{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FESIZO3663IY7TGQFMSKWS5EW5","short_pith_number":"pith:FESIZO36","canonical_record":{"source":{"id":"1907.11512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-26T12:29:37Z","cross_cats_sorted":[],"title_canon_sha256":"aa37dd3047af206a314dc8899016215d24be645b822e06fc4760c00eb99fcce0","abstract_canon_sha256":"ce21823dccb0142141c68acf760cdf1f8f123da8cb3fb1e3420d86f40710c317"},"schema_version":"1.0"},"canonical_sha256":"29248cbb7ef6d18fccd02b24ab4ba4b76e5f7cf9183449af2c654cca175a92cd","source":{"kind":"arxiv","id":"1907.11512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11512","created_at":"2026-05-17T23:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11512v1","created_at":"2026-05-17T23:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11512","created_at":"2026-05-17T23:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"FESIZO3663IY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FESIZO3663IY7TGQ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FESIZO36","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FESIZO3663IY7TGQFMSKWS5EW5","target":"record","payload":{"canonical_record":{"source":{"id":"1907.11512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-26T12:29:37Z","cross_cats_sorted":[],"title_canon_sha256":"aa37dd3047af206a314dc8899016215d24be645b822e06fc4760c00eb99fcce0","abstract_canon_sha256":"ce21823dccb0142141c68acf760cdf1f8f123da8cb3fb1e3420d86f40710c317"},"schema_version":"1.0"},"canonical_sha256":"29248cbb7ef6d18fccd02b24ab4ba4b76e5f7cf9183449af2c654cca175a92cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:28.856426Z","signature_b64":"1GPNpOTs+/MiSqAimw9G8Ut1qU2Afri3kdC4uN53PZwTCD2A21pLxYssyDGYGu4SP9nh+PTk8iuv8uoxvtuFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29248cbb7ef6d18fccd02b24ab4ba4b76e5f7cf9183449af2c654cca175a92cd","last_reissued_at":"2026-05-17T23:39:28.855908Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:28.855908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.11512","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":"2026-05-17T23:39:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p8CG0QaBPm8GxGh1Ai627crxXfH72hgGZpSBq9LQ4OT7vwnoOATP7YdbYvONvUT15KhOZtwMDsMRJxw+HY8FBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:58:17.228506Z"},"content_sha256":"1255de9f2b5c6bb1206e9221fbde82af7d943913c8dc01e412f25126d2a42e32","schema_version":"1.0","event_id":"sha256:1255de9f2b5c6bb1206e9221fbde82af7d943913c8dc01e412f25126d2a42e32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FESIZO3663IY7TGQFMSKWS5EW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Self-Attention Network for Chinese Word Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leilei Gan, Yue Zhang","submitted_at":"2019-07-26T12:29:37Z","abstract_excerpt":"Neural network has become the dominant method for Chinese word segmentation. Most existing models cast the task as sequence labeling, using BiLSTM-CRF for representing the input and making output predictions. Recently, attention-based sequence models have emerged as a highly competitive alternative to LSTMs, which allow better running speed by parallelization of computation. We investigate self attention network for Chinese word segmentation, making comparisons between BiLSTM-CRF models. In addition, the influence of contextualized character embeddings is investigated using BERT, and a method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11512","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":"2026-05-17T23:39:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1YPkaG3zLwogc0dVf5WGEkCMXmSRbsB7Y4edi8wJ72bRyWopPzSJU3fRn/lX4yUseUMIRdBhDzrtrqeBcOGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:58:17.228841Z"},"content_sha256":"82b8847fcb59cfcd5a6f127f4769758a91539dacd9e80932555c153b4394f7d1","schema_version":"1.0","event_id":"sha256:82b8847fcb59cfcd5a6f127f4769758a91539dacd9e80932555c153b4394f7d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FESIZO3663IY7TGQFMSKWS5EW5/bundle.json","state_url":"https://pith.science/pith/FESIZO3663IY7TGQFMSKWS5EW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FESIZO3663IY7TGQFMSKWS5EW5/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":"2026-06-07T06:58:17Z","links":{"resolver":"https://pith.science/pith/FESIZO3663IY7TGQFMSKWS5EW5","bundle":"https://pith.science/pith/FESIZO3663IY7TGQFMSKWS5EW5/bundle.json","state":"https://pith.science/pith/FESIZO3663IY7TGQFMSKWS5EW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FESIZO3663IY7TGQFMSKWS5EW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FESIZO3663IY7TGQFMSKWS5EW5","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":"ce21823dccb0142141c68acf760cdf1f8f123da8cb3fb1e3420d86f40710c317","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-26T12:29:37Z","title_canon_sha256":"aa37dd3047af206a314dc8899016215d24be645b822e06fc4760c00eb99fcce0"},"schema_version":"1.0","source":{"id":"1907.11512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.11512","created_at":"2026-05-17T23:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"1907.11512v1","created_at":"2026-05-17T23:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11512","created_at":"2026-05-17T23:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"FESIZO3663IY","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FESIZO3663IY7TGQ","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FESIZO36","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:82b8847fcb59cfcd5a6f127f4769758a91539dacd9e80932555c153b4394f7d1","target":"graph","created_at":"2026-05-17T23:39:28Z","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":"Neural network has become the dominant method for Chinese word segmentation. Most existing models cast the task as sequence labeling, using BiLSTM-CRF for representing the input and making output predictions. Recently, attention-based sequence models have emerged as a highly competitive alternative to LSTMs, which allow better running speed by parallelization of computation. We investigate self attention network for Chinese word segmentation, making comparisons between BiLSTM-CRF models. In addition, the influence of contextualized character embeddings is investigated using BERT, and a method ","authors_text":"Leilei Gan, Yue Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-26T12:29:37Z","title":"Investigating Self-Attention Network for Chinese Word Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11512","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":"sha256:1255de9f2b5c6bb1206e9221fbde82af7d943913c8dc01e412f25126d2a42e32","target":"record","created_at":"2026-05-17T23:39:28Z","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":"ce21823dccb0142141c68acf760cdf1f8f123da8cb3fb1e3420d86f40710c317","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-26T12:29:37Z","title_canon_sha256":"aa37dd3047af206a314dc8899016215d24be645b822e06fc4760c00eb99fcce0"},"schema_version":"1.0","source":{"id":"1907.11512","kind":"arxiv","version":1}},"canonical_sha256":"29248cbb7ef6d18fccd02b24ab4ba4b76e5f7cf9183449af2c654cca175a92cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29248cbb7ef6d18fccd02b24ab4ba4b76e5f7cf9183449af2c654cca175a92cd","first_computed_at":"2026-05-17T23:39:28.855908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:28.855908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1GPNpOTs+/MiSqAimw9G8Ut1qU2Afri3kdC4uN53PZwTCD2A21pLxYssyDGYGu4SP9nh+PTk8iuv8uoxvtuFCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:28.856426Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.11512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1255de9f2b5c6bb1206e9221fbde82af7d943913c8dc01e412f25126d2a42e32","sha256:82b8847fcb59cfcd5a6f127f4769758a91539dacd9e80932555c153b4394f7d1"],"state_sha256":"4549393e88cf87eac642a2ce50045129bd5a378830be555cec1bce3d02f53762"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YrZR/08qzbqJTyCH0KXLSuRmMgcooTi58GSbhyp4ndv+AQs2SUbi0zS/dEfbcbBJ6c3u4lmM0OBfHCufgyveDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:58:17.230661Z","bundle_sha256":"80140543de9472cdfec50326ef84549b311df2ba3e0241b2ff577afa7fbaaba3"}}