{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IRPPFDYJCC7VKU55I3AZG2MP2D","short_pith_number":"pith:IRPPFDYJ","schema_version":"1.0","canonical_sha256":"445ef28f0910bf5553bd46c193698fd0ff381f30e5b07658c191b684386197cf","source":{"kind":"arxiv","id":"2401.13537","version":3},"attestation_state":"computed","paper":{"title":"Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex","physics.data-an"],"primary_cat":"hep-ph","authors_text":"John Andrew Raine, Lukas Heinrich, Margarita Osadchy, Matthew Leigh, Michael Kagan, Samuel Klein, Tobias Golling","submitted_at":"2024-01-24T15:46:32Z","abstract_excerpt":"We propose masked particle modeling (MPM) as a self-supervised method for learning generic, transferable, and reusable representations on unordered sets of inputs for use in high energy physics (HEP) scientific data. This work provides a novel scheme to perform masked modeling based pre-training to learn permutation invariant functions on sets. More generally, this work provides a step towards building large foundation models for HEP that can be generically pre-trained with self-supervised learning and later fine-tuned for a variety of down-stream tasks. In MPM, particles in a set are masked a"},"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":"2401.13537","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ph","submitted_at":"2024-01-24T15:46:32Z","cross_cats_sorted":["cs.LG","hep-ex","physics.data-an"],"title_canon_sha256":"aae079a697422b38ddad3886a103039171bbc950878392ef6c3ca6743a57c9bf","abstract_canon_sha256":"61164880a565d42cd98be10bc479f030206d0568f387b719da549ec9eacb14e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:32.418212Z","signature_b64":"xTK8aQkYHtZtI3yufDCCBPB6zmJ0bVhZAlH35JsYpxkFawC26AuS8xfhf8TgR86k5pVyEnl4kpJq899qETB5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"445ef28f0910bf5553bd46c193698fd0ff381f30e5b07658c191b684386197cf","last_reissued_at":"2026-07-05T08:42:32.417737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:32.417737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex","physics.data-an"],"primary_cat":"hep-ph","authors_text":"John Andrew Raine, Lukas Heinrich, Margarita Osadchy, Matthew Leigh, Michael Kagan, Samuel Klein, Tobias Golling","submitted_at":"2024-01-24T15:46:32Z","abstract_excerpt":"We propose masked particle modeling (MPM) as a self-supervised method for learning generic, transferable, and reusable representations on unordered sets of inputs for use in high energy physics (HEP) scientific data. This work provides a novel scheme to perform masked modeling based pre-training to learn permutation invariant functions on sets. More generally, this work provides a step towards building large foundation models for HEP that can be generically pre-trained with self-supervised learning and later fine-tuned for a variety of down-stream tasks. In MPM, particles in a set are masked a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13537","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/2401.13537/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":"2401.13537","created_at":"2026-07-05T08:42:32.417795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13537v3","created_at":"2026-07-05T08:42:32.417795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13537","created_at":"2026-07-05T08:42:32.417795+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRPPFDYJCC7V","created_at":"2026-07-05T08:42:32.417795+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRPPFDYJCC7VKU55","created_at":"2026-07-05T08:42:32.417795+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRPPFDYJ","created_at":"2026-07-05T08:42:32.417795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.10665","citing_title":"Pretrained Event Classification Model for High Energy Physics Analysis","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21035","citing_title":"Masked-Token Prediction for Anomaly Detection at the Large Hadron Collider","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D","json":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D.json","graph_json":"https://pith.science/api/pith-number/IRPPFDYJCC7VKU55I3AZG2MP2D/graph.json","events_json":"https://pith.science/api/pith-number/IRPPFDYJCC7VKU55I3AZG2MP2D/events.json","paper":"https://pith.science/paper/IRPPFDYJ"},"agent_actions":{"view_html":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D","download_json":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D.json","view_paper":"https://pith.science/paper/IRPPFDYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13537&json=true","fetch_graph":"https://pith.science/api/pith-number/IRPPFDYJCC7VKU55I3AZG2MP2D/graph.json","fetch_events":"https://pith.science/api/pith-number/IRPPFDYJCC7VKU55I3AZG2MP2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D/action/storage_attestation","attest_author":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D/action/author_attestation","sign_citation":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D/action/citation_signature","submit_replication":"https://pith.science/pith/IRPPFDYJCC7VKU55I3AZG2MP2D/action/replication_record"}},"created_at":"2026-07-05T08:42:32.417795+00:00","updated_at":"2026-07-05T08:42:32.417795+00:00"}