{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HXECV7NIDK3GRCVWELVC3NBF2P","short_pith_number":"pith:HXECV7NI","canonical_record":{"source":{"id":"1908.08528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T17:58:55Z","cross_cats_sorted":[],"title_canon_sha256":"23f84a03ca4b94651205551c5cbb85e01607c5b5c55b3c5178ef868489096d51","abstract_canon_sha256":"8662e58dc9639a65840e477851b3079c70b93717a82741ae44b97bb14b478e3d"},"schema_version":"1.0"},"canonical_sha256":"3dc82afda81ab6688ab622ea2db425d3e5c5452e32cb5666e0d89d32cd39deb1","source":{"kind":"arxiv","id":"1908.08528","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08528","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08528v1","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08528","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"HXECV7NIDK3G","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"HXECV7NIDK3GRCVW","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"HXECV7NI","created_at":"2026-07-04T23:59:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HXECV7NIDK3GRCVWELVC3NBF2P","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T17:58:55Z","cross_cats_sorted":[],"title_canon_sha256":"23f84a03ca4b94651205551c5cbb85e01607c5b5c55b3c5178ef868489096d51","abstract_canon_sha256":"8662e58dc9639a65840e477851b3079c70b93717a82741ae44b97bb14b478e3d"},"schema_version":"1.0"},"canonical_sha256":"3dc82afda81ab6688ab622ea2db425d3e5c5452e32cb5666e0d89d32cd39deb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:13.796797Z","signature_b64":"m1oiOlOvbAttyohITzUoypExQmqNCJ/A5/FmmiSYli77p+0Grsu8p/fAx4AEQ95mSCJl3PZfLPy3ZVQz+5M/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dc82afda81ab6688ab622ea2db425d3e5c5452e32cb5666e0d89d32cd39deb1","last_reissued_at":"2026-07-04T23:59:13.796460Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:13.796460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08528","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":"2026-07-04T23:59:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUM249ix2DcfLz7V0GCHy5HdRahgoTQ7Dz1ugJ7P55pJh3y0TvmExKSuCnuO/+AyampksHd8pFLWIE5H/Qg+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:55:49.920459Z"},"content_sha256":"3ca7c0373dbfa8e3ef6e5c5cd81008895cf4e51588180a69b312d94645c965bb","schema_version":"1.0","event_id":"sha256:3ca7c0373dbfa8e3ef6e5c5cd81008895cf4e51588180a69b312d94645c965bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HXECV7NIDK3GRCVWELVC3NBF2P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Lemmatization as Embeddings-Based Word Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rudolf Rosa, Zden\\v{e}k \\v{Z}abokrtsk\\'y","submitted_at":"2019-08-22T17:58:55Z","abstract_excerpt":"We focus on the task of unsupervised lemmatization, i.e. grouping together inflected forms of one word under one label (a lemma) without the use of annotated training data. We propose to perform agglomerative clustering of word forms with a novel distance measure. Our distance measure is based on the observation that inflections of the same word tend to be similar both string-wise and in meaning. We therefore combine word embedding cosine similarity, serving as a proxy to the meaning similarity, with Jaro-Winkler edit distance. Our experiments on 23 languages show our approach to be promising,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08528","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/1908.08528/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":"2026-07-04T23:59:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ot+tJQDjMXVRKsK6dzIjGeGBvKaAIkph1lWZO7Huv+snQYli5wBO4OEBSqnWua0GSfLbSRodNi5LqrlE804sCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:55:49.921440Z"},"content_sha256":"cb6b697e8d51cc69a3ed22d677858ee67ad4a4ffb38333ce5c5510dc727b1093","schema_version":"1.0","event_id":"sha256:cb6b697e8d51cc69a3ed22d677858ee67ad4a4ffb38333ce5c5510dc727b1093"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXECV7NIDK3GRCVWELVC3NBF2P/bundle.json","state_url":"https://pith.science/pith/HXECV7NIDK3GRCVWELVC3NBF2P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXECV7NIDK3GRCVWELVC3NBF2P/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":"2026-08-16T09:55:49Z","links":{"resolver":"https://pith.science/pith/HXECV7NIDK3GRCVWELVC3NBF2P","bundle":"https://pith.science/pith/HXECV7NIDK3GRCVWELVC3NBF2P/bundle.json","state":"https://pith.science/pith/HXECV7NIDK3GRCVWELVC3NBF2P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXECV7NIDK3GRCVWELVC3NBF2P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HXECV7NIDK3GRCVWELVC3NBF2P","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":"8662e58dc9639a65840e477851b3079c70b93717a82741ae44b97bb14b478e3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T17:58:55Z","title_canon_sha256":"23f84a03ca4b94651205551c5cbb85e01607c5b5c55b3c5178ef868489096d51"},"schema_version":"1.0","source":{"id":"1908.08528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08528","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08528v1","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08528","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"HXECV7NIDK3G","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"HXECV7NIDK3GRCVW","created_at":"2026-07-04T23:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"HXECV7NI","created_at":"2026-07-04T23:59:13Z"}],"graph_snapshots":[{"event_id":"sha256:cb6b697e8d51cc69a3ed22d677858ee67ad4a4ffb38333ce5c5510dc727b1093","target":"graph","created_at":"2026-07-04T23:59:13Z","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/1908.08528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We focus on the task of unsupervised lemmatization, i.e. grouping together inflected forms of one word under one label (a lemma) without the use of annotated training data. We propose to perform agglomerative clustering of word forms with a novel distance measure. Our distance measure is based on the observation that inflections of the same word tend to be similar both string-wise and in meaning. We therefore combine word embedding cosine similarity, serving as a proxy to the meaning similarity, with Jaro-Winkler edit distance. Our experiments on 23 languages show our approach to be promising,","authors_text":"Rudolf Rosa, Zden\\v{e}k \\v{Z}abokrtsk\\'y","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T17:58:55Z","title":"Unsupervised Lemmatization as Embeddings-Based Word Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08528","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":"sha256:3ca7c0373dbfa8e3ef6e5c5cd81008895cf4e51588180a69b312d94645c965bb","target":"record","created_at":"2026-07-04T23:59:13Z","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":"8662e58dc9639a65840e477851b3079c70b93717a82741ae44b97bb14b478e3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T17:58:55Z","title_canon_sha256":"23f84a03ca4b94651205551c5cbb85e01607c5b5c55b3c5178ef868489096d51"},"schema_version":"1.0","source":{"id":"1908.08528","kind":"arxiv","version":1}},"canonical_sha256":"3dc82afda81ab6688ab622ea2db425d3e5c5452e32cb5666e0d89d32cd39deb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dc82afda81ab6688ab622ea2db425d3e5c5452e32cb5666e0d89d32cd39deb1","first_computed_at":"2026-07-04T23:59:13.796460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:13.796460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m1oiOlOvbAttyohITzUoypExQmqNCJ/A5/FmmiSYli77p+0Grsu8p/fAx4AEQ95mSCJl3PZfLPy3ZVQz+5M/CQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:13.796797Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ca7c0373dbfa8e3ef6e5c5cd81008895cf4e51588180a69b312d94645c965bb","sha256:cb6b697e8d51cc69a3ed22d677858ee67ad4a4ffb38333ce5c5510dc727b1093"],"state_sha256":"cb21e52da04eb383a8698ffaf5b9eaf3f1165d4a4bb4fa5f7a702e95bcda5145"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UWcnhYJyuYZPnnl6e5CXfTO2Pdt3PEM8mldsURzI/i9bEDqukdp5HRFNv+CdOFNKwQy4ZMDMtkKwSOwDlUQvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T09:55:49.928502Z","bundle_sha256":"b3e6538e43535c37a514cb3f51a826ba5866d0e46886a1803a9f22c7e71052f9"}}