{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:GLDIPSXQYHWCNF4AABR6EDR4X5","short_pith_number":"pith:GLDIPSXQ","canonical_record":{"source":{"id":"1611.01547","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T21:35:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d088cb38639aa805124af33e29f6ec52eba46fb793701c99623b15b056edaf0","abstract_canon_sha256":"ec21d18e4e967ec11000388faba82fadbddadee88e93ed3178819fb1c244eb54"},"schema_version":"1.0"},"canonical_sha256":"32c687caf0c1ec2697800063e20e3cbf63a8771d35d9cfad4f83d331daeb1109","source":{"kind":"arxiv","id":"1611.01547","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01547","created_at":"2026-05-18T00:46:59Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01547v5","created_at":"2026-05-18T00:46:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01547","created_at":"2026-05-18T00:46:59Z"},{"alias_kind":"pith_short_12","alias_value":"GLDIPSXQYHWC","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GLDIPSXQYHWCNF4A","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GLDIPSXQ","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:GLDIPSXQYHWCNF4AABR6EDR4X5","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01547","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T21:35:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d088cb38639aa805124af33e29f6ec52eba46fb793701c99623b15b056edaf0","abstract_canon_sha256":"ec21d18e4e967ec11000388faba82fadbddadee88e93ed3178819fb1c244eb54"},"schema_version":"1.0"},"canonical_sha256":"32c687caf0c1ec2697800063e20e3cbf63a8771d35d9cfad4f83d331daeb1109","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:59.355874Z","signature_b64":"jNAUGfSHTBdliT30CQ+e60VbhzcVCazDDw3DkZHSVNOuOREexaRdkH4qcvigSu2DlzeNGRKkWoubM07yqGMzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32c687caf0c1ec2697800063e20e3cbf63a8771d35d9cfad4f83d331daeb1109","last_reissued_at":"2026-05-18T00:46:59.354893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:59.354893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01547","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:46:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BdkFgw2SLlLC+uyDN3cvDpa3HHpVL6QCH0Z0vfGLZ48yHDqKfkJkIwVZyKgax1bGGdvhTBqnaJ/LJtV+xD9YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:21:32.612537Z"},"content_sha256":"d7f3823b44711dc807d8ab2944891f59d66b18c7eed98049989dc4e15d2674ee","schema_version":"1.0","event_id":"sha256:d7f3823b44711dc807d8ab2944891f59d66b18c7eed98049989dc4e15d2674ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:GLDIPSXQYHWCNF4AABR6EDR4X5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Joel Barry, Philip Blair, Yuval Merhav","submitted_at":"2016-11-04T21:35:07Z","abstract_excerpt":"We propose a language-agnostic way of automatically generating sets of semantically similar clusters of entities along with sets of \"outlier\" elements, which may then be used to perform an intrinsic evaluation of word embeddings in the outlier detection task. We used our methodology to create a gold-standard dataset, which we call WikiSem500, and evaluated multiple state-of-the-art embeddings. The results show a correlation between performance on this dataset and performance on sentiment analysis."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01547","kind":"arxiv","version":5},"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":"2026-05-18T00:46:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pya70UgE/seZyZbr0JYO5H6elJVUiIyLX7dDTH1ShH1g+pJxwTKERaAKGeI8o8KVUV4bjglbBl1tNgeYbxJYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:21:32.612879Z"},"content_sha256":"8a162d900c8b5b3255c9b92ad113f31d92f7e775f1a51b31a0620f9da132c4a0","schema_version":"1.0","event_id":"sha256:8a162d900c8b5b3255c9b92ad113f31d92f7e775f1a51b31a0620f9da132c4a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLDIPSXQYHWCNF4AABR6EDR4X5/bundle.json","state_url":"https://pith.science/pith/GLDIPSXQYHWCNF4AABR6EDR4X5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLDIPSXQYHWCNF4AABR6EDR4X5/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":"2026-07-07T12:21:32Z","links":{"resolver":"https://pith.science/pith/GLDIPSXQYHWCNF4AABR6EDR4X5","bundle":"https://pith.science/pith/GLDIPSXQYHWCNF4AABR6EDR4X5/bundle.json","state":"https://pith.science/pith/GLDIPSXQYHWCNF4AABR6EDR4X5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLDIPSXQYHWCNF4AABR6EDR4X5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:GLDIPSXQYHWCNF4AABR6EDR4X5","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":"ec21d18e4e967ec11000388faba82fadbddadee88e93ed3178819fb1c244eb54","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T21:35:07Z","title_canon_sha256":"4d088cb38639aa805124af33e29f6ec52eba46fb793701c99623b15b056edaf0"},"schema_version":"1.0","source":{"id":"1611.01547","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01547","created_at":"2026-05-18T00:46:59Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01547v5","created_at":"2026-05-18T00:46:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01547","created_at":"2026-05-18T00:46:59Z"},{"alias_kind":"pith_short_12","alias_value":"GLDIPSXQYHWC","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"GLDIPSXQYHWCNF4A","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"GLDIPSXQ","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:8a162d900c8b5b3255c9b92ad113f31d92f7e775f1a51b31a0620f9da132c4a0","target":"graph","created_at":"2026-05-18T00:46:59Z","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":"We propose a language-agnostic way of automatically generating sets of semantically similar clusters of entities along with sets of \"outlier\" elements, which may then be used to perform an intrinsic evaluation of word embeddings in the outlier detection task. We used our methodology to create a gold-standard dataset, which we call WikiSem500, and evaluated multiple state-of-the-art embeddings. The results show a correlation between performance on this dataset and performance on sentiment analysis.","authors_text":"Joel Barry, Philip Blair, Yuval Merhav","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T21:35:07Z","title":"Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01547","kind":"arxiv","version":5},"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:d7f3823b44711dc807d8ab2944891f59d66b18c7eed98049989dc4e15d2674ee","target":"record","created_at":"2026-05-18T00:46:59Z","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":"ec21d18e4e967ec11000388faba82fadbddadee88e93ed3178819fb1c244eb54","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-04T21:35:07Z","title_canon_sha256":"4d088cb38639aa805124af33e29f6ec52eba46fb793701c99623b15b056edaf0"},"schema_version":"1.0","source":{"id":"1611.01547","kind":"arxiv","version":5}},"canonical_sha256":"32c687caf0c1ec2697800063e20e3cbf63a8771d35d9cfad4f83d331daeb1109","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32c687caf0c1ec2697800063e20e3cbf63a8771d35d9cfad4f83d331daeb1109","first_computed_at":"2026-05-18T00:46:59.354893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:59.354893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jNAUGfSHTBdliT30CQ+e60VbhzcVCazDDw3DkZHSVNOuOREexaRdkH4qcvigSu2DlzeNGRKkWoubM07yqGMzDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:59.355874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01547","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7f3823b44711dc807d8ab2944891f59d66b18c7eed98049989dc4e15d2674ee","sha256:8a162d900c8b5b3255c9b92ad113f31d92f7e775f1a51b31a0620f9da132c4a0"],"state_sha256":"8919046084535cd3a455efdfd24f72488462cc4e77e26e4cb0432f90fdb13f5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8+QKqKSnOZKgucHnqlBBxfT9xXxmW1ikm6PybJAHrI66InlH32raIDejACZmoFuYFC9xSYm3X5yGruEfbOUBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:21:32.614773Z","bundle_sha256":"48d9973ce313418e1a825ea9c5d29f139006733b3e92232aa4bb68057a7caf2f"}}