{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V6O2OPCVTYRZ6FRGQXFXS67OQQ","short_pith_number":"pith:V6O2OPCV","schema_version":"1.0","canonical_sha256":"af9da73c559e239f162685cb797bee84224e25e45d23f1d7ffc0ae19c157e730","source":{"kind":"arxiv","id":"2412.18773","version":2},"attestation_state":"computed","paper":{"title":"Learning Broken Symmetries with Approximate Invariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ex"],"primary_cat":"hep-ph","authors_text":"Aishik Ghosh, Daniel Whiteson, Edmund Witkowski, Gregor Kasieczka, Seth Nabat","submitted_at":"2024-12-25T04:29:04Z","abstract_excerpt":"Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized dataset, and is broken in actual data, due to asymmetries in the detector, or varying response resolution as a function of particle momentum. Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the full, broken symmetry, effectively overconstraining the response of the neural network. We propose a learning mod"},"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":"2412.18773","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-ph","submitted_at":"2024-12-25T04:29:04Z","cross_cats_sorted":["cs.LG","hep-ex"],"title_canon_sha256":"2d30978faa4526747418e0dfddb9c8b43239878f36dd6d77164c4920827674a7","abstract_canon_sha256":"c182a7c3c11bac92b14c3722967e7a4acddf94a6e3736ef35e695c2b8df67b10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:21.092710Z","signature_b64":"5CCnRFBVL9/H1bbZgrzMuw3JBdokRBQcLhQ2eY2Z23vc/5kZlZ6NrY2Dpv/4H6IsGLjIREkS3T7ZU1AhpBgQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af9da73c559e239f162685cb797bee84224e25e45d23f1d7ffc0ae19c157e730","last_reissued_at":"2026-07-05T10:44:21.092208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:21.092208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Broken Symmetries with Approximate Invariance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ex"],"primary_cat":"hep-ph","authors_text":"Aishik Ghosh, Daniel Whiteson, Edmund Witkowski, Gregor Kasieczka, Seth Nabat","submitted_at":"2024-12-25T04:29:04Z","abstract_excerpt":"Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized dataset, and is broken in actual data, due to asymmetries in the detector, or varying response resolution as a function of particle momentum. Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the full, broken symmetry, effectively overconstraining the response of the neural network. We propose a learning mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18773","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/2412.18773/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":"2412.18773","created_at":"2026-07-05T10:44:21.092268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18773v2","created_at":"2026-07-05T10:44:21.092268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18773","created_at":"2026-07-05T10:44:21.092268+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6O2OPCVTYRZ","created_at":"2026-07-05T10:44:21.092268+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6O2OPCVTYRZ6FRG","created_at":"2026-07-05T10:44:21.092268+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6O2OPCV","created_at":"2026-07-05T10:44:21.092268+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/V6O2OPCVTYRZ6FRGQXFXS67OQQ","json":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ.json","graph_json":"https://pith.science/api/pith-number/V6O2OPCVTYRZ6FRGQXFXS67OQQ/graph.json","events_json":"https://pith.science/api/pith-number/V6O2OPCVTYRZ6FRGQXFXS67OQQ/events.json","paper":"https://pith.science/paper/V6O2OPCV"},"agent_actions":{"view_html":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ","download_json":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ.json","view_paper":"https://pith.science/paper/V6O2OPCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18773&json=true","fetch_graph":"https://pith.science/api/pith-number/V6O2OPCVTYRZ6FRGQXFXS67OQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/V6O2OPCVTYRZ6FRGQXFXS67OQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ/action/storage_attestation","attest_author":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ/action/author_attestation","sign_citation":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ/action/citation_signature","submit_replication":"https://pith.science/pith/V6O2OPCVTYRZ6FRGQXFXS67OQQ/action/replication_record"}},"created_at":"2026-07-05T10:44:21.092268+00:00","updated_at":"2026-07-05T10:44:21.092268+00:00"}