{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GPAQLZJYYEKLHJSTWHRXGDCTGT","short_pith_number":"pith:GPAQLZJY","schema_version":"1.0","canonical_sha256":"33c105e538c114b3a653b1e3730c5334f378e4e4e795a93fa9f7e13ec117ae84","source":{"kind":"arxiv","id":"2409.12589","version":2},"attestation_state":"computed","paper":{"title":"Is Tokenization Needed for Masked Particle Modelling?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"hep-ph","authors_text":"Fran\\c{c}ois Charton, In\\^es Ochoa, Lukas Heinrich, Margarita Osadchy, Matthew Leigh, Michael Kagan, Samuel Klein, Tobias Golling","submitted_at":"2024-09-19T09:12:29Z","abstract_excerpt":"In this work, we significantly enhance masked particle modeling (MPM), a self-supervised learning scheme for constructing highly expressive representations of unordered sets relevant to developing foundation models for high-energy physics. In MPM, a model is trained to recover the missing elements of a set, a learning objective that requires no labels and can be applied directly to experimental data. We achieve significant performance improvements over previous work on MPM by addressing inefficiencies in the implementation and incorporating a more powerful decoder. We compare several pre-train"},"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":"2409.12589","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ph","submitted_at":"2024-09-19T09:12:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dfae844f67bc4659456a47c7dfcfab59915c9b08fd00805273e5041eaf5c06ed","abstract_canon_sha256":"68cdc2e84a3820c14ba54db8cd90c419bf6d2f03e52f474e3e7514ae615678ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:56.985894Z","signature_b64":"Ic1WP/g2u+mUowS/L745Q+WNhtNv3oHc6XU+ZW/SK5im9+CxxQ8jaWCglAt7iPYZFq4XCuNMY/O04FLWSc/RCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33c105e538c114b3a653b1e3730c5334f378e4e4e795a93fa9f7e13ec117ae84","last_reissued_at":"2026-07-05T09:13:56.985348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:56.985348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Tokenization Needed for Masked Particle Modelling?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"hep-ph","authors_text":"Fran\\c{c}ois Charton, In\\^es Ochoa, Lukas Heinrich, Margarita Osadchy, Matthew Leigh, Michael Kagan, Samuel Klein, Tobias Golling","submitted_at":"2024-09-19T09:12:29Z","abstract_excerpt":"In this work, we significantly enhance masked particle modeling (MPM), a self-supervised learning scheme for constructing highly expressive representations of unordered sets relevant to developing foundation models for high-energy physics. In MPM, a model is trained to recover the missing elements of a set, a learning objective that requires no labels and can be applied directly to experimental data. We achieve significant performance improvements over previous work on MPM by addressing inefficiencies in the implementation and incorporating a more powerful decoder. We compare several pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12589","kind":"arxiv","version":2},"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/2409.12589/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":"2409.12589","created_at":"2026-07-05T09:13:56.985420+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12589v2","created_at":"2026-07-05T09:13:56.985420+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12589","created_at":"2026-07-05T09:13:56.985420+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPAQLZJYYEKL","created_at":"2026-07-05T09:13:56.985420+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPAQLZJYYEKLHJST","created_at":"2026-07-05T09:13:56.985420+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPAQLZJY","created_at":"2026-07-05T09:13:56.985420+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT","json":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT.json","graph_json":"https://pith.science/api/pith-number/GPAQLZJYYEKLHJSTWHRXGDCTGT/graph.json","events_json":"https://pith.science/api/pith-number/GPAQLZJYYEKLHJSTWHRXGDCTGT/events.json","paper":"https://pith.science/paper/GPAQLZJY"},"agent_actions":{"view_html":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT","download_json":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT.json","view_paper":"https://pith.science/paper/GPAQLZJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12589&json=true","fetch_graph":"https://pith.science/api/pith-number/GPAQLZJYYEKLHJSTWHRXGDCTGT/graph.json","fetch_events":"https://pith.science/api/pith-number/GPAQLZJYYEKLHJSTWHRXGDCTGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT/action/storage_attestation","attest_author":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT/action/author_attestation","sign_citation":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT/action/citation_signature","submit_replication":"https://pith.science/pith/GPAQLZJYYEKLHJSTWHRXGDCTGT/action/replication_record"}},"created_at":"2026-07-05T09:13:56.985420+00:00","updated_at":"2026-07-05T09:13:56.985420+00:00"}