{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2KVB7Q2ARKF3WEQ6QU7PQBKKLK","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":"6884ae32da6e900c1c18e75705339e3fd54b401eda70795293ac5594d5428a40","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T09:32:10Z","title_canon_sha256":"89a0ba3f32ff23b3a1ef09172c06dbb4c6ad771b37a6edfb821e6e80c3aad88e"},"schema_version":"1.0","source":{"id":"2309.15881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15881","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15881v1","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15881","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"pith_short_12","alias_value":"2KVB7Q2ARKF3","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"pith_short_16","alias_value":"2KVB7Q2ARKF3WEQ6","created_at":"2026-07-05T06:55:07Z"},{"alias_kind":"pith_short_8","alias_value":"2KVB7Q2A","created_at":"2026-07-05T06:55:07Z"}],"graph_snapshots":[{"event_id":"sha256:79ac302042de11ae9bcd1e2852add35c909fe4f8921e7ee8f4bbe72802d4ea88","target":"graph","created_at":"2026-07-05T06:55:07Z","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/2309.15881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern DNN-based recommendation systems rely on training-derived embeddings of sparse features. Input sparsity makes obtaining high-quality embeddings for rarely-occurring categories harder as their representations are updated infrequently. We demonstrate a training-time technique to produce superior embeddings via effective cross-category learning and theoretically explain its surprising effectiveness. The scheme, termed the multi-layer embeddings training (MLET), trains embeddings using factorization of the embedding layer, with an inner dimension higher than the target embedding dimension. ","authors_text":"Ashish Kumar Singh, Benjamin Cho, Benjamin Ghaemmaghami, Leo Orshansky, Mattan Erez, Michael Orshansky, Zihao Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T09:32:10Z","title":"Enhancing Cross-Category Learning in Recommendation Systems with Multi-Layer Embedding Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15881","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:eb1941af951d7a3082ee075de0327935c5c9045bfb711a495d7833e1644a9a1b","target":"record","created_at":"2026-07-05T06:55:07Z","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":"6884ae32da6e900c1c18e75705339e3fd54b401eda70795293ac5594d5428a40","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-27T09:32:10Z","title_canon_sha256":"89a0ba3f32ff23b3a1ef09172c06dbb4c6ad771b37a6edfb821e6e80c3aad88e"},"schema_version":"1.0","source":{"id":"2309.15881","kind":"arxiv","version":1}},"canonical_sha256":"d2aa1fc3408a8bbb121e853ef8054a5a89dfcf4f850dc164016309e8a29fdec1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2aa1fc3408a8bbb121e853ef8054a5a89dfcf4f850dc164016309e8a29fdec1","first_computed_at":"2026-07-05T06:55:07.837405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:07.837405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nanIMAv8fXLEG8Z0Jnxn+qoV3Lv4EjqQ3L4TASSZbzgAV5eXtunr3/Tplx0MCft37lZUyVA8EPrxxgaojgu6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:07.837746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb1941af951d7a3082ee075de0327935c5c9045bfb711a495d7833e1644a9a1b","sha256:79ac302042de11ae9bcd1e2852add35c909fe4f8921e7ee8f4bbe72802d4ea88"],"state_sha256":"bf467531f393a83f68c57e28942d35dce04fe0096197f997fa88b8eb1b8698e9"}