{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:53ZLWINBTNDELI6J6CQ7WUMJWF","short_pith_number":"pith:53ZLWINB","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"},"canonical_sha256":"eef2bb21a19b4645a3c9f0a1fb5189b173da9f74a291f2fbd58a512cbdbcce1a","source":{"kind":"arxiv","id":"1803.00502","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00502","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00502v4","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00502","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"pith_short_12","alias_value":"53ZLWINBTNDE","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"53ZLWINBTNDELI6J","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"53ZLWINB","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:53ZLWINBTNDELI6J6CQ7WUMJWF","target":"record","payload":{"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"},"canonical_sha256":"eef2bb21a19b4645a3c9f0a1fb5189b173da9f74a291f2fbd58a512cbdbcce1a","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"},"source_kind":"arxiv","source_id":"1803.00502","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pob+3y3BVYevWDxuxKbJtY1yo92M9Grkd7Ro+t5x5u7PjciK6+sgNaEBknUUixOM7HNCM/q0gvL/vYQWdu61Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T18:51:01.270191Z"},"content_sha256":"5d3c0e1b7e35e4741904f2880bec41e8acf7cac7dbd656a24bce7a3d6e6eee3f","schema_version":"1.0","event_id":"sha256:5d3c0e1b7e35e4741904f2880bec41e8acf7cac7dbd656a24bce7a3d6e6eee3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:53ZLWINBTNDELI6J6CQ7WUMJWF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K/7OMdKktLeU0qUTEr0+QV+zKp+x7/xgGEtKVJp+qC3qou9MvOIOaJqPL8VONrDdiu0y/OYf+G1VzbCHS35jBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T18:51:01.270547Z"},"content_sha256":"be8fb1eda36ecf9a0df8517ce289d738ed582e08bb9ea57e5fbec417f378d3af","schema_version":"1.0","event_id":"sha256:be8fb1eda36ecf9a0df8517ce289d738ed582e08bb9ea57e5fbec417f378d3af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/bundle.json","state_url":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/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":"2026-06-28T18:51:01Z","links":{"resolver":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF","bundle":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/bundle.json","state":"https://pith.science/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53ZLWINBTNDELI6J6CQ7WUMJWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:53ZLWINBTNDELI6J6CQ7WUMJWF","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":"9e5b30120618b5db824d7a00abee83514cee73dddd750cb9264def396619ff2f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T17:02:17Z","title_canon_sha256":"64d4cc4dbb293d6a5548fe527507b1c63288488d5e7a7048a7c6f089adf39ef5"},"schema_version":"1.0","source":{"id":"1803.00502","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00502","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00502v4","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00502","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"pith_short_12","alias_value":"53ZLWINBTNDE","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"53ZLWINBTNDELI6J","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"53ZLWINB","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:be8fb1eda36ecf9a0df8517ce289d738ed582e08bb9ea57e5fbec417f378d3af","target":"graph","created_at":"2026-05-18T00:15:36Z","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":"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","authors_text":"Zi Yin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T17:02:17Z","title":"Understand Functionality and Dimensionality of Vector Embeddings: the Distributional Hypothesis, the Pairwise Inner Product Loss and Its Bias-Variance Trade-off"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00502","kind":"arxiv","version":4},"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":"sha256:5d3c0e1b7e35e4741904f2880bec41e8acf7cac7dbd656a24bce7a3d6e6eee3f","target":"record","created_at":"2026-05-18T00:15:36Z","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":"9e5b30120618b5db824d7a00abee83514cee73dddd750cb9264def396619ff2f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-01T17:02:17Z","title_canon_sha256":"64d4cc4dbb293d6a5548fe527507b1c63288488d5e7a7048a7c6f089adf39ef5"},"schema_version":"1.0","source":{"id":"1803.00502","kind":"arxiv","version":4}},"canonical_sha256":"eef2bb21a19b4645a3c9f0a1fb5189b173da9f74a291f2fbd58a512cbdbcce1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eef2bb21a19b4645a3c9f0a1fb5189b173da9f74a291f2fbd58a512cbdbcce1a","first_computed_at":"2026-05-18T00:15:36.519191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:36.519191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mJmY84Se/kK0DghvVd5otBGU2F2y2ZHFDFA/z3zeaVcPdTVgZXuARHLezrhxzM0Cq/PtvVpbmnQTUlV6HhWkAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:36.519912Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.00502","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d3c0e1b7e35e4741904f2880bec41e8acf7cac7dbd656a24bce7a3d6e6eee3f","sha256:be8fb1eda36ecf9a0df8517ce289d738ed582e08bb9ea57e5fbec417f378d3af"],"state_sha256":"c2b233c980f93f1679adc1985b444dee387fa8e541d43b4013893e2d018bd5ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s7MLUu3oCWUP548BkvQGJBfczM2SgNDRlnN6sElDroZWS2xAGLyubS46BeqgLUzOwPTrFg+qf0TlPGy2ct+uDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T18:51:01.272420Z","bundle_sha256":"a3f5139a26599c1552dd2c4c87d09f7ba262597c2a31c0915671c2548110b519"}}