{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZKRL4AINYPAQP77R5466HYG3GD","short_pith_number":"pith:ZKRL4AIN","schema_version":"1.0","canonical_sha256":"caa2be010dc3c107fff1ef3de3e0db30d750a4a8af9e2e60416a25d68f61794d","source":{"kind":"arxiv","id":"1708.03498","version":2},"attestation_state":"computed","paper":{"title":"Neural Expectation Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Schmidhuber, Klaus Greff, Sjoerd van Steenkiste","submitted_at":"2017-08-11T10:17:23Z","abstract_excerpt":"Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations. In this paper, we explicitly formalize this problem as inference in a spatial mixture model where each component is parametrized by a neural network. Based on the Expectation Maximization framework we then derive a differentiable clustering method that simultaneously learns how to group and represent individual entities. We evaluate our method on the (seque"},"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":"1708.03498","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-08-11T10:17:23Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"1188ace3cefceecbaa002c0f5f3bd4c85f7229860fe6addfe5d8043ee04b4d96","abstract_canon_sha256":"6243758454f4ff6dd064ab5d76351eb0e651e3d4be208633201202c389727f09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:18.945614Z","signature_b64":"gy76ub2vTGOBvNeMxkm4JHIodFedYt1wK6iqzHDMGbuOwxyDGuUWfHtUHqwCb68ObRxkgyBq1jImRStSBYyCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa2be010dc3c107fff1ef3de3e0db30d750a4a8af9e2e60416a25d68f61794d","last_reissued_at":"2026-05-18T00:31:18.944905Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:18.944905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Expectation Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Schmidhuber, Klaus Greff, Sjoerd van Steenkiste","submitted_at":"2017-08-11T10:17:23Z","abstract_excerpt":"Many real world tasks such as reasoning and physical interaction require identification and manipulation of conceptual entities. A first step towards solving these tasks is the automated discovery of distributed symbol-like representations. In this paper, we explicitly formalize this problem as inference in a spatial mixture model where each component is parametrized by a neural network. Based on the Expectation Maximization framework we then derive a differentiable clustering method that simultaneously learns how to group and represent individual entities. We evaluate our method on the (seque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03498","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":""},"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":"1708.03498","created_at":"2026-05-18T00:31:18.945021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.03498v2","created_at":"2026-05-18T00:31:18.945021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03498","created_at":"2026-05-18T00:31:18.945021+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKRL4AINYPAQ","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKRL4AINYPAQP77R","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKRL4AIN","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13484","citing_title":"Joint Representation Learning and Clustering via Gradient-Based Manifold Optimization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD","json":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD.json","graph_json":"https://pith.science/api/pith-number/ZKRL4AINYPAQP77R5466HYG3GD/graph.json","events_json":"https://pith.science/api/pith-number/ZKRL4AINYPAQP77R5466HYG3GD/events.json","paper":"https://pith.science/paper/ZKRL4AIN"},"agent_actions":{"view_html":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD","download_json":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD.json","view_paper":"https://pith.science/paper/ZKRL4AIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.03498&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKRL4AINYPAQP77R5466HYG3GD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKRL4AINYPAQP77R5466HYG3GD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD/action/storage_attestation","attest_author":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD/action/author_attestation","sign_citation":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD/action/citation_signature","submit_replication":"https://pith.science/pith/ZKRL4AINYPAQP77R5466HYG3GD/action/replication_record"}},"created_at":"2026-05-18T00:31:18.945021+00:00","updated_at":"2026-05-18T00:31:18.945021+00:00"}