{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DGT5FRBBZUQV6KBIJKBKJE6VUR","short_pith_number":"pith:DGT5FRBB","canonical_record":{"source":{"id":"2204.01175","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-03T22:53:36Z","cross_cats_sorted":[],"title_canon_sha256":"192255c7a7455620ef92090fbdfc33bbdb6c422e00b381bba36aea656e55e366","abstract_canon_sha256":"88e6e05eb6d1249f6cf222ba13a22ff65294dc20e803deced35edd352f9e7154"},"schema_version":"1.0"},"canonical_sha256":"19a7d2c421cd215f28284a82a493d5a462d56c0cdcba6db5ed17731b9523e078","source":{"kind":"arxiv","id":"2204.01175","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.01175","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"arxiv_version","alias_value":"2204.01175v2","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01175","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"pith_short_12","alias_value":"DGT5FRBBZUQV","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"pith_short_16","alias_value":"DGT5FRBBZUQV6KBI","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"pith_short_8","alias_value":"DGT5FRBB","created_at":"2026-07-05T06:42:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DGT5FRBBZUQV6KBIJKBKJE6VUR","target":"record","payload":{"canonical_record":{"source":{"id":"2204.01175","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-03T22:53:36Z","cross_cats_sorted":[],"title_canon_sha256":"192255c7a7455620ef92090fbdfc33bbdb6c422e00b381bba36aea656e55e366","abstract_canon_sha256":"88e6e05eb6d1249f6cf222ba13a22ff65294dc20e803deced35edd352f9e7154"},"schema_version":"1.0"},"canonical_sha256":"19a7d2c421cd215f28284a82a493d5a462d56c0cdcba6db5ed17731b9523e078","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:16.141824Z","signature_b64":"auowk5O4EgA2CMnLWG778ymGvaYYZ2Pt/KUdq7mJWhnBZogLKNPtuz9oKTh3R8FQGGLt3+oYQXxEeeTokmJQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19a7d2c421cd215f28284a82a493d5a462d56c0cdcba6db5ed17731b9523e078","last_reissued_at":"2026-07-05T06:42:16.141309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:16.141309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.01175","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":"2026-07-05T06:42:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvFI5CWgGfq/THJH/+8yOlLx3xhSc1HoNnrCjl0KrlaYeZzeK8ufu3rTgy59DKgFYbG4A04E9BNAK+nAaj4tDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:21:58.900830Z"},"content_sha256":"e3ba72c769025b70ce7e5c697724a3c5ddbed2e2648eb61454eab78acea52344","schema_version":"1.0","event_id":"sha256:e3ba72c769025b70ce7e5c697724a3c5ddbed2e2648eb61454eab78acea52344"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DGT5FRBBZUQV6KBIJKBKJE6VUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Part-of-Speech Tagger for Yiddish","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Assaf Urieli, Beatrice Santorini, Joel Wallenberg, Neville Ryant, Seth Kulick","submitted_at":"2022-04-03T22:53:36Z","abstract_excerpt":"We describe the construction and evaluation of a part-of-speech tagger for Yiddish. This is the first step in a larger project of automatically assigning part-of-speech tags and syntactic structure to Yiddish text for purposes of linguistic research. We combine two resources for the current work - an 80K-word subset of the Penn Parsed Corpus of Historical Yiddish (PPCHY) and 650 million words of OCR'd Yiddish text from the Yiddish Book Center (YBC). Yiddish orthography in the YBC corpus has many spelling inconsistencies, and we present some evidence that even simple non-contextualized embeddin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01175","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.01175/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":"2026-07-05T06:42:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oX+VAm//5I15vOGP68JCCi/jBJaDuSkcpbdlOI15mtH1zRfWPQg9gNOqCzDF8EWNdLydTt6tvZZ8F2g0YE6oAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:21:58.901771Z"},"content_sha256":"b153e14f9f04ba85b75c6518a422bb59f681cec9711dbae569f2fa59273935db","schema_version":"1.0","event_id":"sha256:b153e14f9f04ba85b75c6518a422bb59f681cec9711dbae569f2fa59273935db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGT5FRBBZUQV6KBIJKBKJE6VUR/bundle.json","state_url":"https://pith.science/pith/DGT5FRBBZUQV6KBIJKBKJE6VUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGT5FRBBZUQV6KBIJKBKJE6VUR/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":"2026-08-23T18:21:58Z","links":{"resolver":"https://pith.science/pith/DGT5FRBBZUQV6KBIJKBKJE6VUR","bundle":"https://pith.science/pith/DGT5FRBBZUQV6KBIJKBKJE6VUR/bundle.json","state":"https://pith.science/pith/DGT5FRBBZUQV6KBIJKBKJE6VUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGT5FRBBZUQV6KBIJKBKJE6VUR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DGT5FRBBZUQV6KBIJKBKJE6VUR","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":"88e6e05eb6d1249f6cf222ba13a22ff65294dc20e803deced35edd352f9e7154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-03T22:53:36Z","title_canon_sha256":"192255c7a7455620ef92090fbdfc33bbdb6c422e00b381bba36aea656e55e366"},"schema_version":"1.0","source":{"id":"2204.01175","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.01175","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"arxiv_version","alias_value":"2204.01175v2","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.01175","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"pith_short_12","alias_value":"DGT5FRBBZUQV","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"pith_short_16","alias_value":"DGT5FRBBZUQV6KBI","created_at":"2026-07-05T06:42:16Z"},{"alias_kind":"pith_short_8","alias_value":"DGT5FRBB","created_at":"2026-07-05T06:42:16Z"}],"graph_snapshots":[{"event_id":"sha256:b153e14f9f04ba85b75c6518a422bb59f681cec9711dbae569f2fa59273935db","target":"graph","created_at":"2026-07-05T06:42:16Z","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/2204.01175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe the construction and evaluation of a part-of-speech tagger for Yiddish. This is the first step in a larger project of automatically assigning part-of-speech tags and syntactic structure to Yiddish text for purposes of linguistic research. We combine two resources for the current work - an 80K-word subset of the Penn Parsed Corpus of Historical Yiddish (PPCHY) and 650 million words of OCR'd Yiddish text from the Yiddish Book Center (YBC). Yiddish orthography in the YBC corpus has many spelling inconsistencies, and we present some evidence that even simple non-contextualized embeddin","authors_text":"Assaf Urieli, Beatrice Santorini, Joel Wallenberg, Neville Ryant, Seth Kulick","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-03T22:53:36Z","title":"A Part-of-Speech Tagger for Yiddish"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.01175","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:e3ba72c769025b70ce7e5c697724a3c5ddbed2e2648eb61454eab78acea52344","target":"record","created_at":"2026-07-05T06:42:16Z","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":"88e6e05eb6d1249f6cf222ba13a22ff65294dc20e803deced35edd352f9e7154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-03T22:53:36Z","title_canon_sha256":"192255c7a7455620ef92090fbdfc33bbdb6c422e00b381bba36aea656e55e366"},"schema_version":"1.0","source":{"id":"2204.01175","kind":"arxiv","version":2}},"canonical_sha256":"19a7d2c421cd215f28284a82a493d5a462d56c0cdcba6db5ed17731b9523e078","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19a7d2c421cd215f28284a82a493d5a462d56c0cdcba6db5ed17731b9523e078","first_computed_at":"2026-07-05T06:42:16.141309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:16.141309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"auowk5O4EgA2CMnLWG778ymGvaYYZ2Pt/KUdq7mJWhnBZogLKNPtuz9oKTh3R8FQGGLt3+oYQXxEeeTokmJQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:16.141824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.01175","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3ba72c769025b70ce7e5c697724a3c5ddbed2e2648eb61454eab78acea52344","sha256:b153e14f9f04ba85b75c6518a422bb59f681cec9711dbae569f2fa59273935db"],"state_sha256":"b473cb6155b2f0da7298be681bbd4a0e4cd76d4cee54fab65c1bef0d511485fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"paI0/2SxD6ufPwfQd+Rg4SX9CYvOO0OrFOCZTJkRJQ89E3i1OUDcDwjl/Vk+0kjnd7mUN/b3dimWCMXpdcNwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:21:58.907462Z","bundle_sha256":"528ba088dbd5ea14cbcc41ca1f734b94bfc24aaa55dcd478a6ef58ea723a5295"}}