{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2KNG5UWJKUYVXGLTCRCHKEUXL6","short_pith_number":"pith:2KNG5UWJ","canonical_record":{"source":{"id":"2306.03557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-06T10:18:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c35f1ccecf0d80a28a857fd42ff2ff54ef02d21aebfa0eefca977ca66df991f","abstract_canon_sha256":"c0ba604e4a9ba2801e5d23ed81f79e349e7243aab1c7e5cf2bdef7ced8f948a7"},"schema_version":"1.0"},"canonical_sha256":"d29a6ed2c955315b997314447512975faeadfdfaea3636b0ef92f97784b21adb","source":{"kind":"arxiv","id":"2306.03557","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03557","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03557v2","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03557","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"2KNG5UWJKUYV","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"2KNG5UWJKUYVXGLT","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"2KNG5UWJ","created_at":"2026-07-05T06:35:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2KNG5UWJKUYVXGLTCRCHKEUXL6","target":"record","payload":{"canonical_record":{"source":{"id":"2306.03557","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-06T10:18:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c35f1ccecf0d80a28a857fd42ff2ff54ef02d21aebfa0eefca977ca66df991f","abstract_canon_sha256":"c0ba604e4a9ba2801e5d23ed81f79e349e7243aab1c7e5cf2bdef7ced8f948a7"},"schema_version":"1.0"},"canonical_sha256":"d29a6ed2c955315b997314447512975faeadfdfaea3636b0ef92f97784b21adb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:52.047141Z","signature_b64":"D941TAzze95jQ7+2+e6gCPXQW5Kvxax4ZKDZcCp+x97DODvm1AVnXclfyNXc5/JofcpiGsVE298hYoR2hJOfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d29a6ed2c955315b997314447512975faeadfdfaea3636b0ef92f97784b21adb","last_reissued_at":"2026-07-05T06:35:52.046750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:52.046750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.03557","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":"2026-07-05T06:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPN4aPrziB+DiU447pb9eO53AWfbBOa7nWmbm7apd9wKdZAQeW5FfO2LN9UKMrrVxxwDOSKP0+Kj4fo2xF5OBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:28:18.959296Z"},"content_sha256":"d751f0207b50fc9f142b575fb08b080ec0d44f396f59ab837a1ad6e1ee6e6604","schema_version":"1.0","event_id":"sha256:d751f0207b50fc9f142b575fb08b080ec0d44f396f59ab837a1ad6e1ee6e6604"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2KNG5UWJKUYVXGLTCRCHKEUXL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mattia Di Gangi, Mohammad Zeineldeen, Nick Rossenbach, Parnia Bahar","submitted_at":"2023-06-06T10:18:17Z","abstract_excerpt":"Automatic Arabic diacritization is useful in many applications, ranging from reading support for language learners to accurate pronunciation predictor for downstream tasks like speech synthesis. While most of the previous works focused on models that operate on raw non-diacritized text, production systems can gain accuracy by first letting humans partly annotate ambiguous words. In this paper, we propose 2SDiac, a multi-source model that can effectively support optional diacritics in input to inform all predictions. We also introduce Guided Learning, a training scheme to leverage given diacrit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03557","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/2306.03557/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":"2026-07-05T06:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sEDXsZrJN4nQUgCniDqztVPCgq30uGswrLDKgCpzwnynCO++KfB1Y2SMr30OLpmfAFI8V//rnyMBp2rDEC4IAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:28:18.959842Z"},"content_sha256":"392faccc1f4abb7af00bce6c46ce819de79f22edecb129239a4eeb7e72bfdc79","schema_version":"1.0","event_id":"sha256:392faccc1f4abb7af00bce6c46ce819de79f22edecb129239a4eeb7e72bfdc79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KNG5UWJKUYVXGLTCRCHKEUXL6/bundle.json","state_url":"https://pith.science/pith/2KNG5UWJKUYVXGLTCRCHKEUXL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KNG5UWJKUYVXGLTCRCHKEUXL6/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":"2026-08-19T01:28:18Z","links":{"resolver":"https://pith.science/pith/2KNG5UWJKUYVXGLTCRCHKEUXL6","bundle":"https://pith.science/pith/2KNG5UWJKUYVXGLTCRCHKEUXL6/bundle.json","state":"https://pith.science/pith/2KNG5UWJKUYVXGLTCRCHKEUXL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KNG5UWJKUYVXGLTCRCHKEUXL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2KNG5UWJKUYVXGLTCRCHKEUXL6","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":"c0ba604e4a9ba2801e5d23ed81f79e349e7243aab1c7e5cf2bdef7ced8f948a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-06T10:18:17Z","title_canon_sha256":"2c35f1ccecf0d80a28a857fd42ff2ff54ef02d21aebfa0eefca977ca66df991f"},"schema_version":"1.0","source":{"id":"2306.03557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03557","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03557v2","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03557","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"2KNG5UWJKUYV","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"2KNG5UWJKUYVXGLT","created_at":"2026-07-05T06:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"2KNG5UWJ","created_at":"2026-07-05T06:35:52Z"}],"graph_snapshots":[{"event_id":"sha256:392faccc1f4abb7af00bce6c46ce819de79f22edecb129239a4eeb7e72bfdc79","target":"graph","created_at":"2026-07-05T06:35:52Z","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/2306.03557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Arabic diacritization is useful in many applications, ranging from reading support for language learners to accurate pronunciation predictor for downstream tasks like speech synthesis. While most of the previous works focused on models that operate on raw non-diacritized text, production systems can gain accuracy by first letting humans partly annotate ambiguous words. In this paper, we propose 2SDiac, a multi-source model that can effectively support optional diacritics in input to inform all predictions. We also introduce Guided Learning, a training scheme to leverage given diacrit","authors_text":"Mattia Di Gangi, Mohammad Zeineldeen, Nick Rossenbach, Parnia Bahar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-06T10:18:17Z","title":"Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03557","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:d751f0207b50fc9f142b575fb08b080ec0d44f396f59ab837a1ad6e1ee6e6604","target":"record","created_at":"2026-07-05T06:35:52Z","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":"c0ba604e4a9ba2801e5d23ed81f79e349e7243aab1c7e5cf2bdef7ced8f948a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-06T10:18:17Z","title_canon_sha256":"2c35f1ccecf0d80a28a857fd42ff2ff54ef02d21aebfa0eefca977ca66df991f"},"schema_version":"1.0","source":{"id":"2306.03557","kind":"arxiv","version":2}},"canonical_sha256":"d29a6ed2c955315b997314447512975faeadfdfaea3636b0ef92f97784b21adb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d29a6ed2c955315b997314447512975faeadfdfaea3636b0ef92f97784b21adb","first_computed_at":"2026-07-05T06:35:52.046750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:52.046750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D941TAzze95jQ7+2+e6gCPXQW5Kvxax4ZKDZcCp+x97DODvm1AVnXclfyNXc5/JofcpiGsVE298hYoR2hJOfCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:52.047141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d751f0207b50fc9f142b575fb08b080ec0d44f396f59ab837a1ad6e1ee6e6604","sha256:392faccc1f4abb7af00bce6c46ce819de79f22edecb129239a4eeb7e72bfdc79"],"state_sha256":"28814d02d93e1bddb92291a311521478f82e7c970647f76008d9c90f4ff7c365"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fg2sL6q1g7vFOZ9GmOg2q2LpF8zBkKrE3JxmLSNmmXM4mrHwNLVTHgVrMC5wcdJYipAKI3t8JWrqtk1mNvWWBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T01:28:18.964827Z","bundle_sha256":"1ff156d35dc2ed9bffd74a97f115a2bb2c2f12a0d92158ae149caa6e96d0dc44"}}