{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RDRB2NHSA3USS5GEDIV7YK3SBZ","short_pith_number":"pith:RDRB2NHS","canonical_record":{"source":{"id":"1908.09716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-26T14:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"8aa8895419db0bb0ca5fefda886e72947066550d606df331b9d9bde4b188ddc1","abstract_canon_sha256":"9d564f47413aff791f1ae2c17f84cc9547f6984e1e0183f0080cf609f528b89f"},"schema_version":"1.0"},"canonical_sha256":"88e21d34f206e92974c41a2bfc2b720e6f28168df5959a6a41d210e0fb82c27a","source":{"kind":"arxiv","id":"1908.09716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.09716","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"arxiv_version","alias_value":"1908.09716v1","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09716","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"pith_short_12","alias_value":"RDRB2NHSA3US","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"pith_short_16","alias_value":"RDRB2NHSA3USS5GE","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"pith_short_8","alias_value":"RDRB2NHS","created_at":"2026-07-04T23:59:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RDRB2NHSA3USS5GEDIV7YK3SBZ","target":"record","payload":{"canonical_record":{"source":{"id":"1908.09716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-26T14:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"8aa8895419db0bb0ca5fefda886e72947066550d606df331b9d9bde4b188ddc1","abstract_canon_sha256":"9d564f47413aff791f1ae2c17f84cc9547f6984e1e0183f0080cf609f528b89f"},"schema_version":"1.0"},"canonical_sha256":"88e21d34f206e92974c41a2bfc2b720e6f28168df5959a6a41d210e0fb82c27a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:42.910960Z","signature_b64":"z319i52xAATWIwS0xe6ptoM/XpYKvIAy0/WzgWf9YDTTGTDAR4TEgLT/A4kZZ0++Q7Q2Xp/7SSEhWuVsOY5WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88e21d34f206e92974c41a2bfc2b720e6f28168df5959a6a41d210e0fb82c27a","last_reissued_at":"2026-07-04T23:59:42.910577Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:42.910577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.09716","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":"2026-07-04T23:59:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ot/ROqJPyVSp7OGJLS2bieemuSTBUZOyw1Nr2TG6nOJyFpdOJc0gyP80OWSdJ/3b+bJbCmHhNCorYXVv232ICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:00:08.829324Z"},"content_sha256":"4f739b9d5b1dfb47623f48a173e6f6515c1111345a29f5aa74769c37de872090","schema_version":"1.0","event_id":"sha256:4f739b9d5b1dfb47623f48a173e6f6515c1111345a29f5aa74769c37de872090"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RDRB2NHSA3USS5GEDIV7YK3SBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"uniblock: Scoring and Filtering Corpus with Unicode Block Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Weiyue Wang, Yingbo Gao","submitted_at":"2019-08-26T14:55:03Z","abstract_excerpt":"The preprocessing pipelines in Natural Language Processing usually involve a step of removing sentences consisted of illegal characters. The definition of illegal characters and the specific removal strategy depend on the task, language, domain, etc, which often lead to tiresome and repetitive scripting of rules. In this paper, we introduce a simple statistical method, uniblock, to overcome this problem. For each sentence, uniblock generates a fixed-size feature vector using Unicode block information of the characters. A Gaussian mixture model is then estimated on some clean corpus using varia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09716","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.09716/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-04T23:59:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6ZObZVjRZyqz+3UZqt+lyz3uV8S7SdQEiTmOBQJTRTJiB9Tdc6DSXKF7dXURhTC1zaGZWxHNVXFnZDuX7ZYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:00:08.830048Z"},"content_sha256":"5275f837d83cc4d4dbb905d3d6e84d0dd7e2afecc14c6ba6a653c45bc3f83851","schema_version":"1.0","event_id":"sha256:5275f837d83cc4d4dbb905d3d6e84d0dd7e2afecc14c6ba6a653c45bc3f83851"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDRB2NHSA3USS5GEDIV7YK3SBZ/bundle.json","state_url":"https://pith.science/pith/RDRB2NHSA3USS5GEDIV7YK3SBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDRB2NHSA3USS5GEDIV7YK3SBZ/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":"2026-08-14T22:00:08Z","links":{"resolver":"https://pith.science/pith/RDRB2NHSA3USS5GEDIV7YK3SBZ","bundle":"https://pith.science/pith/RDRB2NHSA3USS5GEDIV7YK3SBZ/bundle.json","state":"https://pith.science/pith/RDRB2NHSA3USS5GEDIV7YK3SBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDRB2NHSA3USS5GEDIV7YK3SBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RDRB2NHSA3USS5GEDIV7YK3SBZ","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":"9d564f47413aff791f1ae2c17f84cc9547f6984e1e0183f0080cf609f528b89f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-26T14:55:03Z","title_canon_sha256":"8aa8895419db0bb0ca5fefda886e72947066550d606df331b9d9bde4b188ddc1"},"schema_version":"1.0","source":{"id":"1908.09716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.09716","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"arxiv_version","alias_value":"1908.09716v1","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09716","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"pith_short_12","alias_value":"RDRB2NHSA3US","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"pith_short_16","alias_value":"RDRB2NHSA3USS5GE","created_at":"2026-07-04T23:59:42Z"},{"alias_kind":"pith_short_8","alias_value":"RDRB2NHS","created_at":"2026-07-04T23:59:42Z"}],"graph_snapshots":[{"event_id":"sha256:5275f837d83cc4d4dbb905d3d6e84d0dd7e2afecc14c6ba6a653c45bc3f83851","target":"graph","created_at":"2026-07-04T23:59:42Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.09716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The preprocessing pipelines in Natural Language Processing usually involve a step of removing sentences consisted of illegal characters. The definition of illegal characters and the specific removal strategy depend on the task, language, domain, etc, which often lead to tiresome and repetitive scripting of rules. In this paper, we introduce a simple statistical method, uniblock, to overcome this problem. For each sentence, uniblock generates a fixed-size feature vector using Unicode block information of the characters. A Gaussian mixture model is then estimated on some clean corpus using varia","authors_text":"Hermann Ney, Weiyue Wang, Yingbo Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-26T14:55:03Z","title":"uniblock: Scoring and Filtering Corpus with Unicode Block Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09716","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":"sha256:4f739b9d5b1dfb47623f48a173e6f6515c1111345a29f5aa74769c37de872090","target":"record","created_at":"2026-07-04T23:59:42Z","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":"9d564f47413aff791f1ae2c17f84cc9547f6984e1e0183f0080cf609f528b89f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-26T14:55:03Z","title_canon_sha256":"8aa8895419db0bb0ca5fefda886e72947066550d606df331b9d9bde4b188ddc1"},"schema_version":"1.0","source":{"id":"1908.09716","kind":"arxiv","version":1}},"canonical_sha256":"88e21d34f206e92974c41a2bfc2b720e6f28168df5959a6a41d210e0fb82c27a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88e21d34f206e92974c41a2bfc2b720e6f28168df5959a6a41d210e0fb82c27a","first_computed_at":"2026-07-04T23:59:42.910577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:42.910577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z319i52xAATWIwS0xe6ptoM/XpYKvIAy0/WzgWf9YDTTGTDAR4TEgLT/A4kZZ0++Q7Q2Xp/7SSEhWuVsOY5WDw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:42.910960Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.09716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f739b9d5b1dfb47623f48a173e6f6515c1111345a29f5aa74769c37de872090","sha256:5275f837d83cc4d4dbb905d3d6e84d0dd7e2afecc14c6ba6a653c45bc3f83851"],"state_sha256":"44d28e70585d339520a7a93e6e5e8f195bd340ce6ab53e78a78c5db2aa7284be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dq81W3XNo82qokZg6hrqkLrrbfiu+M4LvxiC+jIinOhTA1ZEIJiLif98xYrjsD7JYDhBz0mKcSDIkFSfHkDSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:00:08.841420Z","bundle_sha256":"234c832b54e3bb4a50b0118b20fe415d0008d480a9744b40af1a062dc2e3e221"}}