{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RXWLJSHLFVEHOKXN4IUMLZT6OI","short_pith_number":"pith:RXWLJSHL","canonical_record":{"source":{"id":"1709.00028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-31T18:19:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"646cd73acfc4befb39b5290d56b9a4e1d8daaad837ed1e64679c7a7ea114d4f4","abstract_canon_sha256":"0af4954fe9014da7bbafaa749d9eb8161b4f9666b00be1fe89376edb0cefa599"},"schema_version":"1.0"},"canonical_sha256":"8decb4c8eb2d48772aede228c5e67e7201fffd110f52377703b51d47891b6856","source":{"kind":"arxiv","id":"1709.00028","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00028","created_at":"2026-05-18T00:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00028v1","created_at":"2026-05-18T00:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00028","created_at":"2026-05-18T00:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"RXWLJSHLFVEH","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RXWLJSHLFVEHOKXN","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RXWLJSHL","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RXWLJSHLFVEHOKXN4IUMLZT6OI","target":"record","payload":{"canonical_record":{"source":{"id":"1709.00028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-31T18:19:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"646cd73acfc4befb39b5290d56b9a4e1d8daaad837ed1e64679c7a7ea114d4f4","abstract_canon_sha256":"0af4954fe9014da7bbafaa749d9eb8161b4f9666b00be1fe89376edb0cefa599"},"schema_version":"1.0"},"canonical_sha256":"8decb4c8eb2d48772aede228c5e67e7201fffd110f52377703b51d47891b6856","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:12.278899Z","signature_b64":"GbHgUymqqiEpHsqYmC8f0W9u0cXFtD+m8hITJL/Z118fMPWw5cpWMLDBl2hTU9ZJbzSZeg2FG9/EtZm9v2p8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8decb4c8eb2d48772aede228c5e67e7201fffd110f52377703b51d47891b6856","last_reissued_at":"2026-05-18T00:06:12.278330Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:12.278330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.00028","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":"2026-05-18T00:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9nqT5bsyF8C5eKJFhbFz2fVCuZfFo2qV+rYYeagFkvrttrK4w0d2ZQFzqeCQuzasHl24OKH5uaLnhA70o7xAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:25:46.352029Z"},"content_sha256":"3eb5dfc20f112376c1eda153e71bc193e9c57645d5d17af3fba1b5b8f499190c","schema_version":"1.0","event_id":"sha256:3eb5dfc20f112376c1eda153e71bc193e9c57645d5d17af3fba1b5b8f499190c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RXWLJSHLFVEHOKXN4IUMLZT6OI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Glyph-aware Embedding of Chinese Characters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Falcon Z. Dai, Zheng Cai","submitted_at":"2017-08-31T18:19:08Z","abstract_excerpt":"Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common substructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a character's glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00028","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":"2026-05-18T00:06:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1a7dzUfNldEioR3UBhC0Nfd1H//heHh2SmBnb1KTMyH8YSjKgTUT9yirYLj4yfRpuasQed8GDpagBw6CBw0RDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:25:46.352731Z"},"content_sha256":"cb56d643bcae183fe246abb374575c078a5579eb347630a8e8607af391ecbb0c","schema_version":"1.0","event_id":"sha256:cb56d643bcae183fe246abb374575c078a5579eb347630a8e8607af391ecbb0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXWLJSHLFVEHOKXN4IUMLZT6OI/bundle.json","state_url":"https://pith.science/pith/RXWLJSHLFVEHOKXN4IUMLZT6OI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXWLJSHLFVEHOKXN4IUMLZT6OI/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":"2026-06-11T21:25:46Z","links":{"resolver":"https://pith.science/pith/RXWLJSHLFVEHOKXN4IUMLZT6OI","bundle":"https://pith.science/pith/RXWLJSHLFVEHOKXN4IUMLZT6OI/bundle.json","state":"https://pith.science/pith/RXWLJSHLFVEHOKXN4IUMLZT6OI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXWLJSHLFVEHOKXN4IUMLZT6OI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RXWLJSHLFVEHOKXN4IUMLZT6OI","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":"0af4954fe9014da7bbafaa749d9eb8161b4f9666b00be1fe89376edb0cefa599","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-31T18:19:08Z","title_canon_sha256":"646cd73acfc4befb39b5290d56b9a4e1d8daaad837ed1e64679c7a7ea114d4f4"},"schema_version":"1.0","source":{"id":"1709.00028","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00028","created_at":"2026-05-18T00:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00028v1","created_at":"2026-05-18T00:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00028","created_at":"2026-05-18T00:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"RXWLJSHLFVEH","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"RXWLJSHLFVEHOKXN","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"RXWLJSHL","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:cb56d643bcae183fe246abb374575c078a5579eb347630a8e8607af391ecbb0c","target":"graph","created_at":"2026-05-18T00:06:12Z","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":"Given the advantage and recent success of English character-level and subword-unit models in several NLP tasks, we consider the equivalent modeling problem for Chinese. Chinese script is logographic and many Chinese logograms are composed of common substructures that provide semantic, phonetic and syntactic hints. In this work, we propose to explicitly incorporate the visual appearance of a character's glyph in its representation, resulting in a novel glyph-aware embedding of Chinese characters. Being inspired by the success of convolutional neural networks in computer vision, we use them to i","authors_text":"Falcon Z. Dai, Zheng Cai","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-31T18:19:08Z","title":"Glyph-aware Embedding of Chinese Characters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00028","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":"sha256:3eb5dfc20f112376c1eda153e71bc193e9c57645d5d17af3fba1b5b8f499190c","target":"record","created_at":"2026-05-18T00:06:12Z","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":"0af4954fe9014da7bbafaa749d9eb8161b4f9666b00be1fe89376edb0cefa599","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-31T18:19:08Z","title_canon_sha256":"646cd73acfc4befb39b5290d56b9a4e1d8daaad837ed1e64679c7a7ea114d4f4"},"schema_version":"1.0","source":{"id":"1709.00028","kind":"arxiv","version":1}},"canonical_sha256":"8decb4c8eb2d48772aede228c5e67e7201fffd110f52377703b51d47891b6856","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8decb4c8eb2d48772aede228c5e67e7201fffd110f52377703b51d47891b6856","first_computed_at":"2026-05-18T00:06:12.278330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:12.278330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GbHgUymqqiEpHsqYmC8f0W9u0cXFtD+m8hITJL/Z118fMPWw5cpWMLDBl2hTU9ZJbzSZeg2FG9/EtZm9v2p8AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:12.278899Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00028","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eb5dfc20f112376c1eda153e71bc193e9c57645d5d17af3fba1b5b8f499190c","sha256:cb56d643bcae183fe246abb374575c078a5579eb347630a8e8607af391ecbb0c"],"state_sha256":"3f81b50a8528c0121e99ec14cf631fb188b818acd79d9372bafe42e40cad725c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+vRoNY3OG3rjpDgXmu6MF9B6PcnjhWl/tbjmt7ZfA/hTqNb9w47QqkUDIvoF7lGaLORyzBGwMEMetHhlTprDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T21:25:46.356511Z","bundle_sha256":"cf2676525cb6c4119f4fe596e7b67b192bdf79d7eb0814a7b1e8b21c73f812f4"}}