{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RACF3QJ3665WXHT54ZWIEVPIAK","short_pith_number":"pith:RACF3QJ3","canonical_record":{"source":{"id":"1804.05262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-14T18:30:01Z","cross_cats_sorted":[],"title_canon_sha256":"6de6f8b09298afc8c24719c8d2c391eb77924d5de5260eb639fbeba1aeeb567a","abstract_canon_sha256":"de146062c0fee3402f4b56eac119724d2b9a00972b7292668b21d50879d1e04c"},"schema_version":"1.0"},"canonical_sha256":"88045dc13bf7bb6b9e7de66c8255e802a0855d34f7cc7739a259f99ecbec998a","source":{"kind":"arxiv","id":"1804.05262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05262","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05262v1","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05262","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"RACF3QJ3665W","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RACF3QJ3665WXHT5","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RACF3QJ3","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RACF3QJ3665WXHT54ZWIEVPIAK","target":"record","payload":{"canonical_record":{"source":{"id":"1804.05262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-14T18:30:01Z","cross_cats_sorted":[],"title_canon_sha256":"6de6f8b09298afc8c24719c8d2c391eb77924d5de5260eb639fbeba1aeeb567a","abstract_canon_sha256":"de146062c0fee3402f4b56eac119724d2b9a00972b7292668b21d50879d1e04c"},"schema_version":"1.0"},"canonical_sha256":"88045dc13bf7bb6b9e7de66c8255e802a0855d34f7cc7739a259f99ecbec998a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:28.472756Z","signature_b64":"4yevMTMeh3VzN1jGj6vfskuRrem6/KFfkEfZzMJoTqQemLsADrIqxE/b2vG5lvinxyKbx47BUKzknZx3PvctBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88045dc13bf7bb6b9e7de66c8255e802a0855d34f7cc7739a259f99ecbec998a","last_reissued_at":"2026-05-18T00:18:28.472393Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:28.472393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.05262","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":"2026-05-18T00:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhY1QBPxwCj8cjxmp8vHO66S/u5siXK1KjiQtUcY+PCHg21rhBwDik9n6d6j9ALdty5xrHHJhIekh0jx5n8BBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T15:32:01.750534Z"},"content_sha256":"7c220b2d9f2aece4397549230c93a332ab1f8982f8a59c5a63e25f5c4c609ff3","schema_version":"1.0","event_id":"sha256:7c220b2d9f2aece4397549230c93a332ab1f8982f8a59c5a63e25f5c4c609ff3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RACF3QJ3665WXHT54ZWIEVPIAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danushka Bollegala, Joshua Coates","submitted_at":"2018-04-14T18:30:01Z","abstract_excerpt":"Creating accurate meta-embeddings from pre-trained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have shown to produce accurate meta-embeddings. In this paper, we show that the arithmetic mean of two distinct word embedding sets yields a performant meta-embedding that is comparable or better than more complex meta-embedding learning methods. The result seems counter-intuitive given that vector spaces in different source embeddings are not comparable and cannot be simply averaged. We give insight into why averaging c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05262","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":"2026-05-18T00:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQSFIYRZa3ZDVhLC25NJLQtHOF0vr3Z/vCWNQqN2PFA1SloDSHATEcps7AxkFe2KVpf+JakxW+h9kxS9BroIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T15:32:01.750872Z"},"content_sha256":"5b5c1ea74d7eb5d178b5eaf62ffced68c85585ac012fd3278b7c5b27b296d479","schema_version":"1.0","event_id":"sha256:5b5c1ea74d7eb5d178b5eaf62ffced68c85585ac012fd3278b7c5b27b296d479"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RACF3QJ3665WXHT54ZWIEVPIAK/bundle.json","state_url":"https://pith.science/pith/RACF3QJ3665WXHT54ZWIEVPIAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RACF3QJ3665WXHT54ZWIEVPIAK/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":"2026-06-23T15:32:01Z","links":{"resolver":"https://pith.science/pith/RACF3QJ3665WXHT54ZWIEVPIAK","bundle":"https://pith.science/pith/RACF3QJ3665WXHT54ZWIEVPIAK/bundle.json","state":"https://pith.science/pith/RACF3QJ3665WXHT54ZWIEVPIAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RACF3QJ3665WXHT54ZWIEVPIAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RACF3QJ3665WXHT54ZWIEVPIAK","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":"de146062c0fee3402f4b56eac119724d2b9a00972b7292668b21d50879d1e04c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-14T18:30:01Z","title_canon_sha256":"6de6f8b09298afc8c24719c8d2c391eb77924d5de5260eb639fbeba1aeeb567a"},"schema_version":"1.0","source":{"id":"1804.05262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05262","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05262v1","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05262","created_at":"2026-05-18T00:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"RACF3QJ3665W","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RACF3QJ3665WXHT5","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RACF3QJ3","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:5b5c1ea74d7eb5d178b5eaf62ffced68c85585ac012fd3278b7c5b27b296d479","target":"graph","created_at":"2026-05-18T00:18:28Z","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":"Creating accurate meta-embeddings from pre-trained source embeddings has received attention lately. Methods based on global and locally-linear transformation and concatenation have shown to produce accurate meta-embeddings. In this paper, we show that the arithmetic mean of two distinct word embedding sets yields a performant meta-embedding that is comparable or better than more complex meta-embedding learning methods. The result seems counter-intuitive given that vector spaces in different source embeddings are not comparable and cannot be simply averaged. We give insight into why averaging c","authors_text":"Danushka Bollegala, Joshua Coates","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-14T18:30:01Z","title":"Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05262","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":"sha256:7c220b2d9f2aece4397549230c93a332ab1f8982f8a59c5a63e25f5c4c609ff3","target":"record","created_at":"2026-05-18T00:18:28Z","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":"de146062c0fee3402f4b56eac119724d2b9a00972b7292668b21d50879d1e04c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-14T18:30:01Z","title_canon_sha256":"6de6f8b09298afc8c24719c8d2c391eb77924d5de5260eb639fbeba1aeeb567a"},"schema_version":"1.0","source":{"id":"1804.05262","kind":"arxiv","version":1}},"canonical_sha256":"88045dc13bf7bb6b9e7de66c8255e802a0855d34f7cc7739a259f99ecbec998a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88045dc13bf7bb6b9e7de66c8255e802a0855d34f7cc7739a259f99ecbec998a","first_computed_at":"2026-05-18T00:18:28.472393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:28.472393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4yevMTMeh3VzN1jGj6vfskuRrem6/KFfkEfZzMJoTqQemLsADrIqxE/b2vG5lvinxyKbx47BUKzknZx3PvctBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:28.472756Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.05262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c220b2d9f2aece4397549230c93a332ab1f8982f8a59c5a63e25f5c4c609ff3","sha256:5b5c1ea74d7eb5d178b5eaf62ffced68c85585ac012fd3278b7c5b27b296d479"],"state_sha256":"3f57805a106c2b0e6e09e0f3bb01af2026d715bde4e80403d9faa8d14e7f2df1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ud6tqRQIDEXbzqdtEkjO/HccJqel64eQB12yBnoRhMQU9GYbz/uGhXrjDRR0qBKpW3fS5rQ3TFHQz8z53IvmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T15:32:01.752721Z","bundle_sha256":"4ca0a42b121a0371abe4c52d00fe514b0bfe6f5c4fd039110c35d88f41349b23"}}