{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:U3XSLDIOOO3VW5SEDI3DCIMIT3","short_pith_number":"pith:U3XSLDIO","schema_version":"1.0","canonical_sha256":"a6ef258d0e73b75b76441a363121889ef411361d541c66ae009057f73b156d18","source":{"kind":"arxiv","id":"2007.02933","version":3},"attestation_state":"computed","paper":{"title":"Meta-Learning Symmetries by Reparameterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Allan Zhou, Chelsea Finn, Tom Knowles","submitted_at":"2020-07-06T17:59:54Z","abstract_excerpt":"Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only works when practitioners know the symmetries of the task and can manually construct an architecture with the corresponding equivariances. Our goal is an approach for learning equivariances from data, without needing to design custom task-specific architectures. We present a method for learning and encoding equivariances into networks by learning correspondin"},"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":"2007.02933","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-06T17:59:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2047a21e1a87fe295c7b93535f1151563d1d698bda5c1449bb49ab3d7919bd02","abstract_canon_sha256":"6da3c8c66f83fe5590a5e8a1214307f3a7431c8120bd5950e3d8687f6916f964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:22.178230Z","signature_b64":"W2ZSMG+JmZi3Uv8HzUPNnuxgltL2eDbAiItlmYLZaHseE1eeMfSuVFt09v2CVAR3zZI6fFY5KT5SDbOwoDY9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6ef258d0e73b75b76441a363121889ef411361d541c66ae009057f73b156d18","last_reissued_at":"2026-07-05T02:27:22.177763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:22.177763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning Symmetries by Reparameterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Allan Zhou, Chelsea Finn, Tom Knowles","submitted_at":"2020-07-06T17:59:54Z","abstract_excerpt":"Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only works when practitioners know the symmetries of the task and can manually construct an architecture with the corresponding equivariances. Our goal is an approach for learning equivariances from data, without needing to design custom task-specific architectures. We present a method for learning and encoding equivariances into networks by learning correspondin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02933","kind":"arxiv","version":3},"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/2007.02933/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":"2007.02933","created_at":"2026-07-05T02:27:22.177821+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.02933v3","created_at":"2026-07-05T02:27:22.177821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02933","created_at":"2026-07-05T02:27:22.177821+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3XSLDIOOO3V","created_at":"2026-07-05T02:27:22.177821+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3XSLDIOOO3VW5SE","created_at":"2026-07-05T02:27:22.177821+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3XSLDIO","created_at":"2026-07-05T02:27:22.177821+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17782","citing_title":"Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06479","citing_title":"Risk-Controlled Post-Processing of Decision Policies","ref_index":292,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3","json":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3.json","graph_json":"https://pith.science/api/pith-number/U3XSLDIOOO3VW5SEDI3DCIMIT3/graph.json","events_json":"https://pith.science/api/pith-number/U3XSLDIOOO3VW5SEDI3DCIMIT3/events.json","paper":"https://pith.science/paper/U3XSLDIO"},"agent_actions":{"view_html":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3","download_json":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3.json","view_paper":"https://pith.science/paper/U3XSLDIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.02933&json=true","fetch_graph":"https://pith.science/api/pith-number/U3XSLDIOOO3VW5SEDI3DCIMIT3/graph.json","fetch_events":"https://pith.science/api/pith-number/U3XSLDIOOO3VW5SEDI3DCIMIT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3/action/storage_attestation","attest_author":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3/action/author_attestation","sign_citation":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3/action/citation_signature","submit_replication":"https://pith.science/pith/U3XSLDIOOO3VW5SEDI3DCIMIT3/action/replication_record"}},"created_at":"2026-07-05T02:27:22.177821+00:00","updated_at":"2026-07-05T02:27:22.177821+00:00"}