{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MCHFW2STC33UPI3T45ZCWQN6UB","short_pith_number":"pith:MCHFW2ST","canonical_record":{"source":{"id":"1707.06961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T16:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"0be00a293e5dc58249c7975efaf1615d63d97978c65b79c918295f42ef0ac05b","abstract_canon_sha256":"0890d46f328e227799cb7b92272265bcb6bd0f317f17e8874cebcf119e8b512d"},"schema_version":"1.0"},"canonical_sha256":"608e5b6a5316f747a373e7722b41bea071c1c6aafa8d4acea0b500a3c57b345a","source":{"kind":"arxiv","id":"1707.06961","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06961","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06961v1","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06961","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"MCHFW2STC33U","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MCHFW2STC33UPI3T","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MCHFW2ST","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MCHFW2STC33UPI3T45ZCWQN6UB","target":"record","payload":{"canonical_record":{"source":{"id":"1707.06961","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T16:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"0be00a293e5dc58249c7975efaf1615d63d97978c65b79c918295f42ef0ac05b","abstract_canon_sha256":"0890d46f328e227799cb7b92272265bcb6bd0f317f17e8874cebcf119e8b512d"},"schema_version":"1.0"},"canonical_sha256":"608e5b6a5316f747a373e7722b41bea071c1c6aafa8d4acea0b500a3c57b345a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:51.012215Z","signature_b64":"9ER/EVbTvsUY9LDl30K2n9VGlL3360N24W16g0nXi1PqIH+ZCr+N8jGpnyuKMcNP8N66G+4hXK2JkLMNcjEPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"608e5b6a5316f747a373e7722b41bea071c1c6aafa8d4acea0b500a3c57b345a","last_reissued_at":"2026-05-18T00:39:51.011659Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:51.011659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.06961","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":"2026-05-18T00:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6aBOOi0tA5ZjvTx6lw+J43FQuC7skR3xokp9dTvOn3L6yMkN4BldwVfQuyxXcoaFPSXAtaCcYon7tRXiL82BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T14:43:53.791431Z"},"content_sha256":"8b1db820eda35bccaa51fc54759058a581df261f0775725620d09c32cce78f28","schema_version":"1.0","event_id":"sha256:8b1db820eda35bccaa51fc54759058a581df261f0775725620d09c32cce78f28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MCHFW2STC33UPI3T45ZCWQN6UB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mimicking Word Embeddings using Subword RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jacob Eisenstein, Robert Guthrie, Yuval Pinter","submitted_at":"2017-07-21T16:18:10Z","abstract_excerpt":"Word embeddings improve generalization over lexical features by placing each word in a lower-dimensional space, using distributional information obtained from unlabeled data. However, the effectiveness of word embeddings for downstream NLP tasks is limited by out-of-vocabulary (OOV) words, for which embeddings do not exist. In this paper, we present MIMICK, an approach to generating OOV word embeddings compositionally, by learning a function from spellings to distributional embeddings. Unlike prior work, MIMICK does not require re-training on the original word embedding corpus; instead, learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06961","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":"2026-05-18T00:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fr9B3fDxVLBr2/jxUr2zM8zTpGxprA175U2fQCwnMmX1H6ZnBgjxMMLDEPtjEnAYx8V6LynTXmNfqwkwCkAVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T14:43:53.792117Z"},"content_sha256":"797accdc09c405fa3d9f9ce3b8dad34f2474386d3f48d4bf1232bedac6fe99d5","schema_version":"1.0","event_id":"sha256:797accdc09c405fa3d9f9ce3b8dad34f2474386d3f48d4bf1232bedac6fe99d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCHFW2STC33UPI3T45ZCWQN6UB/bundle.json","state_url":"https://pith.science/pith/MCHFW2STC33UPI3T45ZCWQN6UB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCHFW2STC33UPI3T45ZCWQN6UB/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":"2026-05-29T14:43:53Z","links":{"resolver":"https://pith.science/pith/MCHFW2STC33UPI3T45ZCWQN6UB","bundle":"https://pith.science/pith/MCHFW2STC33UPI3T45ZCWQN6UB/bundle.json","state":"https://pith.science/pith/MCHFW2STC33UPI3T45ZCWQN6UB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCHFW2STC33UPI3T45ZCWQN6UB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MCHFW2STC33UPI3T45ZCWQN6UB","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":"0890d46f328e227799cb7b92272265bcb6bd0f317f17e8874cebcf119e8b512d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T16:18:10Z","title_canon_sha256":"0be00a293e5dc58249c7975efaf1615d63d97978c65b79c918295f42ef0ac05b"},"schema_version":"1.0","source":{"id":"1707.06961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06961","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06961v1","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06961","created_at":"2026-05-18T00:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"MCHFW2STC33U","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MCHFW2STC33UPI3T","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MCHFW2ST","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:797accdc09c405fa3d9f9ce3b8dad34f2474386d3f48d4bf1232bedac6fe99d5","target":"graph","created_at":"2026-05-18T00:39:51Z","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":"Word embeddings improve generalization over lexical features by placing each word in a lower-dimensional space, using distributional information obtained from unlabeled data. However, the effectiveness of word embeddings for downstream NLP tasks is limited by out-of-vocabulary (OOV) words, for which embeddings do not exist. In this paper, we present MIMICK, an approach to generating OOV word embeddings compositionally, by learning a function from spellings to distributional embeddings. Unlike prior work, MIMICK does not require re-training on the original word embedding corpus; instead, learni","authors_text":"Jacob Eisenstein, Robert Guthrie, Yuval Pinter","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T16:18:10Z","title":"Mimicking Word Embeddings using Subword RNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06961","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":"sha256:8b1db820eda35bccaa51fc54759058a581df261f0775725620d09c32cce78f28","target":"record","created_at":"2026-05-18T00:39:51Z","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":"0890d46f328e227799cb7b92272265bcb6bd0f317f17e8874cebcf119e8b512d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-21T16:18:10Z","title_canon_sha256":"0be00a293e5dc58249c7975efaf1615d63d97978c65b79c918295f42ef0ac05b"},"schema_version":"1.0","source":{"id":"1707.06961","kind":"arxiv","version":1}},"canonical_sha256":"608e5b6a5316f747a373e7722b41bea071c1c6aafa8d4acea0b500a3c57b345a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"608e5b6a5316f747a373e7722b41bea071c1c6aafa8d4acea0b500a3c57b345a","first_computed_at":"2026-05-18T00:39:51.011659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:51.011659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ER/EVbTvsUY9LDl30K2n9VGlL3360N24W16g0nXi1PqIH+ZCr+N8jGpnyuKMcNP8N66G+4hXK2JkLMNcjEPCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:51.012215Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b1db820eda35bccaa51fc54759058a581df261f0775725620d09c32cce78f28","sha256:797accdc09c405fa3d9f9ce3b8dad34f2474386d3f48d4bf1232bedac6fe99d5"],"state_sha256":"272e20103061c63166b500a4f8041fc8299b8ff45ef50d7655d11debb968d6c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9kzAyXJotDw3H8w8wMfDhALhk28O0girnYvX7qRlRxihBRoLTqVGGrkj47ncABYOQ/wk+sJT6s+YEvd04C3mBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T14:43:53.796157Z","bundle_sha256":"ab0e96b740e6052c2ec67343e81283404f885a5f35273b1cffe0c0e8f5d2c1a6"}}