{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SVKSCKYYAF2ZMIOR3DFK3E6U7J","short_pith_number":"pith:SVKSCKYY","canonical_record":{"source":{"id":"2511.13182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-17T09:43:54Z","cross_cats_sorted":[],"title_canon_sha256":"e4ab23d75a45cde41ae20f22404a35cb940777b5d06b92332a20c18b2bc1b8d4","abstract_canon_sha256":"5fedf69e2590bb1cd3ac44e47079d7c5c9c60f55e0c1b72ce94b80000a618544"},"schema_version":"1.0"},"canonical_sha256":"9555212b1801759621d1d8caad93d4fa6403f6afd128785374382048796d2944","source":{"kind":"arxiv","id":"2511.13182","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.13182","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2511.13182v3","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.13182","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"SVKSCKYYAF2Z","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"SVKSCKYYAF2ZMIOR","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"SVKSCKYY","created_at":"2026-07-14T01:22:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SVKSCKYYAF2ZMIOR3DFK3E6U7J","target":"record","payload":{"canonical_record":{"source":{"id":"2511.13182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-17T09:43:54Z","cross_cats_sorted":[],"title_canon_sha256":"e4ab23d75a45cde41ae20f22404a35cb940777b5d06b92332a20c18b2bc1b8d4","abstract_canon_sha256":"5fedf69e2590bb1cd3ac44e47079d7c5c9c60f55e0c1b72ce94b80000a618544"},"schema_version":"1.0"},"canonical_sha256":"9555212b1801759621d1d8caad93d4fa6403f6afd128785374382048796d2944","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:02.235499Z","signature_b64":"6SoJornFNOx9y+Z45eQ0XyLio8Art6ST+I7hlQhD4Rjuql0LrzBf01thUu7FZEE9Zpc4btWLTlhwiR+8kl5kDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9555212b1801759621d1d8caad93d4fa6403f6afd128785374382048796d2944","last_reissued_at":"2026-07-14T01:22:02.234562Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:02.234562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.13182","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4RoXCVT2DCjQtVKTGR68ejn/SmiwLW7mi8w4rtLuNOI2GpcUIIyN38c+VNrMMBV7z2uU93PAz8wDpnG8/uujBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:04:32.958675Z"},"content_sha256":"32ab9b373ab487bfbdcfd59045244b66a4f1f9bbfaaaca92055f6b8a77738c10","schema_version":"1.0","event_id":"sha256:32ab9b373ab487bfbdcfd59045244b66a4f1f9bbfaaaca92055f6b8a77738c10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SVKSCKYYAF2ZMIOR3DFK3E6U7J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Laura Diosan, Mihai Nadas","submitted_at":"2025-11-17T09:43:54Z","abstract_excerpt":"Automatic diacritic restoration is crucial for text processing in languages with rich diacritical marks, such as Romanian. This study evaluates the performance of several large language models (LLMs) in restoring diacritics in Romanian texts. Using a comprehensive corpus, we tested models including OpenAI's GPT-3.5, GPT-4, GPT-4o, Google's Gemini 1.0 Pro, Meta's Llama 2 and Llama 3, MistralAI's Mixtral 8x7B Instruct, airoboros 70B, and OpenLLM-Ro's RoLlama 2 7B, under multiple prompt templates ranging from zero-shot to complex multi-shot instructions. Results show that models such as GPT-4o ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.13182","kind":"arxiv","version":3},"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/2511.13182/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":"2026-07-14T01:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AJKyNtBOBdXd85WTngrmdMuVQ9D3Ct8pJhQOn6XSSiyzRVcCjeE06/CFnxH8Ejkpl/1kfTrGamB7mz3SzHWaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:04:32.959902Z"},"content_sha256":"98a831edb29a8b837927befe31f58655cad74838140f5250ff7eba354da573c6","schema_version":"1.0","event_id":"sha256:98a831edb29a8b837927befe31f58655cad74838140f5250ff7eba354da573c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVKSCKYYAF2ZMIOR3DFK3E6U7J/bundle.json","state_url":"https://pith.science/pith/SVKSCKYYAF2ZMIOR3DFK3E6U7J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVKSCKYYAF2ZMIOR3DFK3E6U7J/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":"2026-08-04T22:04:32Z","links":{"resolver":"https://pith.science/pith/SVKSCKYYAF2ZMIOR3DFK3E6U7J","bundle":"https://pith.science/pith/SVKSCKYYAF2ZMIOR3DFK3E6U7J/bundle.json","state":"https://pith.science/pith/SVKSCKYYAF2ZMIOR3DFK3E6U7J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVKSCKYYAF2ZMIOR3DFK3E6U7J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SVKSCKYYAF2ZMIOR3DFK3E6U7J","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":"5fedf69e2590bb1cd3ac44e47079d7c5c9c60f55e0c1b72ce94b80000a618544","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-17T09:43:54Z","title_canon_sha256":"e4ab23d75a45cde41ae20f22404a35cb940777b5d06b92332a20c18b2bc1b8d4"},"schema_version":"1.0","source":{"id":"2511.13182","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.13182","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2511.13182v3","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.13182","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"SVKSCKYYAF2Z","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"SVKSCKYYAF2ZMIOR","created_at":"2026-07-14T01:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"SVKSCKYY","created_at":"2026-07-14T01:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:98a831edb29a8b837927befe31f58655cad74838140f5250ff7eba354da573c6","target":"graph","created_at":"2026-07-14T01:22:02Z","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/2511.13182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic diacritic restoration is crucial for text processing in languages with rich diacritical marks, such as Romanian. This study evaluates the performance of several large language models (LLMs) in restoring diacritics in Romanian texts. Using a comprehensive corpus, we tested models including OpenAI's GPT-3.5, GPT-4, GPT-4o, Google's Gemini 1.0 Pro, Meta's Llama 2 and Llama 3, MistralAI's Mixtral 8x7B Instruct, airoboros 70B, and OpenLLM-Ro's RoLlama 2 7B, under multiple prompt templates ranging from zero-shot to complex multi-shot instructions. Results show that models such as GPT-4o ac","authors_text":"Laura Diosan, Mihai Nadas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-17T09:43:54Z","title":"Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.13182","kind":"arxiv","version":3},"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":"sha256:32ab9b373ab487bfbdcfd59045244b66a4f1f9bbfaaaca92055f6b8a77738c10","target":"record","created_at":"2026-07-14T01:22:02Z","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":"5fedf69e2590bb1cd3ac44e47079d7c5c9c60f55e0c1b72ce94b80000a618544","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-17T09:43:54Z","title_canon_sha256":"e4ab23d75a45cde41ae20f22404a35cb940777b5d06b92332a20c18b2bc1b8d4"},"schema_version":"1.0","source":{"id":"2511.13182","kind":"arxiv","version":3}},"canonical_sha256":"9555212b1801759621d1d8caad93d4fa6403f6afd128785374382048796d2944","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9555212b1801759621d1d8caad93d4fa6403f6afd128785374382048796d2944","first_computed_at":"2026-07-14T01:22:02.234562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:02.234562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6SoJornFNOx9y+Z45eQ0XyLio8Art6ST+I7hlQhD4Rjuql0LrzBf01thUu7FZEE9Zpc4btWLTlhwiR+8kl5kDA==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:02.235499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.13182","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32ab9b373ab487bfbdcfd59045244b66a4f1f9bbfaaaca92055f6b8a77738c10","sha256:98a831edb29a8b837927befe31f58655cad74838140f5250ff7eba354da573c6"],"state_sha256":"333c80c91c8904779c3dd86e82317e81eab92d2a86e189eb9628c12c38406f59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"byRl7ZWRe+lrnlfS27ofTPB47UwN8vD8fdlF6uNaZ47hUslOFayOcBxtYxY9UVBcD0DskkRZW7A9fIniYjqxBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:04:32.968826Z","bundle_sha256":"1ccbc2e377667e71ffa33f587bddbd1a032da45f7b1ecbbbc35a31e86d8fda6a"}}