{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:53ZLWINBTNDELI6J6CQ7WUMJWF","short_pith_number":"pith:53ZLWINB","schema_version":"1.0","canonical_sha256":"eef2bb21a19b4645a3c9f0a1fb5189b173da9f74a291f2fbd58a512cbdbcce1a","source":{"kind":"arxiv","id":"1803.00502","version":4},"attestation_state":"computed","paper":{"title":"Understand Functionality and Dimensionality of Vector Embeddings: the Distributional Hypothesis, the Pairwise Inner Product Loss and Its Bias-Variance Trade-off","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Zi Yin","submitted_at":"2018-03-01T17:02:17Z","abstract_excerpt":"Vector embedding is a foundational building block of many deep learning models, especially in natural language processing. In this paper, we present a theoretical framework for understanding the effect of dimensionality on vector embeddings. We observe that the distributional hypothesis, a governing principle of statistical semantics, requires a natural unitary-invariance for vector embeddings. Motivated by the unitary-invariance observation, we propose the Pairwise Inner Product (PIP) loss, a unitary-invariant metric on the similarity between two embeddings. We demonstrate that the PIP loss c"},"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":"1803.00502","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T17:02:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"64d4cc4dbb293d6a5548fe527507b1c63288488d5e7a7048a7c6f089adf39ef5","abstract_canon_sha256":"9e5b30120618b5db824d7a00abee83514cee73dddd750cb9264def396619ff2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:36.519912Z","signature_b64":"mJmY84Se/kK0DghvVd5otBGU2F2y2ZHFDFA/z3zeaVcPdTVgZXuARHLezrhxzM0Cq/PtvVpbmnQTUlV6HhWkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eef2bb21a19b4645a3c9f0a1fb5189b173da9f74a291f2fbd58a512cbdbcce1a","last_reissued_at":"2026-05-18T00:15:36.519191Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:36.519191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understand Functionality and Dimensionality of Vector Embeddings: the Distributional Hypothesis, the Pairwise Inner Product Loss and Its Bias-Variance Trade-off","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Zi Yin","submitted_at":"2018-03-01T17:02:17Z","abstract_excerpt":"Vector embedding is a foundational building block of many deep learning models, especially in natural language processing. In this paper, we present a theoretical framework for understanding the effect of dimensionality on vector embeddings. We observe that the distributional hypothesis, a governing principle of statistical semantics, requires a natural unitary-invariance for vector embeddings. Motivated by the unitary-invariance observation, we propose the Pairwise Inner Product (PIP) loss, a unitary-invariant metric on the similarity between two embeddings. We demonstrate that the PIP loss c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00502","kind":"arxiv","version":4},"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":"1803.00502","created_at":"2026-05-18T00:15:36.519296+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00502v4","created_at":"2026-05-18T00:15:36.519296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00502","created_at":"2026-05-18T00:15:36.519296+00:00"},{"alias_kind":"pith_short_12","alias_value":"53ZLWINBTNDE","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"53ZLWINBTNDELI6J","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"53ZLWINB","created_at":"2026-05-18T12:32:05.422762+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/53ZLWINBTNDELI6J6CQ7WUMJWF","json":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF.json","graph_json":"https://pith.science/api/pith-number/53ZLWINBTNDELI6J6CQ7WUMJWF/graph.json","events_json":"https://pith.science/api/pith-number/53ZLWINBTNDELI6J6CQ7WUMJWF/events.json","paper":"https://pith.science/paper/53ZLWINB"},"agent_actions":{"view_html":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF","download_json":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF.json","view_paper":"https://pith.science/paper/53ZLWINB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00502&json=true","fetch_graph":"https://pith.science/api/pith-number/53ZLWINBTNDELI6J6CQ7WUMJWF/graph.json","fetch_events":"https://pith.science/api/pith-number/53ZLWINBTNDELI6J6CQ7WUMJWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/action/storage_attestation","attest_author":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/action/author_attestation","sign_citation":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/action/citation_signature","submit_replication":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/action/replication_record"}},"created_at":"2026-05-18T00:15:36.519296+00:00","updated_at":"2026-05-18T00:15:36.519296+00:00"}