{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:G6M7KFRFGORSNS6OAYJ46A4OSB","short_pith_number":"pith:G6M7KFRF","canonical_record":{"source":{"id":"1809.04259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T05:15:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e944a98fc7e1ad5fa61b8a88afcec3ad38c5c658c730e2a3c657cfccd290168","abstract_canon_sha256":"7eb7cb6bf2d717224cbf6ff5b254dd089b0c5762785ebbcb2a0af0ed539c88d8"},"schema_version":"1.0"},"canonical_sha256":"3799f5162533a326cbce0613cf038e90643eb338eab5bce64261eddb3969d55d","source":{"kind":"arxiv","id":"1809.04259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04259","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04259v1","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04259","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"G6M7KFRFGORS","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G6M7KFRFGORSNS6O","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G6M7KFRF","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:G6M7KFRFGORSNS6OAYJ46A4OSB","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T05:15:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e944a98fc7e1ad5fa61b8a88afcec3ad38c5c658c730e2a3c657cfccd290168","abstract_canon_sha256":"7eb7cb6bf2d717224cbf6ff5b254dd089b0c5762785ebbcb2a0af0ed539c88d8"},"schema_version":"1.0"},"canonical_sha256":"3799f5162533a326cbce0613cf038e90643eb338eab5bce64261eddb3969d55d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:52.973826Z","signature_b64":"aKf1BH0TrDw+iSVUJpCc29dKb6WeuhTBRWgYi8xVLugp8nGIPlRP/BrDP3yc30lFFabexldI6K0eLuhXIGbAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3799f5162533a326cbce0613cf038e90643eb338eab5bce64261eddb3969d55d","last_reissued_at":"2026-05-18T00:05:52.973274Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:52.973274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04259","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":"2026-05-18T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkmoXAycqd8iM7FeUs1JHiBbH+iVqj2ir0Fb2YXw5twPwL2mJMIMn8X7c6y5DLqieLMWSRtwfCzxFXG4TcZ4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:58:46.249451Z"},"content_sha256":"bde7e4b0978243e7d004885f8c04b5cf1d1d8dd42751c5533d896aeb841b456c","schema_version":"1.0","event_id":"sha256:bde7e4b0978243e7d004885f8c04b5cf1d1d8dd42751c5533d896aeb841b456c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:G6M7KFRFGORSNS6OAYJ46A4OSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalizing Word Embeddings using Bag of Subwords","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinman Zhao, Sidharth Mudgal, Yingyu Liang","submitted_at":"2018-09-12T05:15:32Z","abstract_excerpt":"We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character $n$-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model's ability in capturing the relationship be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04259","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":"2026-05-18T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ZG0sDscXnXd5jqpTibbiwQGZuYBSa3q9nqcuoRfzwWX8hn217rRTRO9oA/oLILMsNcraKT9Hvt2Z+preTv1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:58:46.249802Z"},"content_sha256":"7e03cc47121b5f5028015178f95e607d602c29e6f43d0adbaef1ccb048adf4d2","schema_version":"1.0","event_id":"sha256:7e03cc47121b5f5028015178f95e607d602c29e6f43d0adbaef1ccb048adf4d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/bundle.json","state_url":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/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":"2026-06-04T03:58:46Z","links":{"resolver":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB","bundle":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/bundle.json","state":"https://pith.science/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G6M7KFRFGORSNS6OAYJ46A4OSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:G6M7KFRFGORSNS6OAYJ46A4OSB","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":"7eb7cb6bf2d717224cbf6ff5b254dd089b0c5762785ebbcb2a0af0ed539c88d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T05:15:32Z","title_canon_sha256":"4e944a98fc7e1ad5fa61b8a88afcec3ad38c5c658c730e2a3c657cfccd290168"},"schema_version":"1.0","source":{"id":"1809.04259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04259","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04259v1","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04259","created_at":"2026-05-18T00:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"G6M7KFRFGORS","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"G6M7KFRFGORSNS6O","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"G6M7KFRF","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:7e03cc47121b5f5028015178f95e607d602c29e6f43d0adbaef1ccb048adf4d2","target":"graph","created_at":"2026-05-18T00:05:52Z","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 approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of character $n$-grams. The model is simple, fast to train and provides good vectors for rare or unseen words. Experiments show that our model achieves state-of-the-art performances in English word similarity task and in joint prediction of part-of-speech tag and morphosyntactic attributes in 23 languages, suggesting our model's ability in capturing the relationship be","authors_text":"Jinman Zhao, Sidharth Mudgal, Yingyu Liang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T05:15:32Z","title":"Generalizing Word Embeddings using Bag of Subwords"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04259","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:bde7e4b0978243e7d004885f8c04b5cf1d1d8dd42751c5533d896aeb841b456c","target":"record","created_at":"2026-05-18T00:05:52Z","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":"7eb7cb6bf2d717224cbf6ff5b254dd089b0c5762785ebbcb2a0af0ed539c88d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T05:15:32Z","title_canon_sha256":"4e944a98fc7e1ad5fa61b8a88afcec3ad38c5c658c730e2a3c657cfccd290168"},"schema_version":"1.0","source":{"id":"1809.04259","kind":"arxiv","version":1}},"canonical_sha256":"3799f5162533a326cbce0613cf038e90643eb338eab5bce64261eddb3969d55d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3799f5162533a326cbce0613cf038e90643eb338eab5bce64261eddb3969d55d","first_computed_at":"2026-05-18T00:05:52.973274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:52.973274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aKf1BH0TrDw+iSVUJpCc29dKb6WeuhTBRWgYi8xVLugp8nGIPlRP/BrDP3yc30lFFabexldI6K0eLuhXIGbAAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:52.973826Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bde7e4b0978243e7d004885f8c04b5cf1d1d8dd42751c5533d896aeb841b456c","sha256:7e03cc47121b5f5028015178f95e607d602c29e6f43d0adbaef1ccb048adf4d2"],"state_sha256":"037b9ed75de01256bc4cdcc0a17577aebf95f06c3c5489d829cfe87210ee52d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eNUWAZ9O1GZTnkWde3jLyXB3jUQnoR4Et3OTZdDsXUwHCFe1wHRyxKt8LvT5jMEYuik0GYPttppwaJPBvjKSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T03:58:46.251694Z","bundle_sha256":"35ea02da68fc7b943d4a4fc5d3aeee9d9d113f1b76642c9bb39344026eb59d14"}}