{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:CWO6GHYCE2CUBYIRNLI3FWRAOO","short_pith_number":"pith:CWO6GHYC","canonical_record":{"source":{"id":"1905.07790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-19T18:23:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d10dd6b3dc69b793ad3c0aa30fca14722796e6995fa6ec86fff1e7ce7ae3134a","abstract_canon_sha256":"445d8f5024bceb7c91193da0a869444140e277b4f281f11a053cf7e4f446cdb6"},"schema_version":"1.0"},"canonical_sha256":"159de31f02268540e1116ad1b2da2073b5cabf0ffafb7452b79e9e04a83f1025","source":{"kind":"arxiv","id":"1905.07790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07790","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07790v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07790","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"CWO6GHYCE2CU","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CWO6GHYCE2CUBYIR","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CWO6GHYC","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:CWO6GHYCE2CUBYIRNLI3FWRAOO","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-19T18:23:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d10dd6b3dc69b793ad3c0aa30fca14722796e6995fa6ec86fff1e7ce7ae3134a","abstract_canon_sha256":"445d8f5024bceb7c91193da0a869444140e277b4f281f11a053cf7e4f446cdb6"},"schema_version":"1.0"},"canonical_sha256":"159de31f02268540e1116ad1b2da2073b5cabf0ffafb7452b79e9e04a83f1025","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.471976Z","signature_b64":"qjEUv//bKvXqWgRvWA3N1iQ8KY1g8oheAIgFYfFUCAXJPvDmSD8eAiNw21n/Omo8Vug3pxd+Q4c03yfpGvRqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"159de31f02268540e1116ad1b2da2073b5cabf0ffafb7452b79e9e04a83f1025","last_reissued_at":"2026-05-17T23:45:48.471500Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.471500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07790","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pteUCJqzbXIzuEO/VbhcI2P/6BpLQ6wCy7hcfenBss+FlNMT/EkkxCoeC4dih00n8m89FXEPKQyg4Cgp6kc8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:28:39.232155Z"},"content_sha256":"5312a8ee8f5f66ed7a9832214d3607e86c1c91b934509b5e155499a17c5be636","schema_version":"1.0","event_id":"sha256:5312a8ee8f5f66ed7a9832214d3607e86c1c91b934509b5e155499a17c5be636"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:CWO6GHYCE2CUBYIRNLI3FWRAOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correlation Coefficients and Semantic Textual Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Aleksandar Savkov, April Shen, Nils Y. Hammerla, Vitalii Zhelezniak","submitted_at":"2019-05-19T18:23:14Z","abstract_excerpt":"A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little attention has been devoted to similarity measures between these embeddings, with cosine similarity being used unquestionably in the majority of cases. In this work, we illustrate that for all common word vectors, cosine similarity is essentially equivalent to the Pearson correlation coefficient, which provides some justification for its use. We thoroughly characterise cases"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07790","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":"2026-05-17T23:45:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NU+P2TdYUVFq3z8vwcJ/ptFb7PLjvtsiYp+MGLV1trbM5ixk4wgOYKh0mCNAU7M66htSqZEfLFWx4ikrQTvxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:28:39.232873Z"},"content_sha256":"f313f0573256d1a8aeec5f4555376ab30ce250d9d7b6c968baa11688ef62f97f","schema_version":"1.0","event_id":"sha256:f313f0573256d1a8aeec5f4555376ab30ce250d9d7b6c968baa11688ef62f97f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWO6GHYCE2CUBYIRNLI3FWRAOO/bundle.json","state_url":"https://pith.science/pith/CWO6GHYCE2CUBYIRNLI3FWRAOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWO6GHYCE2CUBYIRNLI3FWRAOO/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":"2026-05-30T00:28:39Z","links":{"resolver":"https://pith.science/pith/CWO6GHYCE2CUBYIRNLI3FWRAOO","bundle":"https://pith.science/pith/CWO6GHYCE2CUBYIRNLI3FWRAOO/bundle.json","state":"https://pith.science/pith/CWO6GHYCE2CUBYIRNLI3FWRAOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWO6GHYCE2CUBYIRNLI3FWRAOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CWO6GHYCE2CUBYIRNLI3FWRAOO","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":"445d8f5024bceb7c91193da0a869444140e277b4f281f11a053cf7e4f446cdb6","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-19T18:23:14Z","title_canon_sha256":"d10dd6b3dc69b793ad3c0aa30fca14722796e6995fa6ec86fff1e7ce7ae3134a"},"schema_version":"1.0","source":{"id":"1905.07790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07790","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07790v1","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07790","created_at":"2026-05-17T23:45:48Z"},{"alias_kind":"pith_short_12","alias_value":"CWO6GHYCE2CU","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CWO6GHYCE2CUBYIR","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CWO6GHYC","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:f313f0573256d1a8aeec5f4555376ab30ce250d9d7b6c968baa11688ef62f97f","target":"graph","created_at":"2026-05-17T23:45:48Z","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":"A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little attention has been devoted to similarity measures between these embeddings, with cosine similarity being used unquestionably in the majority of cases. In this work, we illustrate that for all common word vectors, cosine similarity is essentially equivalent to the Pearson correlation coefficient, which provides some justification for its use. We thoroughly characterise cases","authors_text":"Aleksandar Savkov, April Shen, Nils Y. Hammerla, Vitalii Zhelezniak","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-19T18:23:14Z","title":"Correlation Coefficients and Semantic Textual Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07790","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":"sha256:5312a8ee8f5f66ed7a9832214d3607e86c1c91b934509b5e155499a17c5be636","target":"record","created_at":"2026-05-17T23:45:48Z","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":"445d8f5024bceb7c91193da0a869444140e277b4f281f11a053cf7e4f446cdb6","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-19T18:23:14Z","title_canon_sha256":"d10dd6b3dc69b793ad3c0aa30fca14722796e6995fa6ec86fff1e7ce7ae3134a"},"schema_version":"1.0","source":{"id":"1905.07790","kind":"arxiv","version":1}},"canonical_sha256":"159de31f02268540e1116ad1b2da2073b5cabf0ffafb7452b79e9e04a83f1025","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"159de31f02268540e1116ad1b2da2073b5cabf0ffafb7452b79e9e04a83f1025","first_computed_at":"2026-05-17T23:45:48.471500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:48.471500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qjEUv//bKvXqWgRvWA3N1iQ8KY1g8oheAIgFYfFUCAXJPvDmSD8eAiNw21n/Omo8Vug3pxd+Q4c03yfpGvRqBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:48.471976Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5312a8ee8f5f66ed7a9832214d3607e86c1c91b934509b5e155499a17c5be636","sha256:f313f0573256d1a8aeec5f4555376ab30ce250d9d7b6c968baa11688ef62f97f"],"state_sha256":"a4f2ebb5f5ce9ad4687401dacae1c2178ca9c4bfacf0752bd00d7aee9ca89eec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TUZRND7tn5mokSgxWgO5uKjAmjeM4lETBU+GNHqvKn43cn6OfwQhDCLAT7V1XEdQx1wL4qGDMcwrlYfinq/yCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T00:28:39.236942Z","bundle_sha256":"e03856225e0da88ebd3cd5ce78992bbe2a1972d7f4241ede99e8473eaf5425c2"}}