{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XUQGUI457JCL2OEXEXGDO2EB4Z","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":"4a7c09b40f4642035c08233f6890a5c32d2fc6a58af29048264c196255fe01fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T10:00:33Z","title_canon_sha256":"18304f9100149a4f6e3149f01378f25b7a8faf682249694b91ba898d3c257527"},"schema_version":"1.0","source":{"id":"2411.09318","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09318","created_at":"2026-07-05T09:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09318v2","created_at":"2026-07-05T09:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09318","created_at":"2026-07-05T09:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"XUQGUI457JCL","created_at":"2026-07-05T09:35:54Z"},{"alias_kind":"pith_short_16","alias_value":"XUQGUI457JCL2OEX","created_at":"2026-07-05T09:35:54Z"},{"alias_kind":"pith_short_8","alias_value":"XUQGUI45","created_at":"2026-07-05T09:35:54Z"}],"graph_snapshots":[{"event_id":"sha256:2b90dab985a5a3d300f4cbcf4c83333d7d1b91433fb17729931509149d20f41d","target":"graph","created_at":"2026-07-05T09:35:54Z","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/2411.09318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Indonesia is one of the most diverse countries linguistically. However, despite this linguistic diversity, Indonesian languages remain underrepresented in Natural Language Processing (NLP) research and technologies. In the past two years, several efforts have been conducted to construct NLP resources for Indonesian languages. However, most of these efforts have been focused on creating manual resources thus difficult to scale to more languages. Although many Indonesian languages do not have a web presence, locally there are resources that document these languages well in printed forms such as ","authors_text":"Afinzaki Amiral, Ayu Purwarianti, Derry Tanti Wijaya, Kumara Ari Yuana, Mohammad Rifqi Farhansyah, Muhammad Zuhdi Fikri Johari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T10:00:33Z","title":"DriveThru: a Document Extraction Platform and Benchmark Datasets for Indonesian Local Language Archives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09318","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":"sha256:7a73680e4d628a64c3f2db0a3f34e187732100d0c97c789c2adda44b1e21b7b1","target":"record","created_at":"2026-07-05T09:35:54Z","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":"4a7c09b40f4642035c08233f6890a5c32d2fc6a58af29048264c196255fe01fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-14T10:00:33Z","title_canon_sha256":"18304f9100149a4f6e3149f01378f25b7a8faf682249694b91ba898d3c257527"},"schema_version":"1.0","source":{"id":"2411.09318","kind":"arxiv","version":2}},"canonical_sha256":"bd206a239dfa44bd389725cc376881e66aeb8953b8b2cc02cad816df5d20be1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd206a239dfa44bd389725cc376881e66aeb8953b8b2cc02cad816df5d20be1a","first_computed_at":"2026-07-05T09:35:54.698991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:54.698991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2mooYAIxt3303JIUze/BiY2guyO2txDgP+3X7guDjkwhHKi7CqtsX0spQINYBdpwL+rhGXbLnOg0CU4dw6W0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:54.699504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09318","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a73680e4d628a64c3f2db0a3f34e187732100d0c97c789c2adda44b1e21b7b1","sha256:2b90dab985a5a3d300f4cbcf4c83333d7d1b91433fb17729931509149d20f41d"],"state_sha256":"db226ce4ee80f88651ae080b060b5b6452b007ecb10d800abbedf6bc3caf0324"}