{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S3ZD6JZ54IPSA76CN5MBOP6HSR","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":"59d0656c87e2fcb4004622f0610fced1d3cd63f63e023d257fc6f313749c9f0e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T17:28:22Z","title_canon_sha256":"299ff9b238f2fd373dfe4a3f4fb2c360acb3c1701f9ef3335408bb5ffc928c27"},"schema_version":"1.0","source":{"id":"2212.09648","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09648","created_at":"2026-07-05T06:33:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09648v4","created_at":"2026-07-05T06:33:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09648","created_at":"2026-07-05T06:33:18Z"},{"alias_kind":"pith_short_12","alias_value":"S3ZD6JZ54IPS","created_at":"2026-07-05T06:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"S3ZD6JZ54IPSA76C","created_at":"2026-07-05T06:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"S3ZD6JZ5","created_at":"2026-07-05T06:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:c22696abc73b1ebca4b9456f71045ed86da1ac1b6f29767ad81f189330f826f8","target":"graph","created_at":"2026-07-05T06:33:18Z","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/2212.09648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present NusaCrowd, a collaborative initiative to collect and unify existing resources for Indonesian languages, including opening access to previously non-public resources. Through this initiative, we have brought together 137 datasets and 118 standardized data loaders. The quality of the datasets has been assessed manually and automatically, and their value is demonstrated through multiple experiments. NusaCrowd's data collection enables the creation of the first zero-shot benchmarks for natural language understanding and generation in Indonesian and the local languages of Indonesia. Furth","authors_text":"Ade Romadhony, Alham Fikri Aji, Ali Akbar Septiandri, Arie Ardiyanti Suryani, Ayu Purwarianti, Bryan Wilie, Cahya Wirawan, Christian Wibisono, Cuk Tho, Dan Su, David Moeljadi, Dyah Damapuspita, Fajri Koto, Frederikus Hudi, Genta Indra Winata, Graham Neubig, Herry Sujaini, Holy Lovenia, Ichwanul Muslim Karo Karo, Ika Alfina, Ilham Firdausi Putra, Ivan Halim Parmonangan, James Jaya, Jennifer Santoso, Karissa Vincentio, Kaustubh D. Dhole, Keith Stevens, Made Nindyatama Nityasya, Muhammad Farid Adilazuarda, Muhammad Satrio Wicaksono, Pascale Fung, Rahmad Mahendra, Rifki Afina Putri, Ryandito Diandaru, Ryan Ignatius, Sakriani Sakti, Samsul Rahmadani, Samuel Cahyawijaya, Sebastian Ruder, Tiezheng Yu, Timothy Baldwin, Tirana Noor Fatyanosa, Vito Ghifari, Wenliang Dai, Yan Xu, Yulianti Oenang, Ziwei Ji","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T17:28:22Z","title":"NusaCrowd: Open Source Initiative for Indonesian NLP Resources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09648","kind":"arxiv","version":4},"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:e59fc6af64e522cf7ad38149b2eb19eed733df1761d9aa69f9d5aa43c647ddbe","target":"record","created_at":"2026-07-05T06:33:18Z","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":"59d0656c87e2fcb4004622f0610fced1d3cd63f63e023d257fc6f313749c9f0e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T17:28:22Z","title_canon_sha256":"299ff9b238f2fd373dfe4a3f4fb2c360acb3c1701f9ef3335408bb5ffc928c27"},"schema_version":"1.0","source":{"id":"2212.09648","kind":"arxiv","version":4}},"canonical_sha256":"96f23f273de21f207fc26f58173fc7946e64cca8ee3eda0872d7aaa18a413626","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96f23f273de21f207fc26f58173fc7946e64cca8ee3eda0872d7aaa18a413626","first_computed_at":"2026-07-05T06:33:18.151513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:18.151513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"by90s+6fjRFedhysU41nyzhbWkgiuLtkbXfwZaof4GutX+wB8x/8f7u0B5JrV0beUL8+ZTUbV9E4W6FzfhGRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:18.152011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09648","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e59fc6af64e522cf7ad38149b2eb19eed733df1761d9aa69f9d5aa43c647ddbe","sha256:c22696abc73b1ebca4b9456f71045ed86da1ac1b6f29767ad81f189330f826f8"],"state_sha256":"f2e141783d2aa0a7a76570e9e481d52b058508262153613f5f854d8fec569e54"}