{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:OOVVDZG26EPFZGFAXEVLUBQDIZ","short_pith_number":"pith:OOVVDZG2","schema_version":"1.0","canonical_sha256":"73ab51e4daf11e5c98a0b92aba0603465f7c3f8f2f3038680861914cf1dc0d69","source":{"kind":"arxiv","id":"1602.02215","version":1},"attestation_state":"computed","paper":{"title":"Swivel: Improving Embeddings by Noticing What's Missing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Waterson, Colin Evans, Noam Shazeer, Ryan Doherty","submitted_at":"2016-02-06T04:39:41Z","abstract_excerpt":"We present Submatrix-wise Vector Embedding Learner (Swivel), a method for generating low-dimensional feature embeddings from a feature co-occurrence matrix. Swivel performs approximate factorization of the point-wise mutual information matrix via stochastic gradient descent. It uses a piecewise loss with special handling for unobserved co-occurrences, and thus makes use of all the information in the matrix. While this requires computation proportional to the size of the entire matrix, we make use of vectorized multiplication to process thousands of rows and columns at once to compute millions "},"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":"1602.02215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-06T04:39:41Z","cross_cats_sorted":[],"title_canon_sha256":"a671708d4e5866a03c1bd126178079938e0dc1fce6ba99f6187dda70d485ea90","abstract_canon_sha256":"976e20a520ce2b6e75dc7225eb7a211aa57db711fc439d9b8eefa0034b6a7069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:10.623075Z","signature_b64":"U5d6IbalWd4s422A4S8sPgeHLE1xZN89JiNcj6p+t74Sbkv78Toz3G45S4spWCkOnbewjygSfNqyoOK5wV5zBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73ab51e4daf11e5c98a0b92aba0603465f7c3f8f2f3038680861914cf1dc0d69","last_reissued_at":"2026-05-18T01:21:10.622241Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:10.622241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Swivel: Improving Embeddings by Noticing What's Missing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Waterson, Colin Evans, Noam Shazeer, Ryan Doherty","submitted_at":"2016-02-06T04:39:41Z","abstract_excerpt":"We present Submatrix-wise Vector Embedding Learner (Swivel), a method for generating low-dimensional feature embeddings from a feature co-occurrence matrix. Swivel performs approximate factorization of the point-wise mutual information matrix via stochastic gradient descent. It uses a piecewise loss with special handling for unobserved co-occurrences, and thus makes use of all the information in the matrix. While this requires computation proportional to the size of the entire matrix, we make use of vectorized multiplication to process thousands of rows and columns at once to compute millions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02215","kind":"arxiv","version":1},"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":"1602.02215","created_at":"2026-05-18T01:21:10.622378+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.02215v1","created_at":"2026-05-18T01:21:10.622378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02215","created_at":"2026-05-18T01:21:10.622378+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOVVDZG26EPF","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOVVDZG26EPFZGFA","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOVVDZG2","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ","json":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ.json","graph_json":"https://pith.science/api/pith-number/OOVVDZG26EPFZGFAXEVLUBQDIZ/graph.json","events_json":"https://pith.science/api/pith-number/OOVVDZG26EPFZGFAXEVLUBQDIZ/events.json","paper":"https://pith.science/paper/OOVVDZG2"},"agent_actions":{"view_html":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ","download_json":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ.json","view_paper":"https://pith.science/paper/OOVVDZG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.02215&json=true","fetch_graph":"https://pith.science/api/pith-number/OOVVDZG26EPFZGFAXEVLUBQDIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OOVVDZG26EPFZGFAXEVLUBQDIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ/action/storage_attestation","attest_author":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ/action/author_attestation","sign_citation":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ/action/citation_signature","submit_replication":"https://pith.science/pith/OOVVDZG26EPFZGFAXEVLUBQDIZ/action/replication_record"}},"created_at":"2026-05-18T01:21:10.622378+00:00","updated_at":"2026-05-18T01:21:10.622378+00:00"}