{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K2GDOKDVZIC5U5576YRJDRJFZ5","short_pith_number":"pith:K2GDOKDV","canonical_record":{"source":{"id":"2506.18399","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:34:33Z","cross_cats_sorted":[],"title_canon_sha256":"f230a938ba0339b8f99e406b70b1a5eee7f62e106c9cb45f259862883ef0c9ed","abstract_canon_sha256":"22984a7e50b86461e4cb0ac04ee27c3dce19fdcc2a16aea4e45263eef11c8e24"},"schema_version":"1.0"},"canonical_sha256":"568c372875ca05da77bff62291c525cf7b1bd81cc6d0970c16e0ebce8f9a2770","source":{"kind":"arxiv","id":"2506.18399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18399","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18399v1","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18399","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_12","alias_value":"K2GDOKDVZIC5","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_16","alias_value":"K2GDOKDVZIC5U557","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_8","alias_value":"K2GDOKDV","created_at":"2026-07-05T11:25:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K2GDOKDVZIC5U5576YRJDRJFZ5","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18399","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:34:33Z","cross_cats_sorted":[],"title_canon_sha256":"f230a938ba0339b8f99e406b70b1a5eee7f62e106c9cb45f259862883ef0c9ed","abstract_canon_sha256":"22984a7e50b86461e4cb0ac04ee27c3dce19fdcc2a16aea4e45263eef11c8e24"},"schema_version":"1.0"},"canonical_sha256":"568c372875ca05da77bff62291c525cf7b1bd81cc6d0970c16e0ebce8f9a2770","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:49.707961Z","signature_b64":"9/dKij7j1Zw6k6TIu0FZIG4oBAPCGZ4RGaYjHRgWk2HIvGmvRPOyYuFOiQvzfJBZ7sncgA8fOXzNRDP873DTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568c372875ca05da77bff62291c525cf7b1bd81cc6d0970c16e0ebce8f9a2770","last_reissued_at":"2026-07-05T11:25:49.707505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:49.707505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18399","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":"2026-07-05T11:25:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VvkFBMb0BXOL7NFOkCChvVXLRK+v7hGtFXC/WMcO6WSz2pg16vbTEwG1IMNEgV7E5nTXb19TPyqiyeHqH4A/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:53.324598Z"},"content_sha256":"17bd88b0f72476630ea619ec755b03fefd56edffcf03342b71de0c3a6775a963","schema_version":"1.0","event_id":"sha256:17bd88b0f72476630ea619ec755b03fefd56edffcf03342b71de0c3a6775a963"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K2GDOKDVZIC5U5576YRJDRJFZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lemmatization as a Classification Task: Results from Arabic across Multiple Genres","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mostafa Saeed, Nizar Habash","submitted_at":"2025-06-23T08:34:33Z","abstract_excerpt":"Lemmatization is crucial for NLP tasks in morphologically rich languages with ambiguous orthography like Arabic, but existing tools face challenges due to inconsistent standards and limited genre coverage. This paper introduces two novel approaches that frame lemmatization as classification into a Lemma-POS-Gloss (LPG) tagset, leveraging machine translation and semantic clustering. We also present a new Arabic lemmatization test set covering diverse genres, standardized alongside existing datasets. We evaluate character level sequence-to-sequence models, which perform competitively and offer c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18399","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/2506.18399/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":"2026-07-05T11:25:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XX2TzWoHD6sT/IM4dcRwArh+v0mQsPZGZyihn5ZfOLTG2WmodK3FiQabpRXKPhIFW6FPeZujFAoffXbANlHdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:53.325142Z"},"content_sha256":"b80294a222e66690dafd339fcd08221c15670625177bc67d7b2d2000c4bdfd5a","schema_version":"1.0","event_id":"sha256:b80294a222e66690dafd339fcd08221c15670625177bc67d7b2d2000c4bdfd5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2GDOKDVZIC5U5576YRJDRJFZ5/bundle.json","state_url":"https://pith.science/pith/K2GDOKDVZIC5U5576YRJDRJFZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2GDOKDVZIC5U5576YRJDRJFZ5/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":"2026-08-08T02:34:53Z","links":{"resolver":"https://pith.science/pith/K2GDOKDVZIC5U5576YRJDRJFZ5","bundle":"https://pith.science/pith/K2GDOKDVZIC5U5576YRJDRJFZ5/bundle.json","state":"https://pith.science/pith/K2GDOKDVZIC5U5576YRJDRJFZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2GDOKDVZIC5U5576YRJDRJFZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K2GDOKDVZIC5U5576YRJDRJFZ5","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":"22984a7e50b86461e4cb0ac04ee27c3dce19fdcc2a16aea4e45263eef11c8e24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:34:33Z","title_canon_sha256":"f230a938ba0339b8f99e406b70b1a5eee7f62e106c9cb45f259862883ef0c9ed"},"schema_version":"1.0","source":{"id":"2506.18399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18399","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18399v1","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18399","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_12","alias_value":"K2GDOKDVZIC5","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_16","alias_value":"K2GDOKDVZIC5U557","created_at":"2026-07-05T11:25:49Z"},{"alias_kind":"pith_short_8","alias_value":"K2GDOKDV","created_at":"2026-07-05T11:25:49Z"}],"graph_snapshots":[{"event_id":"sha256:b80294a222e66690dafd339fcd08221c15670625177bc67d7b2d2000c4bdfd5a","target":"graph","created_at":"2026-07-05T11:25:49Z","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/2506.18399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lemmatization is crucial for NLP tasks in morphologically rich languages with ambiguous orthography like Arabic, but existing tools face challenges due to inconsistent standards and limited genre coverage. This paper introduces two novel approaches that frame lemmatization as classification into a Lemma-POS-Gloss (LPG) tagset, leveraging machine translation and semantic clustering. We also present a new Arabic lemmatization test set covering diverse genres, standardized alongside existing datasets. We evaluate character level sequence-to-sequence models, which perform competitively and offer c","authors_text":"Mostafa Saeed, Nizar Habash","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:34:33Z","title":"Lemmatization as a Classification Task: Results from Arabic across Multiple Genres"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18399","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":"sha256:17bd88b0f72476630ea619ec755b03fefd56edffcf03342b71de0c3a6775a963","target":"record","created_at":"2026-07-05T11:25:49Z","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":"22984a7e50b86461e4cb0ac04ee27c3dce19fdcc2a16aea4e45263eef11c8e24","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-23T08:34:33Z","title_canon_sha256":"f230a938ba0339b8f99e406b70b1a5eee7f62e106c9cb45f259862883ef0c9ed"},"schema_version":"1.0","source":{"id":"2506.18399","kind":"arxiv","version":1}},"canonical_sha256":"568c372875ca05da77bff62291c525cf7b1bd81cc6d0970c16e0ebce8f9a2770","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"568c372875ca05da77bff62291c525cf7b1bd81cc6d0970c16e0ebce8f9a2770","first_computed_at":"2026-07-05T11:25:49.707505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:49.707505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9/dKij7j1Zw6k6TIu0FZIG4oBAPCGZ4RGaYjHRgWk2HIvGmvRPOyYuFOiQvzfJBZ7sncgA8fOXzNRDP873DTCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:49.707961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17bd88b0f72476630ea619ec755b03fefd56edffcf03342b71de0c3a6775a963","sha256:b80294a222e66690dafd339fcd08221c15670625177bc67d7b2d2000c4bdfd5a"],"state_sha256":"8f4da2d5e1f1c755350c76c952a63774c90cae531bd42b5e0943f65875a8ca3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewsxgyFmpQ7r88qZA5vanXLWDDtodcKLvPzc3a1/6uppZPQHc3MUf0ccinuHCcFUzil6rGfZg9+g1VSNTcnjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:34:53.329174Z","bundle_sha256":"76e884d807a7ff0859c96bcb29fee7c6e8660244a65aee0c3fcdaa236388bf88"}}