{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:DRFIUM3UEGJWN62HZ7G6M7O4II","short_pith_number":"pith:DRFIUM3U","canonical_record":{"source":{"id":"1708.05891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-19T19:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"338eb501bed48be1652cccc3ec1ad76d7518b96c472796525619a6cb50013dd4","abstract_canon_sha256":"20026a1782e0b7c053e538c87433fac417b5a92aa48e52298c975afa9a5bb527"},"schema_version":"1.0"},"canonical_sha256":"1c4a8a3374219366fb47cfcde67ddc4208dc9d522c22b45e4c5ebd8660d16dc8","source":{"kind":"arxiv","id":"1708.05891","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05891","created_at":"2026-05-18T00:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05891v1","created_at":"2026-05-18T00:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05891","created_at":"2026-05-18T00:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"DRFIUM3UEGJW","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DRFIUM3UEGJWN62H","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DRFIUM3U","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:DRFIUM3UEGJWN62HZ7G6M7O4II","target":"record","payload":{"canonical_record":{"source":{"id":"1708.05891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-19T19:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"338eb501bed48be1652cccc3ec1ad76d7518b96c472796525619a6cb50013dd4","abstract_canon_sha256":"20026a1782e0b7c053e538c87433fac417b5a92aa48e52298c975afa9a5bb527"},"schema_version":"1.0"},"canonical_sha256":"1c4a8a3374219366fb47cfcde67ddc4208dc9d522c22b45e4c5ebd8660d16dc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:43.831191Z","signature_b64":"uS+BgyCAbxnjGJ3Z+MZlwvERAJEvlr+GCTI/8OQSBjMnXWwlw2o2hcZV7rUmx/oHJoApnEAukr1hJ8W9siZnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c4a8a3374219366fb47cfcde67ddc4208dc9d522c22b45e4c5ebd8660d16dc8","last_reissued_at":"2026-05-18T00:37:43.830398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:43.830398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.05891","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":"2026-05-18T00:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uA8NyVG6fXMNQKDo1+W7l+n+bU/DJfhHPiQnMjjzqGP51CAi0YG89Ef3qnnqOEjBagClO/C5CyJlttr/gcTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:07:34.522696Z"},"content_sha256":"972093846b029fec525f25bb2a1504a69d65cb4ce75102989c65be2230e9bb55","schema_version":"1.0","event_id":"sha256:972093846b029fec525f25bb2a1504a69d65cb4ce75102989c65be2230e9bb55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:DRFIUM3UEGJWN62HZ7G6M7O4II","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Abdelali, Hamdy Mubarak, Kallmeyer Laura, Kareem Darwish, Mohamed Eldesouki, Mohammed Attia, Younes Samih","submitted_at":"2017-08-19T19:52:36Z","abstract_excerpt":"Arabic word segmentation is essential for a variety of NLP applications such as machine translation and information retrieval. Segmentation entails breaking words into their constituent stems, affixes and clitics. In this paper, we compare two approaches for segmenting four major Arabic dialects using only several thousand training examples for each dialect. The two approaches involve posing the problem as a ranking problem, where an SVM ranker picks the best segmentation, and as a sequence labeling problem, where a bi-LSTM RNN coupled with CRF determines where best to segment words. We are ab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05891","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":"2026-05-18T00:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Go7DeqjOjXODg49991WAkwe/CcT9Ipaih00vPElBI/24xvD1bFwrxpPMX8JvdFmun2n9Gq9P6TlVMjVMIny7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:07:34.523447Z"},"content_sha256":"58a9aba3416002795d0b40048f780ca9fecbb3e8bf5d4c0b76b15ac1b23e77d7","schema_version":"1.0","event_id":"sha256:58a9aba3416002795d0b40048f780ca9fecbb3e8bf5d4c0b76b15ac1b23e77d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DRFIUM3UEGJWN62HZ7G6M7O4II/bundle.json","state_url":"https://pith.science/pith/DRFIUM3UEGJWN62HZ7G6M7O4II/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DRFIUM3UEGJWN62HZ7G6M7O4II/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":"2026-05-23T16:07:34Z","links":{"resolver":"https://pith.science/pith/DRFIUM3UEGJWN62HZ7G6M7O4II","bundle":"https://pith.science/pith/DRFIUM3UEGJWN62HZ7G6M7O4II/bundle.json","state":"https://pith.science/pith/DRFIUM3UEGJWN62HZ7G6M7O4II/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DRFIUM3UEGJWN62HZ7G6M7O4II/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:DRFIUM3UEGJWN62HZ7G6M7O4II","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":"20026a1782e0b7c053e538c87433fac417b5a92aa48e52298c975afa9a5bb527","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-19T19:52:36Z","title_canon_sha256":"338eb501bed48be1652cccc3ec1ad76d7518b96c472796525619a6cb50013dd4"},"schema_version":"1.0","source":{"id":"1708.05891","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05891","created_at":"2026-05-18T00:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05891v1","created_at":"2026-05-18T00:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05891","created_at":"2026-05-18T00:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"DRFIUM3UEGJW","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"DRFIUM3UEGJWN62H","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"DRFIUM3U","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:58a9aba3416002795d0b40048f780ca9fecbb3e8bf5d4c0b76b15ac1b23e77d7","target":"graph","created_at":"2026-05-18T00:37:43Z","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":"Arabic word segmentation is essential for a variety of NLP applications such as machine translation and information retrieval. Segmentation entails breaking words into their constituent stems, affixes and clitics. In this paper, we compare two approaches for segmenting four major Arabic dialects using only several thousand training examples for each dialect. The two approaches involve posing the problem as a ranking problem, where an SVM ranker picks the best segmentation, and as a sequence labeling problem, where a bi-LSTM RNN coupled with CRF determines where best to segment words. We are ab","authors_text":"Ahmed Abdelali, Hamdy Mubarak, Kallmeyer Laura, Kareem Darwish, Mohamed Eldesouki, Mohammed Attia, Younes Samih","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-19T19:52:36Z","title":"Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05891","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":"sha256:972093846b029fec525f25bb2a1504a69d65cb4ce75102989c65be2230e9bb55","target":"record","created_at":"2026-05-18T00:37:43Z","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":"20026a1782e0b7c053e538c87433fac417b5a92aa48e52298c975afa9a5bb527","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-19T19:52:36Z","title_canon_sha256":"338eb501bed48be1652cccc3ec1ad76d7518b96c472796525619a6cb50013dd4"},"schema_version":"1.0","source":{"id":"1708.05891","kind":"arxiv","version":1}},"canonical_sha256":"1c4a8a3374219366fb47cfcde67ddc4208dc9d522c22b45e4c5ebd8660d16dc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c4a8a3374219366fb47cfcde67ddc4208dc9d522c22b45e4c5ebd8660d16dc8","first_computed_at":"2026-05-18T00:37:43.830398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:43.830398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uS+BgyCAbxnjGJ3Z+MZlwvERAJEvlr+GCTI/8OQSBjMnXWwlw2o2hcZV7rUmx/oHJoApnEAukr1hJ8W9siZnAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:43.831191Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.05891","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:972093846b029fec525f25bb2a1504a69d65cb4ce75102989c65be2230e9bb55","sha256:58a9aba3416002795d0b40048f780ca9fecbb3e8bf5d4c0b76b15ac1b23e77d7"],"state_sha256":"6f0e1d6410dda08fb8d0f9e0ae9950013d7b20a4119dc0a9b93f4eeff4ec4a77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"30wUz5HDGMrUMByaX8CMxWjsh8aqtbdG+NL2JM2ICY02p/CWq0QUIl9S7Bl92qapl1R+CMt1SHfl4R28q6kjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T16:07:34.527020Z","bundle_sha256":"15002d56d8486e7bddd8be65e21ea0e3605939d721b6201c4253c06880f91921"}}