{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AA7HS6E4H24HJWNPHZ546LBQWF","short_pith_number":"pith:AA7HS6E4","schema_version":"1.0","canonical_sha256":"003e79789c3eb874d9af3e7bcf2c30b17e0c3e26c1c790e1bfd194f5ea3a8a69","source":{"kind":"arxiv","id":"2202.03772","version":3},"attestation_state":"computed","paper":{"title":"Particle Transformer for Jet Tagging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex","physics.data-an"],"primary_cat":"hep-ph","authors_text":"Congqiao Li, Huilin Qu, Sitian Qian","submitted_at":"2022-02-08T10:36:29Z","abstract_excerpt":"Jet tagging is a critical yet challenging classification task in particle physics. While deep learning has transformed jet tagging and significantly improved performance, the lack of a large-scale public dataset impedes further enhancement. In this work, we present JetClass, a new comprehensive dataset for jet tagging. The JetClass dataset consists of 100 M jets, about two orders of magnitude larger than existing public datasets. A total of 10 types of jets are simulated, including several types unexplored for tagging so far. Based on the large dataset, we propose a new Transformer-based archi"},"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":"2202.03772","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ph","submitted_at":"2022-02-08T10:36:29Z","cross_cats_sorted":["cs.LG","hep-ex","physics.data-an"],"title_canon_sha256":"72a9019c40e34ba9726d8e5e8cd4feb2879623feb246aa4b00cc461d28c8482c","abstract_canon_sha256":"cf68019d94dd66694f6da03b3e7d6bcc77b5c8d4cb91723f8d517c1503f1cc0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:23.736259Z","signature_b64":"jLESkembj67HrQuRAMlUwvlpfxRQ/msWJ+HUs3W0urVNfnrMuQfx7NFN4I84UP/2yFTuLouhymWAZnqjE/jxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"003e79789c3eb874d9af3e7bcf2c30b17e0c3e26c1c790e1bfd194f5ea3a8a69","last_reissued_at":"2026-07-05T07:38:23.735678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:23.735678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Particle Transformer for Jet Tagging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex","physics.data-an"],"primary_cat":"hep-ph","authors_text":"Congqiao Li, Huilin Qu, Sitian Qian","submitted_at":"2022-02-08T10:36:29Z","abstract_excerpt":"Jet tagging is a critical yet challenging classification task in particle physics. While deep learning has transformed jet tagging and significantly improved performance, the lack of a large-scale public dataset impedes further enhancement. In this work, we present JetClass, a new comprehensive dataset for jet tagging. The JetClass dataset consists of 100 M jets, about two orders of magnitude larger than existing public datasets. A total of 10 types of jets are simulated, including several types unexplored for tagging so far. Based on the large dataset, we propose a new Transformer-based archi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03772","kind":"arxiv","version":3},"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/2202.03772/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":"2202.03772","created_at":"2026-07-05T07:38:23.735748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03772v3","created_at":"2026-07-05T07:38:23.735748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03772","created_at":"2026-07-05T07:38:23.735748+00:00"},{"alias_kind":"pith_short_12","alias_value":"AA7HS6E4H24H","created_at":"2026-07-05T07:38:23.735748+00:00"},{"alias_kind":"pith_short_16","alias_value":"AA7HS6E4H24HJWNP","created_at":"2026-07-05T07:38:23.735748+00:00"},{"alias_kind":"pith_short_8","alias_value":"AA7HS6E4","created_at":"2026-07-05T07:38:23.735748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.05762","citing_title":"Articulating Assumptions in AI-Generated Scientific Analyses through Task Decomposition","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06775","citing_title":"Data Preservation in High Energy Physics: Global Report 2026","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24637","citing_title":"Application of Deep Learning to Jet Charge Discrimination","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21790","citing_title":"What Do Lorentz-Equivariant Jet Taggers Learn?","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18460","citing_title":"ParticleTransformer is all you need for reconstructing hadronic tau leptons","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17500","citing_title":"Reconfigurable Computing Challenge: Transformer for Jet Tagging on Versal AI Engines","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02225","citing_title":"Heavy-Flavor Electron Classification Using Hadronic Environment as Point Cloud","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23791","citing_title":"One Generator, Any Process: LLM-Conditioning for the LHC","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18460","citing_title":"ParticleTransformer is all you need for reconstructing hadronic tau leptons","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26821","citing_title":"Particle-Lund Multimodality in Jet Taggers","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00224","citing_title":"An AI-ready, Polarized Electron-Positron Collision Dataset","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11259","citing_title":"Comprehensive Mass Predictions: From Triply Heavy Baryons to Pentaquarks","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2303.14511","citing_title":"Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surface","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03258","citing_title":"IAFormer: Interaction-Aware Transformer network for collider data analysis","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21789","citing_title":"Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23641","citing_title":"Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15910","citing_title":"Geometric algebra as the input language of collider foundation models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18382","citing_title":"Probing SMEFT Operators through $t\\bar{t}t\\bar{t}$ Production with Hyper-Graph Neural Networks at the LHC","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21042","citing_title":"What exactly did the Transformer learn from our physics data?","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11783","citing_title":"Learning from all particles in high-energy collisions","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2508.19190","citing_title":"Hits to Higgs: Hit-Level Higgs Classification from Raw LHC Detector Data Using Higgsformer","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07420","citing_title":"KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12229","citing_title":"Open LHC Monte Carlo Event Generation","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27044","citing_title":"Improved results on Higgs boson pair production in the 4b final state","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF","json":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF.json","graph_json":"https://pith.science/api/pith-number/AA7HS6E4H24HJWNPHZ546LBQWF/graph.json","events_json":"https://pith.science/api/pith-number/AA7HS6E4H24HJWNPHZ546LBQWF/events.json","paper":"https://pith.science/paper/AA7HS6E4"},"agent_actions":{"view_html":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF","download_json":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF.json","view_paper":"https://pith.science/paper/AA7HS6E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03772&json=true","fetch_graph":"https://pith.science/api/pith-number/AA7HS6E4H24HJWNPHZ546LBQWF/graph.json","fetch_events":"https://pith.science/api/pith-number/AA7HS6E4H24HJWNPHZ546LBQWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF/action/storage_attestation","attest_author":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF/action/author_attestation","sign_citation":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF/action/citation_signature","submit_replication":"https://pith.science/pith/AA7HS6E4H24HJWNPHZ546LBQWF/action/replication_record"}},"created_at":"2026-07-05T07:38:23.735748+00:00","updated_at":"2026-07-05T07:38:23.735748+00:00"}