{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:B7FLCQLAZ56NGGOC4XMOXJUAFY","short_pith_number":"pith:B7FLCQLA","canonical_record":{"source":{"id":"1811.10167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-26T03:58:09Z","cross_cats_sorted":[],"title_canon_sha256":"b1d45e37315a7dc21cfff63af2bd1969bf6b33025494fb7ee7f130b3fe80c567","abstract_canon_sha256":"d494e31b6c27c8edb895b776bdf73774484274bf7f67ef21f1d4ebcc7973a1c5"},"schema_version":"1.0"},"canonical_sha256":"0fcab14160cf7cd319c2e5d8eba6802e108e9a949e89797bb1dca8f415ca259a","source":{"kind":"arxiv","id":"1811.10167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10167","created_at":"2026-05-17T23:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10167v1","created_at":"2026-05-17T23:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10167","created_at":"2026-05-17T23:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"B7FLCQLAZ56N","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"B7FLCQLAZ56NGGOC","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"B7FLCQLA","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:B7FLCQLAZ56NGGOC4XMOXJUAFY","target":"record","payload":{"canonical_record":{"source":{"id":"1811.10167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-26T03:58:09Z","cross_cats_sorted":[],"title_canon_sha256":"b1d45e37315a7dc21cfff63af2bd1969bf6b33025494fb7ee7f130b3fe80c567","abstract_canon_sha256":"d494e31b6c27c8edb895b776bdf73774484274bf7f67ef21f1d4ebcc7973a1c5"},"schema_version":"1.0"},"canonical_sha256":"0fcab14160cf7cd319c2e5d8eba6802e108e9a949e89797bb1dca8f415ca259a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:57.183830Z","signature_b64":"590DyLCAppHGgFLhoYS6WXHYwbvfErWWmIw28FFiyiNOICuL/HDqVoO+7FYT4yrrJCPs4V4Tx6jB3WEalv75Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fcab14160cf7cd319c2e5d8eba6802e108e9a949e89797bb1dca8f415ca259a","last_reissued_at":"2026-05-17T23:59:57.183327Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:57.183327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.10167","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":"2026-05-17T23:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KIaGWwZ9GCe5sVJkpuvXdat8rSPTfhUO+PslrZ+zt+3aqW8NOkgP5vh7/lxAvmxuAFiFcODxj0GNTVRv0r+gBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:59:37.505469Z"},"content_sha256":"8a8ec69831189f5427d5e49840528bfde39bb8dcb7194f099f6a15d6f216ae2d","schema_version":"1.0","event_id":"sha256:8a8ec69831189f5427d5e49840528bfde39bb8dcb7194f099f6a15d6f216ae2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:B7FLCQLAZ56NGGOC4XMOXJUAFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LSICC: A Large Scale Informal Chinese Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianyu Zhao, Zhuoran Ji","submitted_at":"2018-11-26T03:58:09Z","abstract_excerpt":"Deep learning based natural language processing model is proven powerful, but need large-scale dataset. Due to the significant gap between the real-world tasks and existing Chinese corpus, in this paper, we introduce a large-scale corpus of informal Chinese. This corpus contains around 37 million book reviews and 50 thousand netizen's comments to the news. We explore the informal words frequencies of the corpus and show the difference between our corpus and the existing ones. The corpus can be further used to train deep learning based natural language processing tasks such as Chinese word segm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10167","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":"2026-05-17T23:59:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ufe41Pb3o6UjLBrZvT9Yk4/2KVkZ4NQoOpyTgbclohrQRHGQUGhRJ4yQ7Gc2Puha9yp4W6fPIXbotgnkuCHiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:59:37.505830Z"},"content_sha256":"4d3c86e4068b2c1d46ea5154992c3746d52b988966f252994abe9090851e2f7b","schema_version":"1.0","event_id":"sha256:4d3c86e4068b2c1d46ea5154992c3746d52b988966f252994abe9090851e2f7b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B7FLCQLAZ56NGGOC4XMOXJUAFY/bundle.json","state_url":"https://pith.science/pith/B7FLCQLAZ56NGGOC4XMOXJUAFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B7FLCQLAZ56NGGOC4XMOXJUAFY/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":"2026-06-30T12:59:37Z","links":{"resolver":"https://pith.science/pith/B7FLCQLAZ56NGGOC4XMOXJUAFY","bundle":"https://pith.science/pith/B7FLCQLAZ56NGGOC4XMOXJUAFY/bundle.json","state":"https://pith.science/pith/B7FLCQLAZ56NGGOC4XMOXJUAFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B7FLCQLAZ56NGGOC4XMOXJUAFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:B7FLCQLAZ56NGGOC4XMOXJUAFY","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":"d494e31b6c27c8edb895b776bdf73774484274bf7f67ef21f1d4ebcc7973a1c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-26T03:58:09Z","title_canon_sha256":"b1d45e37315a7dc21cfff63af2bd1969bf6b33025494fb7ee7f130b3fe80c567"},"schema_version":"1.0","source":{"id":"1811.10167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10167","created_at":"2026-05-17T23:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10167v1","created_at":"2026-05-17T23:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10167","created_at":"2026-05-17T23:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"B7FLCQLAZ56N","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"B7FLCQLAZ56NGGOC","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"B7FLCQLA","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:4d3c86e4068b2c1d46ea5154992c3746d52b988966f252994abe9090851e2f7b","target":"graph","created_at":"2026-05-17T23:59:57Z","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":"Deep learning based natural language processing model is proven powerful, but need large-scale dataset. Due to the significant gap between the real-world tasks and existing Chinese corpus, in this paper, we introduce a large-scale corpus of informal Chinese. This corpus contains around 37 million book reviews and 50 thousand netizen's comments to the news. We explore the informal words frequencies of the corpus and show the difference between our corpus and the existing ones. The corpus can be further used to train deep learning based natural language processing tasks such as Chinese word segm","authors_text":"Jianyu Zhao, Zhuoran Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-26T03:58:09Z","title":"LSICC: A Large Scale Informal Chinese Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10167","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":"sha256:8a8ec69831189f5427d5e49840528bfde39bb8dcb7194f099f6a15d6f216ae2d","target":"record","created_at":"2026-05-17T23:59:57Z","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":"d494e31b6c27c8edb895b776bdf73774484274bf7f67ef21f1d4ebcc7973a1c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-26T03:58:09Z","title_canon_sha256":"b1d45e37315a7dc21cfff63af2bd1969bf6b33025494fb7ee7f130b3fe80c567"},"schema_version":"1.0","source":{"id":"1811.10167","kind":"arxiv","version":1}},"canonical_sha256":"0fcab14160cf7cd319c2e5d8eba6802e108e9a949e89797bb1dca8f415ca259a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0fcab14160cf7cd319c2e5d8eba6802e108e9a949e89797bb1dca8f415ca259a","first_computed_at":"2026-05-17T23:59:57.183327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:57.183327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"590DyLCAppHGgFLhoYS6WXHYwbvfErWWmIw28FFiyiNOICuL/HDqVoO+7FYT4yrrJCPs4V4Tx6jB3WEalv75Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:57.183830Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a8ec69831189f5427d5e49840528bfde39bb8dcb7194f099f6a15d6f216ae2d","sha256:4d3c86e4068b2c1d46ea5154992c3746d52b988966f252994abe9090851e2f7b"],"state_sha256":"2c47f134eddfbd2a4307f13958a566cf406ef61e888f43503f933cbc2d62875c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZE9IXuje1Iggf/wSINuGWeZ8JE3NH0g7mc5VS2rnckIRKzae5aTgdZYU8W8JmopP4y58kxENiIf5mYOagwvAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T12:59:37.507752Z","bundle_sha256":"369c99949fb67501cdb845ad2295cfa6cc4a6ef665a83df86d57ac1cb493c351"}}