{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZMIVZC4L5HJ7IMQJDMX4FJQZJV","short_pith_number":"pith:ZMIVZC4L","schema_version":"1.0","canonical_sha256":"cb115c8b8be9d3f432091b2fc2a6194d50393c28001af2754d8f135c248e6bf6","source":{"kind":"arxiv","id":"2210.03773","version":1},"attestation_state":"computed","paper":{"title":"In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Grayson Jorgenson, Henry Kvinge, Jesse D. Lew, Scott Vasquez, Tegan H. Emerson, Timothy Doster","submitted_at":"2022-10-07T18:43:21Z","abstract_excerpt":"It is often said that a deep learning model is \"invariant\" to some specific type of transformation. However, what is meant by this statement strongly depends on the context in which it is made. In this paper we explore the nature of invariance and equivariance of deep learning models with the goal of better understanding the ways in which they actually capture these concepts on a formal level. We introduce a family of invariance and equivariance metrics that allows us to quantify these properties in a way that disentangles them from other metrics such as loss or accuracy. We use our metrics to"},"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":"2210.03773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T18:43:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"27c119f2b09a7cbb8f6e6f38c47d4e1b16a61ee7d0b06acdda796da017fe2a81","abstract_canon_sha256":"00047d0e67ed8fd58d5620335749e6e9b62872e782be724d9f81595dc16fc32f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:32.143470Z","signature_b64":"CXcTFCpWQUFHX30XxDNhmKQfLvW88PxApaStKjIxYN+ht12mYJhZV/Up5w8g7PKT/qygXcOZKEUPxIKONSwZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb115c8b8be9d3f432091b2fc2a6194d50393c28001af2754d8f135c248e6bf6","last_reissued_at":"2026-07-05T05:04:32.143004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:32.143004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Grayson Jorgenson, Henry Kvinge, Jesse D. Lew, Scott Vasquez, Tegan H. Emerson, Timothy Doster","submitted_at":"2022-10-07T18:43:21Z","abstract_excerpt":"It is often said that a deep learning model is \"invariant\" to some specific type of transformation. However, what is meant by this statement strongly depends on the context in which it is made. In this paper we explore the nature of invariance and equivariance of deep learning models with the goal of better understanding the ways in which they actually capture these concepts on a formal level. We introduce a family of invariance and equivariance metrics that allows us to quantify these properties in a way that disentangles them from other metrics such as loss or accuracy. We use our metrics to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03773","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/2210.03773/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":"2210.03773","created_at":"2026-07-05T05:04:32.143063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03773v1","created_at":"2026-07-05T05:04:32.143063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03773","created_at":"2026-07-05T05:04:32.143063+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMIVZC4L5HJ7","created_at":"2026-07-05T05:04:32.143063+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMIVZC4L5HJ7IMQJ","created_at":"2026-07-05T05:04:32.143063+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMIVZC4L","created_at":"2026-07-05T05:04:32.143063+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/ZMIVZC4L5HJ7IMQJDMX4FJQZJV","json":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV.json","graph_json":"https://pith.science/api/pith-number/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/graph.json","events_json":"https://pith.science/api/pith-number/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/events.json","paper":"https://pith.science/paper/ZMIVZC4L"},"agent_actions":{"view_html":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV","download_json":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV.json","view_paper":"https://pith.science/paper/ZMIVZC4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03773&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/action/storage_attestation","attest_author":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/action/author_attestation","sign_citation":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/action/citation_signature","submit_replication":"https://pith.science/pith/ZMIVZC4L5HJ7IMQJDMX4FJQZJV/action/replication_record"}},"created_at":"2026-07-05T05:04:32.143063+00:00","updated_at":"2026-07-05T05:04:32.143063+00:00"}