{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P4UGRLZB6SGL227VCAH4TZND73","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":"685d891d854be3e60783ddcca570ea5d7d81d8a8e2ee2b1442a68b3c5159b77d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T16:17:24Z","title_canon_sha256":"ca8b8fc8515bcfdf37aafb4c7da822587ed0fac957d960f33738889e6aee73e1"},"schema_version":"1.0","source":{"id":"2606.24758","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24758","created_at":"2026-06-24T01:15:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24758v1","created_at":"2026-06-24T01:15:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24758","created_at":"2026-06-24T01:15:41Z"},{"alias_kind":"pith_short_12","alias_value":"P4UGRLZB6SGL","created_at":"2026-06-24T01:15:41Z"},{"alias_kind":"pith_short_16","alias_value":"P4UGRLZB6SGL227V","created_at":"2026-06-24T01:15:41Z"},{"alias_kind":"pith_short_8","alias_value":"P4UGRLZB","created_at":"2026-06-24T01:15:41Z"}],"graph_snapshots":[{"event_id":"sha256:4ac88262b0fca450e889a9125cc6f85caae42d4dbb3e959aac7095ca7148206d","target":"graph","created_at":"2026-06-24T01:15:41Z","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/2606.24758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Handling repeated characters in text can be tricky, since they can represent either the correct spelling of a word or informal character elongation often seen in social media posts. We present CANDLE, a lightweight system for character-level Arabic noise deduplication that addresses this challenge without relying on handcrafted rules, dictionaries, or morphological analyzers. At the heart of CANDLE is a novel application of Connectionist Temporal Classification (CTC) to this task, a formulation not previously explored for character deduplication, which frames normalization as a sequence alignm","authors_text":"Ahmad Ghannam, Anas Salamah, Faris Alasmary, Kholood Al Tabash, Lahouari Ghouti, Orjuwan Zaafarani, Shouq Sadah, Taif Nono","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T16:17:24Z","title":"CANDLE: Character-level Arabic Noise Deduplication using Lightweight Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24758","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":"sha256:931e8b08da5729dce0a15e4b441a5928fd36e35ef8284727d42dbf8eaf68e402","target":"record","created_at":"2026-06-24T01:15:41Z","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":"685d891d854be3e60783ddcca570ea5d7d81d8a8e2ee2b1442a68b3c5159b77d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T16:17:24Z","title_canon_sha256":"ca8b8fc8515bcfdf37aafb4c7da822587ed0fac957d960f33738889e6aee73e1"},"schema_version":"1.0","source":{"id":"2606.24758","kind":"arxiv","version":1}},"canonical_sha256":"7f2868af21f48cbd6bf5100fc9e5a3fef877a34d0acf44d84d70821f5e1df909","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f2868af21f48cbd6bf5100fc9e5a3fef877a34d0acf44d84d70821f5e1df909","first_computed_at":"2026-06-24T01:15:41.446897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:41.446897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UidFzJIGShjZNALc3zxKByikosOUE9pH+Cz8T4TZb1YGcUQUoegcE1kH5Mskd+nUNR18EMxNczRyT6zLn/SCAg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:41.447308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24758","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:931e8b08da5729dce0a15e4b441a5928fd36e35ef8284727d42dbf8eaf68e402","sha256:4ac88262b0fca450e889a9125cc6f85caae42d4dbb3e959aac7095ca7148206d"],"state_sha256":"75ab699496521b4c6c5864db8f191a6e26076b5718629f4151c00ee3aa1e349a"}