{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3C7ESQ56CFWSNQAZAYDQLGZVM7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b60eea10cfe0b15e7706584c2719be5134e964e5eb1a504bdea54a8e0ccee693","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T02:47:40Z","title_canon_sha256":"c51531ad52ce0e61283566bb64716e7fe562559003824729e91abe24fdc10ae8"},"schema_version":"1.0","source":{"id":"2006.05623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.05623","created_at":"2026-07-05T01:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2006.05623v1","created_at":"2026-07-05T01:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05623","created_at":"2026-07-05T01:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"3C7ESQ56CFWS","created_at":"2026-07-05T01:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"3C7ESQ56CFWSNQAZ","created_at":"2026-07-05T01:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"3C7ESQ56","created_at":"2026-07-05T01:09:15Z"}],"graph_snapshots":[{"event_id":"sha256:19b65561df06d008f5dbb6281f8d7fcc67e93f4a3903934373bc553be3d8cd58","target":"graph","created_at":"2026-07-05T01:09:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.05623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern recommendation systems rely on real-valued embeddings of categorical features. Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size. We introduce a multi-layer embedding training (MLET) architecture that trains embeddings via a sequence of linear layers to derive superior embedding accuracy vs. model size trade-off.\n  Our approach is fundamentally based on the ability of factorized linear layers to produce superior embeddings to that of a single linear layer. We focus on the analysis and implementation of a two-layer scheme. Harnes","authors_text":"Ashish Kumar Singh, Benjamin Cho, Benjamin Ghaemmaghami, Leo Orshansky, Mattan Erez, Michael Orshansky, Zihao Deng","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T02:47:40Z","title":"Training with Multi-Layer Embeddings for Model Reduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05623","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ce5a62037a60ade5e18f0b039fe506c666fa12fb90571939db236c5c16cc4ab9","target":"record","created_at":"2026-07-05T01:09:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b60eea10cfe0b15e7706584c2719be5134e964e5eb1a504bdea54a8e0ccee693","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T02:47:40Z","title_canon_sha256":"c51531ad52ce0e61283566bb64716e7fe562559003824729e91abe24fdc10ae8"},"schema_version":"1.0","source":{"id":"2006.05623","kind":"arxiv","version":1}},"canonical_sha256":"d8be4943be116d26c0190607059b3567db81bbcf8f913c9d68a63cf50d78646d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8be4943be116d26c0190607059b3567db81bbcf8f913c9d68a63cf50d78646d","first_computed_at":"2026-07-05T01:09:15.385276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:15.385276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v47Y2YdkPgs6H99u/hb1IYvx/7B3pmgxS6kwJnDkaJUghIkkfLwW01gP5KWxH+nybBdaOskcGDQaC1E/UCK8Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:15.385733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.05623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce5a62037a60ade5e18f0b039fe506c666fa12fb90571939db236c5c16cc4ab9","sha256:19b65561df06d008f5dbb6281f8d7fcc67e93f4a3903934373bc553be3d8cd58"],"state_sha256":"4b4b98b0e1cfd7de5daf52f6e326892fe36cbc09729a85c274fb29b49634c3c4"}