{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ","short_pith_number":"pith:LYVEKVBV","schema_version":"1.0","canonical_sha256":"5e2a45543565b899787a03950fe61d240d775a8030d3b47a50f1f9cf5660fa9b","source":{"kind":"arxiv","id":"2202.02142","version":6},"attestation_state":"computed","paper":{"title":"Deep invariant networks with differentiable augmentation layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandre Gramfort, C\\'edric Rommel, Thomas Moreau","submitted_at":"2022-02-04T14:12:31Z","abstract_excerpt":"Designing learning systems which are invariant to certain data transformations is critical in machine learning. Practitioners can typically enforce a desired invariance on the trained model through the choice of a network architecture, e.g. using convolutions for translations, or using data augmentation. Yet, enforcing true invariance in the network can be difficult, and data invariances are not always known a piori. State-of-the-art methods for learning data augmentation policies require held-out data and are based on bilevel optimization problems, which are complex to solve and often computa"},"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":"2202.02142","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-04T14:12:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b0f138c4e5b059d62450f759da41291400e6596791e4b7a2aac54a06cb01d792","abstract_canon_sha256":"494950a69d1cb80ecf48a814870b07c4a63cb356fb4f0ae92ff7de7551563763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:53.192132Z","signature_b64":"fateLzX0YM+rf6wDHIXk1vScOS1e6wdsVk7qbwrOTUOP7AZb4KwN3ZrSh9ba5AEhdqiKi7UjWcnVh6ZJ9U/cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e2a45543565b899787a03950fe61d240d775a8030d3b47a50f1f9cf5660fa9b","last_reissued_at":"2026-07-05T05:09:53.191707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:53.191707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep invariant networks with differentiable augmentation layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandre Gramfort, C\\'edric Rommel, Thomas Moreau","submitted_at":"2022-02-04T14:12:31Z","abstract_excerpt":"Designing learning systems which are invariant to certain data transformations is critical in machine learning. Practitioners can typically enforce a desired invariance on the trained model through the choice of a network architecture, e.g. using convolutions for translations, or using data augmentation. Yet, enforcing true invariance in the network can be difficult, and data invariances are not always known a piori. State-of-the-art methods for learning data augmentation policies require held-out data and are based on bilevel optimization problems, which are complex to solve and often computa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02142","kind":"arxiv","version":6},"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/2202.02142/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":"2202.02142","created_at":"2026-07-05T05:09:53.191760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02142v6","created_at":"2026-07-05T05:09:53.191760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02142","created_at":"2026-07-05T05:09:53.191760+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYVEKVBVMW4J","created_at":"2026-07-05T05:09:53.191760+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYVEKVBVMW4JS6D2","created_at":"2026-07-05T05:09:53.191760+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYVEKVBV","created_at":"2026-07-05T05:09:53.191760+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/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ","json":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ.json","graph_json":"https://pith.science/api/pith-number/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/graph.json","events_json":"https://pith.science/api/pith-number/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/events.json","paper":"https://pith.science/paper/LYVEKVBV"},"agent_actions":{"view_html":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ","download_json":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ.json","view_paper":"https://pith.science/paper/LYVEKVBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02142&json=true","fetch_graph":"https://pith.science/api/pith-number/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/action/storage_attestation","attest_author":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/action/author_attestation","sign_citation":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/action/citation_signature","submit_replication":"https://pith.science/pith/LYVEKVBVMW4JS6D2AOKQ7ZQ5EQ/action/replication_record"}},"created_at":"2026-07-05T05:09:53.191760+00:00","updated_at":"2026-07-05T05:09:53.191760+00:00"}