{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DEV2XU6XGZ3E4WSDP22FXSO46R","short_pith_number":"pith:DEV2XU6X","canonical_record":{"source":{"id":"1811.02364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T14:24:37Z","cross_cats_sorted":[],"title_canon_sha256":"307cd65f65e2e412d9dd5cf2e45caf48f074fcd609a751aecc55a7b9fdb5ad43","abstract_canon_sha256":"6d378030dfcbcc580b2d962e7b27995d3a08b4b1aa4043c122bc3adbbdf9cb6e"},"schema_version":"1.0"},"canonical_sha256":"192babd3d736764e5a437eb45bc9dcf4579dd4d403ea48930bf159933c28d111","source":{"kind":"arxiv","id":"1811.02364","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02364","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02364v2","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02364","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"DEV2XU6XGZ3E","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DEV2XU6XGZ3E4WSD","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DEV2XU6X","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DEV2XU6XGZ3E4WSDP22FXSO46R","target":"record","payload":{"canonical_record":{"source":{"id":"1811.02364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T14:24:37Z","cross_cats_sorted":[],"title_canon_sha256":"307cd65f65e2e412d9dd5cf2e45caf48f074fcd609a751aecc55a7b9fdb5ad43","abstract_canon_sha256":"6d378030dfcbcc580b2d962e7b27995d3a08b4b1aa4043c122bc3adbbdf9cb6e"},"schema_version":"1.0"},"canonical_sha256":"192babd3d736764e5a437eb45bc9dcf4579dd4d403ea48930bf159933c28d111","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:42.919250Z","signature_b64":"i54tyUZil0SMhrRShfit20qOAbWeuDK6snD/VUhlI2GPMPh7PzQnvzpj/xeCbDI9QM8yq87bKem6q1XhhXXnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"192babd3d736764e5a437eb45bc9dcf4579dd4d403ea48930bf159933c28d111","last_reissued_at":"2026-05-17T23:43:42.918462Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:42.918462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.02364","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Z/10cfP42MpxhC64O12vf0hzI4TbSRFbu2ft5yHplyJZhkTVCD5aONbZrEh7FeGp6J0ZA+ZasuV+5ST+lGkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T19:57:34.189288Z"},"content_sha256":"b999ac6fe3c7be169a5ff4e250222198c67f79e692760f2a6f444bb5fe72935a","schema_version":"1.0","event_id":"sha256:b999ac6fe3c7be169a5ff4e250222198c67f79e692760f2a6f444bb5fe72935a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DEV2XU6XGZ3E4WSDP22FXSO46R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Subword Segmentation for Text Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guohong Fu, Hai Zhao, Jiangtong Li, Kangwei Ling, Shexia He, Zhuosheng Zhang, Zuchao Li","submitted_at":"2018-11-06T14:24:37Z","abstract_excerpt":"Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or complex words. However, character itself is not a natural minimal linguistic unit for representation or word embedding composing due to ignoring the linguistic coherence of consecutive characters inside word. This paper presents a general subword-augmented embedding framework for learning and composing computationally-derived subword-level representations. We s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02364","kind":"arxiv","version":2},"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":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VRcd9iASN9OPycb8W4XmqjN396D8qpO861SozVsk106+q1SzZ/8uDDAooxtvp5fxMxZCp3okrNxhy30yuF7BCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T19:57:34.189990Z"},"content_sha256":"d0e21950a15fce1b75a1ff46ee167df081d6da874c993eddf98eb3191270c35b","schema_version":"1.0","event_id":"sha256:d0e21950a15fce1b75a1ff46ee167df081d6da874c993eddf98eb3191270c35b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DEV2XU6XGZ3E4WSDP22FXSO46R/bundle.json","state_url":"https://pith.science/pith/DEV2XU6XGZ3E4WSDP22FXSO46R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DEV2XU6XGZ3E4WSDP22FXSO46R/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":"2026-05-20T19:57:34Z","links":{"resolver":"https://pith.science/pith/DEV2XU6XGZ3E4WSDP22FXSO46R","bundle":"https://pith.science/pith/DEV2XU6XGZ3E4WSDP22FXSO46R/bundle.json","state":"https://pith.science/pith/DEV2XU6XGZ3E4WSDP22FXSO46R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DEV2XU6XGZ3E4WSDP22FXSO46R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DEV2XU6XGZ3E4WSDP22FXSO46R","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":"6d378030dfcbcc580b2d962e7b27995d3a08b4b1aa4043c122bc3adbbdf9cb6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T14:24:37Z","title_canon_sha256":"307cd65f65e2e412d9dd5cf2e45caf48f074fcd609a751aecc55a7b9fdb5ad43"},"schema_version":"1.0","source":{"id":"1811.02364","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.02364","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.02364v2","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02364","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"DEV2XU6XGZ3E","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DEV2XU6XGZ3E4WSD","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DEV2XU6X","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:d0e21950a15fce1b75a1ff46ee167df081d6da874c993eddf98eb3191270c35b","target":"graph","created_at":"2026-05-17T23:43:42Z","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":"Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or complex words. However, character itself is not a natural minimal linguistic unit for representation or word embedding composing due to ignoring the linguistic coherence of consecutive characters inside word. This paper presents a general subword-augmented embedding framework for learning and composing computationally-derived subword-level representations. We s","authors_text":"Guohong Fu, Hai Zhao, Jiangtong Li, Kangwei Ling, Shexia He, Zhuosheng Zhang, Zuchao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T14:24:37Z","title":"Effective Subword Segmentation for Text Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02364","kind":"arxiv","version":2},"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:b999ac6fe3c7be169a5ff4e250222198c67f79e692760f2a6f444bb5fe72935a","target":"record","created_at":"2026-05-17T23:43:42Z","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":"6d378030dfcbcc580b2d962e7b27995d3a08b4b1aa4043c122bc3adbbdf9cb6e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T14:24:37Z","title_canon_sha256":"307cd65f65e2e412d9dd5cf2e45caf48f074fcd609a751aecc55a7b9fdb5ad43"},"schema_version":"1.0","source":{"id":"1811.02364","kind":"arxiv","version":2}},"canonical_sha256":"192babd3d736764e5a437eb45bc9dcf4579dd4d403ea48930bf159933c28d111","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"192babd3d736764e5a437eb45bc9dcf4579dd4d403ea48930bf159933c28d111","first_computed_at":"2026-05-17T23:43:42.918462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:42.918462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i54tyUZil0SMhrRShfit20qOAbWeuDK6snD/VUhlI2GPMPh7PzQnvzpj/xeCbDI9QM8yq87bKem6q1XhhXXnCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:42.919250Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.02364","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b999ac6fe3c7be169a5ff4e250222198c67f79e692760f2a6f444bb5fe72935a","sha256:d0e21950a15fce1b75a1ff46ee167df081d6da874c993eddf98eb3191270c35b"],"state_sha256":"77b6b826ac79d6c0c7372bf6e063ba0c7625c8d9269d516591b3e6de594438a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/0EnUA2L4WTEckE4z5xCDU0F+jjEOXP7bOzEYzbhzvZvGeX9Syz5d3ogecDC2+uheBRzME6H5tRiRWfUM+XDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T19:57:34.193428Z","bundle_sha256":"9baea700c63afc66b5716d0002bc21be9952bcd6b1be45c91035824cda39c3ca"}}