{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HDDUUDY2HOLLWLUEJZA7DMHPQR","short_pith_number":"pith:HDDUUDY2","schema_version":"1.0","canonical_sha256":"38c74a0f1a3b96bb2e844e41f1b0ef8451e51b9e5c7200e0c6418865a541b638","source":{"kind":"arxiv","id":"1905.10630","version":3},"attestation_state":"computed","paper":{"title":"Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, James Sharpnack, Liwei Wu, Shuqing Li","submitted_at":"2019-05-25T16:55:36Z","abstract_excerpt":"In deep neural nets, lower level embedding layers account for a large portion of the total number of parameters. Tikhonov regularization, graph-based regularization, and hard parameter sharing are approaches that introduce explicit biases into training in a hope to reduce statistical complexity. Alternatively, we propose stochastically shared embeddings (SSE), a data-driven approach to regularizing embedding layers, which stochastically transitions between embeddings during stochastic gradient descent (SGD). Because SSE integrates seamlessly with existing SGD algorithms, it can be used with on"},"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":"1905.10630","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-25T16:55:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7c7f8f59b9d903560c8db98640d663800ecd7974ffad913a117b46bacc7fafd8","abstract_canon_sha256":"ef21c9153c6376da661931f07b08d611ccd36bd3213ba911a3954001ca165a39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:53.945499Z","signature_b64":"edroQK4P/apGTBTKqo2WsQ70NFT024fN4QhpBmKhcIOKhsSVzfrwfblbw4ia/Rxdy+hrKV7u1M+ePrz+i8MADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38c74a0f1a3b96bb2e844e41f1b0ef8451e51b9e5c7200e0c6418865a541b638","last_reissued_at":"2026-07-05T01:39:53.945103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:53.945103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, James Sharpnack, Liwei Wu, Shuqing Li","submitted_at":"2019-05-25T16:55:36Z","abstract_excerpt":"In deep neural nets, lower level embedding layers account for a large portion of the total number of parameters. Tikhonov regularization, graph-based regularization, and hard parameter sharing are approaches that introduce explicit biases into training in a hope to reduce statistical complexity. Alternatively, we propose stochastically shared embeddings (SSE), a data-driven approach to regularizing embedding layers, which stochastically transitions between embeddings during stochastic gradient descent (SGD). Because SSE integrates seamlessly with existing SGD algorithms, it can be used with on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10630","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/1905.10630/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":"1905.10630","created_at":"2026-07-05T01:39:53.945164+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10630v3","created_at":"2026-07-05T01:39:53.945164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10630","created_at":"2026-07-05T01:39:53.945164+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDDUUDY2HOLL","created_at":"2026-07-05T01:39:53.945164+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDDUUDY2HOLLWLUE","created_at":"2026-07-05T01:39:53.945164+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDDUUDY2","created_at":"2026-07-05T01:39:53.945164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR","json":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR.json","graph_json":"https://pith.science/api/pith-number/HDDUUDY2HOLLWLUEJZA7DMHPQR/graph.json","events_json":"https://pith.science/api/pith-number/HDDUUDY2HOLLWLUEJZA7DMHPQR/events.json","paper":"https://pith.science/paper/HDDUUDY2"},"agent_actions":{"view_html":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR","download_json":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR.json","view_paper":"https://pith.science/paper/HDDUUDY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10630&json=true","fetch_graph":"https://pith.science/api/pith-number/HDDUUDY2HOLLWLUEJZA7DMHPQR/graph.json","fetch_events":"https://pith.science/api/pith-number/HDDUUDY2HOLLWLUEJZA7DMHPQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR/action/storage_attestation","attest_author":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR/action/author_attestation","sign_citation":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR/action/citation_signature","submit_replication":"https://pith.science/pith/HDDUUDY2HOLLWLUEJZA7DMHPQR/action/replication_record"}},"created_at":"2026-07-05T01:39:53.945164+00:00","updated_at":"2026-07-05T01:39:53.945164+00:00"}