{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZOZ3755BZUXWJGD2WK7F3RFLLA","short_pith_number":"pith:ZOZ3755B","schema_version":"1.0","canonical_sha256":"cbb3bff7a1cd2f64987ab2be5dc4ab5809463792de15810b95475bc56ace7621","source":{"kind":"arxiv","id":"2204.11371","version":2},"attestation_state":"computed","paper":{"title":"Learning Symmetric Embeddings for Equivariant World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jan Willem van de Meent, Jung Yeon Park, Linfeng Zhao, Ondrej Biza, Robin Walters","submitted_at":"2022-04-24T22:31:52Z","abstract_excerpt":"Incorporating symmetries can lead to highly data-efficient and generalizable models by defining equivalence classes of data samples related by transformations. However, characterizing how transformations act on input data is often difficult, limiting the applicability of equivariant models. We propose learning symmetric embedding networks (SENs) that encode an input space (e.g. images), where we do not know the effect of transformations (e.g. rotations), to a feature space that transforms in a known manner under these operations. This network can be trained end-to-end with an equivariant task "},"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":"2204.11371","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-24T22:31:52Z","cross_cats_sorted":[],"title_canon_sha256":"a711f1e9ccf60a350296395ed943a0dbf5b04fa85e52826e45db769306950f11","abstract_canon_sha256":"cdb5f6e2b13766625d6064ddf7d596a510296d1cece3b34983cafff3652c458c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:35.993599Z","signature_b64":"6XcV1jq33o6e2+hfmX3p3Ki8y9r6YPHxMwGLp96/88wenaa17UBFJLs3VfTFm0DpjJLcFcrK854UMOfSLXFjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbb3bff7a1cd2f64987ab2be5dc4ab5809463792de15810b95475bc56ace7621","last_reissued_at":"2026-07-05T04:36:35.993104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:35.993104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Symmetric Embeddings for Equivariant World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jan Willem van de Meent, Jung Yeon Park, Linfeng Zhao, Ondrej Biza, Robin Walters","submitted_at":"2022-04-24T22:31:52Z","abstract_excerpt":"Incorporating symmetries can lead to highly data-efficient and generalizable models by defining equivalence classes of data samples related by transformations. However, characterizing how transformations act on input data is often difficult, limiting the applicability of equivariant models. We propose learning symmetric embedding networks (SENs) that encode an input space (e.g. images), where we do not know the effect of transformations (e.g. rotations), to a feature space that transforms in a known manner under these operations. This network can be trained end-to-end with an equivariant task "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11371","kind":"arxiv","version":2},"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/2204.11371/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":"2204.11371","created_at":"2026-07-05T04:36:35.993165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.11371v2","created_at":"2026-07-05T04:36:35.993165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11371","created_at":"2026-07-05T04:36:35.993165+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOZ3755BZUXW","created_at":"2026-07-05T04:36:35.993165+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOZ3755BZUXWJGD2","created_at":"2026-07-05T04:36:35.993165+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOZ3755B","created_at":"2026-07-05T04:36:35.993165+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":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA","json":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA.json","graph_json":"https://pith.science/api/pith-number/ZOZ3755BZUXWJGD2WK7F3RFLLA/graph.json","events_json":"https://pith.science/api/pith-number/ZOZ3755BZUXWJGD2WK7F3RFLLA/events.json","paper":"https://pith.science/paper/ZOZ3755B"},"agent_actions":{"view_html":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA","download_json":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA.json","view_paper":"https://pith.science/paper/ZOZ3755B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.11371&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOZ3755BZUXWJGD2WK7F3RFLLA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOZ3755BZUXWJGD2WK7F3RFLLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA/action/storage_attestation","attest_author":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA/action/author_attestation","sign_citation":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA/action/citation_signature","submit_replication":"https://pith.science/pith/ZOZ3755BZUXWJGD2WK7F3RFLLA/action/replication_record"}},"created_at":"2026-07-05T04:36:35.993165+00:00","updated_at":"2026-07-05T04:36:35.993165+00:00"}