improves dileptonic top quark reconstruction resolution by 10-20% and excels in downstream tasks, including toponium discrimination (AUROC 0.877) and initial state classification (AUROC 0.625). The flexibility of Bumblebee makes it suitable for a wide range of particle physics applications, especially 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":"2412.07867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ex","submitted_at":"2024-12-10T19:14:50Z","cross_cats_sorted":["cs.LG","hep-ph"],"title_canon_sha256":"ca5fc926757a604f6045c9b214a81afc09d373caae6f4cbe137afa3128e9401b","abstract_canon_sha256":"19d015e610edb5891c41da26665234721df50ddeaf54d86915d2099a2bc0b2ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:40.439012Z","signature_b64":"F+rTbsoFOE6u7BwxeR4RBe0WwulgZtwuIyoS+3L7qMi454iHhWTP/6LBXIOVDN6vzN6S1xOuylw4fXwCzryrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb166e1d89569c35980fba3e5001d45922e327121dac6730e46d77d99837c0e3","last_reissued_at":"2026-07-05T09:47:40.438504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:40.438504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bumblebee: Foundation Model for Particle Physics Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ph"],"primary_cat":"hep-ex","authors_text":"Andreas W. Jung, Andrew J. Wildridge, Ethan M. Colbert, Jack P. Rodgers, Miaoyuan Liu, Yao Yao","submitted_at":"2024-12-10T19:14:50Z","abstract_excerpt":"Bumblebee is a foundation model for particle physics discovery, inspired by BERT. By removing positional encodings and embedding particle 4-vectors, Bumblebee captures both generator- and reconstruction-level information while ensuring sequence-order invariance. Pre-trained on a masked task, it improves dileptonic top quark reconstruction resolution by 10-20% and excels in downstream tasks, including toponium discrimination (AUROC 0.877) and initial state classification (AUROC 0.625). The flexibility of Bumblebee makes it suitable for a wide range of particle physics applications, especially t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07867","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/2412.07867/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":"2412.07867","created_at":"2026-07-05T09:47:40.438571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07867v1","created_at":"2026-07-05T09:47:40.438571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07867","created_at":"2026-07-05T09:47:40.438571+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MLG4HMJK2OD","created_at":"2026-07-05T09:47:40.438571+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MLG4HMJK2ODLGAP","created_at":"2026-07-05T09:47:40.438571+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MLG4HMJ","created_at":"2026-07-05T09:47:40.438571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2412.10665","citing_title":"Pretrained Event Classification Model for High Energy Physics Analysis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24775","citing_title":"Application of a Mixture of Experts-based Foundation Model to the GlueX DIRC Detector","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE","json":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE.json","graph_json":"https://pith.science/api/pith-number/5MLG4HMJK2ODLGAPXI7FAAOULE/graph.json","events_json":"https://pith.science/api/pith-number/5MLG4HMJK2ODLGAPXI7FAAOULE/events.json","paper":"https://pith.science/paper/5MLG4HMJ"},"agent_actions":{"view_html":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE","download_json":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE.json","view_paper":"https://pith.science/paper/5MLG4HMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07867&json=true","fetch_graph":"https://pith.science/api/pith-number/5MLG4HMJK2ODLGAPXI7FAAOULE/graph.json","fetch_events":"https://pith.science/api/pith-number/5MLG4HMJK2ODLGAPXI7FAAOULE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE/action/storage_attestation","attest_author":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE/action/author_attestation","sign_citation":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE/action/citation_signature","submit_replication":"https://pith.science/pith/5MLG4HMJK2ODLGAPXI7FAAOULE/action/replication_record"}},"created_at":"2026-07-05T09:47:40.438571+00:00","updated_at":"2026-07-05T09:47:40.438571+00:00"}