{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HYANKPKWGWQXGRZ4CBFRK4AS5K","short_pith_number":"pith:HYANKPKW","canonical_record":{"source":{"id":"1708.01766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-05T13:21:01Z","cross_cats_sorted":[],"title_canon_sha256":"3cab77bb5cb5fa93c01ae3a9567a338988dcc81341760b9a5bf3e270c06b992d","abstract_canon_sha256":"5dbe3162f7d996e82bc1eba069189a6556d8f91de52d7a4f590abd4e9dba7752"},"schema_version":"1.0"},"canonical_sha256":"3e00d53d5635a173473c104b157012eab52ea3304e48acc6d17c25a9e981e359","source":{"kind":"arxiv","id":"1708.01766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01766","created_at":"2026-05-18T00:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01766v1","created_at":"2026-05-18T00:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01766","created_at":"2026-05-18T00:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"HYANKPKWGWQX","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"HYANKPKWGWQXGRZ4","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"HYANKPKW","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HYANKPKWGWQXGRZ4CBFRK4AS5K","target":"record","payload":{"canonical_record":{"source":{"id":"1708.01766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-05T13:21:01Z","cross_cats_sorted":[],"title_canon_sha256":"3cab77bb5cb5fa93c01ae3a9567a338988dcc81341760b9a5bf3e270c06b992d","abstract_canon_sha256":"5dbe3162f7d996e82bc1eba069189a6556d8f91de52d7a4f590abd4e9dba7752"},"schema_version":"1.0"},"canonical_sha256":"3e00d53d5635a173473c104b157012eab52ea3304e48acc6d17c25a9e981e359","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:33.224776Z","signature_b64":"5NNTC4/BGimH4TG5T8Hmp+lficPGNKeHAe5MAcs0wyb8NBTJMSxcrVSglyAv09EDpJW8UKYUuRcS5eQheWQKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e00d53d5635a173473c104b157012eab52ea3304e48acc6d17c25a9e981e359","last_reissued_at":"2026-05-18T00:38:33.224408Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:33.224408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.01766","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":"2026-05-18T00:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVcxY35mLePz1Y7kk4vfzqHhjwN22hjCY1YzMje2WSv2IDRbUu9oRd5z8C8Z8J+y8TVfkj0XShPLk7UvmgkuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:59:00.861474Z"},"content_sha256":"1cbd855c9e4dc9dd56250169e2566c48c021b5e56f11a0f5fbbb59c4bc0b48db","schema_version":"1.0","event_id":"sha256:1cbd855c9e4dc9dd56250169e2566c48c021b5e56f11a0f5fbbb59c4bc0b48db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HYANKPKWGWQXGRZ4CBFRK4AS5K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Syllable-based Technique for Word Embeddings of Korean Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinseok Seol, Sang-goo Lee, Sanghyuk Choi, Taeuk Kim","submitted_at":"2017-08-05T13:21:01Z","abstract_excerpt":"Word embedding has become a fundamental component to many NLP tasks such as named entity recognition and machine translation. However, popular models that learn such embeddings are unaware of the morphology of words, so it is not directly applicable to highly agglutinative languages such as Korean. We propose a syllable-based learning model for Korean using a convolutional neural network, in which word representation is composed of trained syllable vectors. Our model successfully produces morphologically meaningful representation of Korean words compared to the original Skip-gram embeddings. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01766","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":"2026-05-18T00:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w9yYuvwWJp89UsxhQvLnGW2OsnbTEcYjANMZ9M4N9iV9wkHj+op/fAz3q9O0RBAOIU+5XuGptM6SwbXNDOtaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:59:00.861819Z"},"content_sha256":"757519d8034b370afc33c9b56739620beff13a99a008469843ebd7197f5e5076","schema_version":"1.0","event_id":"sha256:757519d8034b370afc33c9b56739620beff13a99a008469843ebd7197f5e5076"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HYANKPKWGWQXGRZ4CBFRK4AS5K/bundle.json","state_url":"https://pith.science/pith/HYANKPKWGWQXGRZ4CBFRK4AS5K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HYANKPKWGWQXGRZ4CBFRK4AS5K/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":"2026-06-01T04:59:00Z","links":{"resolver":"https://pith.science/pith/HYANKPKWGWQXGRZ4CBFRK4AS5K","bundle":"https://pith.science/pith/HYANKPKWGWQXGRZ4CBFRK4AS5K/bundle.json","state":"https://pith.science/pith/HYANKPKWGWQXGRZ4CBFRK4AS5K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HYANKPKWGWQXGRZ4CBFRK4AS5K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HYANKPKWGWQXGRZ4CBFRK4AS5K","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":"5dbe3162f7d996e82bc1eba069189a6556d8f91de52d7a4f590abd4e9dba7752","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-05T13:21:01Z","title_canon_sha256":"3cab77bb5cb5fa93c01ae3a9567a338988dcc81341760b9a5bf3e270c06b992d"},"schema_version":"1.0","source":{"id":"1708.01766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.01766","created_at":"2026-05-18T00:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"1708.01766v1","created_at":"2026-05-18T00:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01766","created_at":"2026-05-18T00:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"HYANKPKWGWQX","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"HYANKPKWGWQXGRZ4","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"HYANKPKW","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:757519d8034b370afc33c9b56739620beff13a99a008469843ebd7197f5e5076","target":"graph","created_at":"2026-05-18T00:38:33Z","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 embedding has become a fundamental component to many NLP tasks such as named entity recognition and machine translation. However, popular models that learn such embeddings are unaware of the morphology of words, so it is not directly applicable to highly agglutinative languages such as Korean. We propose a syllable-based learning model for Korean using a convolutional neural network, in which word representation is composed of trained syllable vectors. Our model successfully produces morphologically meaningful representation of Korean words compared to the original Skip-gram embeddings. T","authors_text":"Jinseok Seol, Sang-goo Lee, Sanghyuk Choi, Taeuk Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-05T13:21:01Z","title":"A Syllable-based Technique for Word Embeddings of Korean Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01766","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":"sha256:1cbd855c9e4dc9dd56250169e2566c48c021b5e56f11a0f5fbbb59c4bc0b48db","target":"record","created_at":"2026-05-18T00:38:33Z","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":"5dbe3162f7d996e82bc1eba069189a6556d8f91de52d7a4f590abd4e9dba7752","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-05T13:21:01Z","title_canon_sha256":"3cab77bb5cb5fa93c01ae3a9567a338988dcc81341760b9a5bf3e270c06b992d"},"schema_version":"1.0","source":{"id":"1708.01766","kind":"arxiv","version":1}},"canonical_sha256":"3e00d53d5635a173473c104b157012eab52ea3304e48acc6d17c25a9e981e359","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e00d53d5635a173473c104b157012eab52ea3304e48acc6d17c25a9e981e359","first_computed_at":"2026-05-18T00:38:33.224408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:33.224408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5NNTC4/BGimH4TG5T8Hmp+lficPGNKeHAe5MAcs0wyb8NBTJMSxcrVSglyAv09EDpJW8UKYUuRcS5eQheWQKBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:33.224776Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.01766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cbd855c9e4dc9dd56250169e2566c48c021b5e56f11a0f5fbbb59c4bc0b48db","sha256:757519d8034b370afc33c9b56739620beff13a99a008469843ebd7197f5e5076"],"state_sha256":"5b2eabdbd3dc46cf8e478ae65bbcca48fb51b38c9b5fd0083d357c5b2bbcfe1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1N4LWv+WNcRA4xBcApSOBhbZ0CU4EJmP44uUvUbjUbra/DcNnHP2tpRIHVThT/MuwL++MVGLrF672YF0ygMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:59:00.863890Z","bundle_sha256":"7eb50b757aca73c1229576d40285abc6fba308c20b380648a06885ef01262198"}}