{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KUTLYBKMNJVWSPVLDKFGLLVQRZ","short_pith_number":"pith:KUTLYBKM","schema_version":"1.0","canonical_sha256":"5526bc054c6a6b693eab1a8a65aeb08e780e1c69f900d0ff245846f15267eeae","source":{"kind":"arxiv","id":"2403.07066","version":2},"attestation_state":"computed","paper":{"title":"Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex"],"primary_cat":"hep-ph","authors_text":"Benedikt Maier, Jeffrey Krupa, Michael Kagan, Nathaniel Woodward, Philip Harris","submitted_at":"2024-03-11T18:00:47Z","abstract_excerpt":"Self-Supervised Learning (SSL) is at the core of training modern large machine learning models, providing a scheme for learning powerful representations that can be used in a variety of downstream tasks. However, SSL strategies must be adapted to the type of training data and downstream tasks required. We propose RS3L (\"Re-simulation-based self-supervised representation learning\"), a novel simulation-based SSL strategy that employs a method of re-simulation to drive data augmentation for contrastive learning in the physical sciences, particularly, in fields that rely on stochastic simulators. "},"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":"2403.07066","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ph","submitted_at":"2024-03-11T18:00:47Z","cross_cats_sorted":["cs.LG","hep-ex"],"title_canon_sha256":"781c7597d6a790aa2d55caaec2b7c48d53ba80b17fe79a0c18487ba44be9eb3c","abstract_canon_sha256":"965b53bcb9612a5cbc1ea595883046b836c26133ac9c93fdc8fd785f191cfdc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:22.658439Z","signature_b64":"sLkY9MJbqO6Vm1eUl/6KTnNCuE1D1xqKBZHaCX7rN+3H7WboqZrh6fIosgWmkFGC2L59JqjmCU7oV2yxwhFOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5526bc054c6a6b693eab1a8a65aeb08e780e1c69f900d0ff245846f15267eeae","last_reissued_at":"2026-07-05T10:19:22.657864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:22.657864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex"],"primary_cat":"hep-ph","authors_text":"Benedikt Maier, Jeffrey Krupa, Michael Kagan, Nathaniel Woodward, Philip Harris","submitted_at":"2024-03-11T18:00:47Z","abstract_excerpt":"Self-Supervised Learning (SSL) is at the core of training modern large machine learning models, providing a scheme for learning powerful representations that can be used in a variety of downstream tasks. However, SSL strategies must be adapted to the type of training data and downstream tasks required. We propose RS3L (\"Re-simulation-based self-supervised representation learning\"), a novel simulation-based SSL strategy that employs a method of re-simulation to drive data augmentation for contrastive learning in the physical sciences, particularly, in fields that rely on stochastic simulators. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07066","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/2403.07066/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":"2403.07066","created_at":"2026-07-05T10:19:22.657932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07066v2","created_at":"2026-07-05T10:19:22.657932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07066","created_at":"2026-07-05T10:19:22.657932+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUTLYBKMNJVW","created_at":"2026-07-05T10:19:22.657932+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUTLYBKMNJVWSPVL","created_at":"2026-07-05T10:19:22.657932+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUTLYBKM","created_at":"2026-07-05T10:19:22.657932+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":14,"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":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ","json":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ.json","graph_json":"https://pith.science/api/pith-number/KUTLYBKMNJVWSPVLDKFGLLVQRZ/graph.json","events_json":"https://pith.science/api/pith-number/KUTLYBKMNJVWSPVLDKFGLLVQRZ/events.json","paper":"https://pith.science/paper/KUTLYBKM"},"agent_actions":{"view_html":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ","download_json":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ.json","view_paper":"https://pith.science/paper/KUTLYBKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07066&json=true","fetch_graph":"https://pith.science/api/pith-number/KUTLYBKMNJVWSPVLDKFGLLVQRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KUTLYBKMNJVWSPVLDKFGLLVQRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ/action/storage_attestation","attest_author":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ/action/author_attestation","sign_citation":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ/action/citation_signature","submit_replication":"https://pith.science/pith/KUTLYBKMNJVWSPVLDKFGLLVQRZ/action/replication_record"}},"created_at":"2026-07-05T10:19:22.657932+00:00","updated_at":"2026-07-05T10:19:22.657932+00:00"}