{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IUUVOERLPSUYVWDHIDWW6OV2P7","short_pith_number":"pith:IUUVOERL","canonical_record":{"source":{"id":"2005.00178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T02:08:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3439373ad814e99064406071edf03df6b89f6c1713830f7a903be7bfb5e23fff","abstract_canon_sha256":"c1d605bf15cf98c65de0e6e4a715b3a7bebc6190a4ad7de9379ff57f5c6cc4fe"},"schema_version":"1.0"},"canonical_sha256":"452957122b7ca98ad86740ed6f3aba7fe5e4bcf35893183f950a8ac66bb050df","source":{"kind":"arxiv","id":"2005.00178","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00178","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00178v1","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00178","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"IUUVOERLPSUY","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"pith_short_16","alias_value":"IUUVOERLPSUYVWDH","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"pith_short_8","alias_value":"IUUVOERL","created_at":"2026-07-05T00:59:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IUUVOERLPSUYVWDHIDWW6OV2P7","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T02:08:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3439373ad814e99064406071edf03df6b89f6c1713830f7a903be7bfb5e23fff","abstract_canon_sha256":"c1d605bf15cf98c65de0e6e4a715b3a7bebc6190a4ad7de9379ff57f5c6cc4fe"},"schema_version":"1.0"},"canonical_sha256":"452957122b7ca98ad86740ed6f3aba7fe5e4bcf35893183f950a8ac66bb050df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:38.714516Z","signature_b64":"RS1avm69TV0YaPOUfkQJN6EuqV5JfND1zveXdhuvYe8mrnjSlNFFnfp3hupzXxplfdKWoe5C+LJL3XjmqI3fBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"452957122b7ca98ad86740ed6f3aba7fe5e4bcf35893183f950a8ac66bb050df","last_reissued_at":"2026-07-05T00:59:38.714065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:38.714065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00178","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yogd+XuddR9iVWtJvK0QJhQ4qQ6xb6flnN7zwvTFvFQ4atwaiXHvezlDf6V2Y2q3IIRHR6IIAGmMTuMAQoxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T16:17:59.677531Z"},"content_sha256":"e3d5ad6f150972bebdf79c98e71f5c027635d930897c29559e3cfcea889f9fbf","schema_version":"1.0","event_id":"sha256:e3d5ad6f150972bebdf79c98e71f5c027635d930897c29559e3cfcea889f9fbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IUUVOERLPSUYVWDHIDWW6OV2P7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Benefits of Invariance in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Bloem-Reddy, Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal","submitted_at":"2020-05-01T02:08:58Z","abstract_excerpt":"Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in deep learning. While the literature contains a variety of methods to incorporate invariance into models, theoretical understanding is poor and there is no way to assess when one method should be preferred over another. In this work, we analyze the benefits and limitations of two widely used approaches in deep learning in the presence of invariance: data augmentation and feature averaging. We prove that training with da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00178","kind":"arxiv","version":1},"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/2005.00178/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QmHBrZIRN6YTihp6GCN97NWy8vJm1IS4kLNxYAZJXqLeXA5oHTWxxp6Fboaq2zJ5cPibf3Ah/4SheuDvzs1OAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T16:17:59.677904Z"},"content_sha256":"9226227e96d8dcad361c6a3f667c7aba7c5bf403da43154acbc3e946921d1ff0","schema_version":"1.0","event_id":"sha256:9226227e96d8dcad361c6a3f667c7aba7c5bf403da43154acbc3e946921d1ff0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUUVOERLPSUYVWDHIDWW6OV2P7/bundle.json","state_url":"https://pith.science/pith/IUUVOERLPSUYVWDHIDWW6OV2P7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUUVOERLPSUYVWDHIDWW6OV2P7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T16:17:59Z","links":{"resolver":"https://pith.science/pith/IUUVOERLPSUYVWDHIDWW6OV2P7","bundle":"https://pith.science/pith/IUUVOERLPSUYVWDHIDWW6OV2P7/bundle.json","state":"https://pith.science/pith/IUUVOERLPSUYVWDHIDWW6OV2P7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUUVOERLPSUYVWDHIDWW6OV2P7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IUUVOERLPSUYVWDHIDWW6OV2P7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c1d605bf15cf98c65de0e6e4a715b3a7bebc6190a4ad7de9379ff57f5c6cc4fe","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T02:08:58Z","title_canon_sha256":"3439373ad814e99064406071edf03df6b89f6c1713830f7a903be7bfb5e23fff"},"schema_version":"1.0","source":{"id":"2005.00178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00178","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00178v1","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00178","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"IUUVOERLPSUY","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"pith_short_16","alias_value":"IUUVOERLPSUYVWDH","created_at":"2026-07-05T00:59:38Z"},{"alias_kind":"pith_short_8","alias_value":"IUUVOERL","created_at":"2026-07-05T00:59:38Z"}],"graph_snapshots":[{"event_id":"sha256:9226227e96d8dcad361c6a3f667c7aba7c5bf403da43154acbc3e946921d1ff0","target":"graph","created_at":"2026-07-05T00:59:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.00178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in deep learning. While the literature contains a variety of methods to incorporate invariance into models, theoretical understanding is poor and there is no way to assess when one method should be preferred over another. In this work, we analyze the benefits and limitations of two widely used approaches in deep learning in the presence of invariance: data augmentation and feature averaging. We prove that training with da","authors_text":"Benjamin Bloem-Reddy, Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T02:08:58Z","title":"On the Benefits of Invariance in Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00178","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e3d5ad6f150972bebdf79c98e71f5c027635d930897c29559e3cfcea889f9fbf","target":"record","created_at":"2026-07-05T00:59:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c1d605bf15cf98c65de0e6e4a715b3a7bebc6190a4ad7de9379ff57f5c6cc4fe","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T02:08:58Z","title_canon_sha256":"3439373ad814e99064406071edf03df6b89f6c1713830f7a903be7bfb5e23fff"},"schema_version":"1.0","source":{"id":"2005.00178","kind":"arxiv","version":1}},"canonical_sha256":"452957122b7ca98ad86740ed6f3aba7fe5e4bcf35893183f950a8ac66bb050df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"452957122b7ca98ad86740ed6f3aba7fe5e4bcf35893183f950a8ac66bb050df","first_computed_at":"2026-07-05T00:59:38.714065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:38.714065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RS1avm69TV0YaPOUfkQJN6EuqV5JfND1zveXdhuvYe8mrnjSlNFFnfp3hupzXxplfdKWoe5C+LJL3XjmqI3fBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:38.714516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3d5ad6f150972bebdf79c98e71f5c027635d930897c29559e3cfcea889f9fbf","sha256:9226227e96d8dcad361c6a3f667c7aba7c5bf403da43154acbc3e946921d1ff0"],"state_sha256":"c29b1736c3ab0722a650d20d08d0efb2f4021a7d19062e4f3e29187e78287bb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blqwS6l6Ue6omd3pnVIeq6ADUIA0emb7QjnjP+3bGT5C94UdhrZqB5/v/fG57QOLwuIWkcgTTd9I9Nl6Jl27CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T16:17:59.680433Z","bundle_sha256":"0b3ca43162c00df011314206aa2a0b5c26e9032edfee90efc6458f7ec3362dc3"}}