{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EOZIRXBY77UGN3XS25NKN74ZE5","short_pith_number":"pith:EOZIRXBY","schema_version":"1.0","canonical_sha256":"23b288dc38ffe866eef2d75aa6ff99276ccbd49ae1df9a837368abaae0deb85d","source":{"kind":"arxiv","id":"2102.13219","version":1},"attestation_state":"computed","paper":{"title":"Learning with invariances in random features and kernel models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Song Mei, Theodor Misiakiewicz","submitted_at":"2021-02-25T23:06:21Z","abstract_excerpt":"A number of machine learning tasks entail a high degree of invariance: the data distribution does not change if we act on the data with a certain group of transformations. For instance, labels of images are invariant under translations of the images. Certain neural network architectures -- for instance, convolutional networks -- are believed to owe their success to the fact that they exploit such invariance properties. With the objective of quantifying the gain achieved by invariant architectures, we introduce two classes of models: invariant random features and invariant kernel methods. The l"},"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":"2102.13219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-25T23:06:21Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"bd16a3316ebe52ab439deb2746226e901fbf4916ae306d41bfa74752663edf63","abstract_canon_sha256":"9477611ac15390e95506d49a66d74d22ff8f03247724090be439e73f1500c847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:35.170093Z","signature_b64":"Bj46Cpa76SJV83ZdP8gFj1yUrLQS0LsYhOH1eYOX+EKBJzM+YOjNvV5YXZugHD4ZHt/EHV5VKUWYBoJ1VErBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23b288dc38ffe866eef2d75aa6ff99276ccbd49ae1df9a837368abaae0deb85d","last_reissued_at":"2026-07-05T02:18:35.169665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:35.169665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with invariances in random features and kernel models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Song Mei, Theodor Misiakiewicz","submitted_at":"2021-02-25T23:06:21Z","abstract_excerpt":"A number of machine learning tasks entail a high degree of invariance: the data distribution does not change if we act on the data with a certain group of transformations. For instance, labels of images are invariant under translations of the images. Certain neural network architectures -- for instance, convolutional networks -- are believed to owe their success to the fact that they exploit such invariance properties. With the objective of quantifying the gain achieved by invariant architectures, we introduce two classes of models: invariant random features and invariant kernel methods. The l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.13219","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/2102.13219/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":"2102.13219","created_at":"2026-07-05T02:18:35.169717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.13219v1","created_at":"2026-07-05T02:18:35.169717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.13219","created_at":"2026-07-05T02:18:35.169717+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOZIRXBY77UG","created_at":"2026-07-05T02:18:35.169717+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOZIRXBY77UGN3XS","created_at":"2026-07-05T02:18:35.169717+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOZIRXBY","created_at":"2026-07-05T02:18:35.169717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5","json":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5.json","graph_json":"https://pith.science/api/pith-number/EOZIRXBY77UGN3XS25NKN74ZE5/graph.json","events_json":"https://pith.science/api/pith-number/EOZIRXBY77UGN3XS25NKN74ZE5/events.json","paper":"https://pith.science/paper/EOZIRXBY"},"agent_actions":{"view_html":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5","download_json":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5.json","view_paper":"https://pith.science/paper/EOZIRXBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.13219&json=true","fetch_graph":"https://pith.science/api/pith-number/EOZIRXBY77UGN3XS25NKN74ZE5/graph.json","fetch_events":"https://pith.science/api/pith-number/EOZIRXBY77UGN3XS25NKN74ZE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5/action/storage_attestation","attest_author":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5/action/author_attestation","sign_citation":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5/action/citation_signature","submit_replication":"https://pith.science/pith/EOZIRXBY77UGN3XS25NKN74ZE5/action/replication_record"}},"created_at":"2026-07-05T02:18:35.169717+00:00","updated_at":"2026-07-05T02:18:35.169717+00:00"}