{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MIRXN3EBNQSPQT4FRLGYLOEO44","short_pith_number":"pith:MIRXN3EB","canonical_record":{"source":{"id":"1812.04224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T05:25:38Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"8e20e8d8ad72eb461cd80f2027ea3de01c05df19c26bfde2948234a0f54354e5","abstract_canon_sha256":"0e222f0e04068daf6415aadeb9e4d8033ccab2ae7814d80c16ff8de23d76625b"},"schema_version":"1.0"},"canonical_sha256":"622376ec816c24f84f858acd85b88ee70d8f090fc5f4c78178d3df7d63550aad","source":{"kind":"arxiv","id":"1812.04224","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04224","created_at":"2026-05-17T23:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04224v1","created_at":"2026-05-17T23:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04224","created_at":"2026-05-17T23:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"MIRXN3EBNQSP","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MIRXN3EBNQSPQT4F","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MIRXN3EB","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MIRXN3EBNQSPQT4FRLGYLOEO44","target":"record","payload":{"canonical_record":{"source":{"id":"1812.04224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T05:25:38Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"8e20e8d8ad72eb461cd80f2027ea3de01c05df19c26bfde2948234a0f54354e5","abstract_canon_sha256":"0e222f0e04068daf6415aadeb9e4d8033ccab2ae7814d80c16ff8de23d76625b"},"schema_version":"1.0"},"canonical_sha256":"622376ec816c24f84f858acd85b88ee70d8f090fc5f4c78178d3df7d63550aad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:32.958018Z","signature_b64":"i1Fc9J6gM4KDz2BWt3elPDzjv2rQQIKMV8PzT/pg533Z9TiP/F5Om1wG5lrV2RF85mq5cT7v2oE8PbWrVudMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"622376ec816c24f84f858acd85b88ee70d8f090fc5f4c78178d3df7d63550aad","last_reissued_at":"2026-05-17T23:58:32.957352Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:32.957352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.04224","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYkiJ6aJJfaXsL9xCens5C/PEVawODcTYgaZ9LI4q+2CVyxMZdWBJwfO9ApoUulvos5H1/ixhP8tSMMrgvqPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:48:32.611339Z"},"content_sha256":"62e34cae03f468bae1964433080e92e52942c730069578252d75c4516d85d1f5","schema_version":"1.0","event_id":"sha256:62e34cae03f468bae1964433080e92e52942c730069578252d75c4516d85d1f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MIRXN3EBNQSPQT4FRLGYLOEO44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Dimensionality of Word Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuanyuan Shen, Zi Yin","submitted_at":"2018-12-11T05:25:38Z","abstract_excerpt":"In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity between word embeddings. Using techniques from matrix perturbation theory, we reveal a fundamental bias-variance trade-off in dimensionality selection for word embeddings. This bias-variance trade-off sheds light on many empirical observations which were previously unexplained, for example the existence of an optimal dimensionality. Moreover, new insights and d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04224","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qm7Irat0ZXMftahEmZKPw09DQSj29RJvbj6BhOJ1jc2w7Sd5XY2IF9A19pyxR2gz9vqkPMNVwMavSx0RA+jhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:48:32.611682Z"},"content_sha256":"d1b12f456ba0496d972efdad007a9fbe04aa21185f857debe330122c8b7e0d27","schema_version":"1.0","event_id":"sha256:d1b12f456ba0496d972efdad007a9fbe04aa21185f857debe330122c8b7e0d27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MIRXN3EBNQSPQT4FRLGYLOEO44/bundle.json","state_url":"https://pith.science/pith/MIRXN3EBNQSPQT4FRLGYLOEO44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MIRXN3EBNQSPQT4FRLGYLOEO44/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T17:48:32Z","links":{"resolver":"https://pith.science/pith/MIRXN3EBNQSPQT4FRLGYLOEO44","bundle":"https://pith.science/pith/MIRXN3EBNQSPQT4FRLGYLOEO44/bundle.json","state":"https://pith.science/pith/MIRXN3EBNQSPQT4FRLGYLOEO44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MIRXN3EBNQSPQT4FRLGYLOEO44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MIRXN3EBNQSPQT4FRLGYLOEO44","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":"0e222f0e04068daf6415aadeb9e4d8033ccab2ae7814d80c16ff8de23d76625b","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T05:25:38Z","title_canon_sha256":"8e20e8d8ad72eb461cd80f2027ea3de01c05df19c26bfde2948234a0f54354e5"},"schema_version":"1.0","source":{"id":"1812.04224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04224","created_at":"2026-05-17T23:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04224v1","created_at":"2026-05-17T23:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04224","created_at":"2026-05-17T23:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"MIRXN3EBNQSP","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MIRXN3EBNQSPQT4F","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MIRXN3EB","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:d1b12f456ba0496d972efdad007a9fbe04aa21185f857debe330122c8b7e0d27","target":"graph","created_at":"2026-05-17T23:58:32Z","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"},"paper":{"abstract_excerpt":"In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity between word embeddings. Using techniques from matrix perturbation theory, we reveal a fundamental bias-variance trade-off in dimensionality selection for word embeddings. This bias-variance trade-off sheds light on many empirical observations which were previously unexplained, for example the existence of an optimal dimensionality. Moreover, new insights and d","authors_text":"Yuanyuan Shen, Zi Yin","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T05:25:38Z","title":"On the Dimensionality of Word Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04224","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":"sha256:62e34cae03f468bae1964433080e92e52942c730069578252d75c4516d85d1f5","target":"record","created_at":"2026-05-17T23:58:32Z","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":"0e222f0e04068daf6415aadeb9e4d8033ccab2ae7814d80c16ff8de23d76625b","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-11T05:25:38Z","title_canon_sha256":"8e20e8d8ad72eb461cd80f2027ea3de01c05df19c26bfde2948234a0f54354e5"},"schema_version":"1.0","source":{"id":"1812.04224","kind":"arxiv","version":1}},"canonical_sha256":"622376ec816c24f84f858acd85b88ee70d8f090fc5f4c78178d3df7d63550aad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"622376ec816c24f84f858acd85b88ee70d8f090fc5f4c78178d3df7d63550aad","first_computed_at":"2026-05-17T23:58:32.957352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:32.957352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i1Fc9J6gM4KDz2BWt3elPDzjv2rQQIKMV8PzT/pg533Z9TiP/F5Om1wG5lrV2RF85mq5cT7v2oE8PbWrVudMCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:32.958018Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.04224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62e34cae03f468bae1964433080e92e52942c730069578252d75c4516d85d1f5","sha256:d1b12f456ba0496d972efdad007a9fbe04aa21185f857debe330122c8b7e0d27"],"state_sha256":"7995b3e208cf4e3c13fcc84021aa44ac6c87ef09904d3c99bd4fff17dbb3dd5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVjkLs8TRqE87Ns9HcqMO+pLTmRUWxzzvr6DKv4eRTrTh1WUOJ/YgsL3yIKMR0RaYr/Y1jHuKUdNiURgcgV0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T17:48:32.613721Z","bundle_sha256":"c6a90964a7fb2b864d722a9d7a69d9ef97eadf06da3f5a35a96c1738da4d4fad"}}