{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XZMJEZOHXB3KZKJIDUZG74SPCY","short_pith_number":"pith:XZMJEZOH","canonical_record":{"source":{"id":"2012.15621","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T14:23:55Z","cross_cats_sorted":[],"title_canon_sha256":"47327f41095d8013696d7e1fe05679e6c7637f2760fe85984eb14b87f536f70f","abstract_canon_sha256":"3085ae44fe7cd62dc1e94c43e3cc951315e8a1ba67eefa5ef9b829d7c20f09f4"},"schema_version":"1.0"},"canonical_sha256":"be589265c7b876aca9281d326ff24f160a842b4eec3e2f374f7f6f24480569b7","source":{"kind":"arxiv","id":"2012.15621","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15621","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15621v3","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15621","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"XZMJEZOHXB3K","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"XZMJEZOHXB3KZKJI","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"XZMJEZOH","created_at":"2026-06-10T01:10:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XZMJEZOHXB3KZKJIDUZG74SPCY","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15621","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T14:23:55Z","cross_cats_sorted":[],"title_canon_sha256":"47327f41095d8013696d7e1fe05679e6c7637f2760fe85984eb14b87f536f70f","abstract_canon_sha256":"3085ae44fe7cd62dc1e94c43e3cc951315e8a1ba67eefa5ef9b829d7c20f09f4"},"schema_version":"1.0"},"canonical_sha256":"be589265c7b876aca9281d326ff24f160a842b4eec3e2f374f7f6f24480569b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:54.999357Z","signature_b64":"+UU5QnDcWlUgg93MOpyfuZxtaZa8fVLWXZjVBK4O4c1mWy2VR27pOKfN9ef97ILqfbZv+JwkZUkv5nuU8M86AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be589265c7b876aca9281d326ff24f160a842b4eec3e2f374f7f6f24480569b7","last_reissued_at":"2026-06-10T01:10:54.998472Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:54.998472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15621","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":"2026-06-10T01:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMDN6ByRMKwI8PlMgxvEeo25sVMX/a/BRzydo6ADU0yHJ0hugNsTgPaWENiJcL3l92TVRBIzgP+ZUSMMKq9LBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T00:57:59.066371Z"},"content_sha256":"6d71b8b8424a32bb5499f04de468036b835be599284c942b998c3d4756c7916e","schema_version":"1.0","event_id":"sha256:6d71b8b8424a32bb5499f04de468036b835be599284c942b998c3d4756c7916e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XZMJEZOHXB3KZKJIDUZG74SPCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open Korean Corpora: A Practical Report","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sangwhan Moon, Won Ik Cho, Youngsook Song","submitted_at":"2020-12-31T14:23:55Z","abstract_excerpt":"Korean is often referred to as a low-resource language in the research community. While this claim is partially true, it is also because the availability of resources is inadequately advertised and curated. This work curates and reviews a list of Korean corpora, first describing institution-level resource development, then further iterate through a list of current open datasets for different types of tasks. We then propose a direction on how open-source dataset construction and releases should be done for less-resourced languages to promote research."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15621","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/2012.15621/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":"2026-06-10T01:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MV92yAQCFjCGrFCJKKK1NPVqbEPQH59EzBnjyZuYzInhplhXSosgNEzvucVi4jeh/O7IrxSeeFxDw24HJrJCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T00:57:59.067196Z"},"content_sha256":"9470a8a67dc724b25981107b6f5ff07cb0756dd61a600088a55d4f0e049b5ecb","schema_version":"1.0","event_id":"sha256:9470a8a67dc724b25981107b6f5ff07cb0756dd61a600088a55d4f0e049b5ecb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZMJEZOHXB3KZKJIDUZG74SPCY/bundle.json","state_url":"https://pith.science/pith/XZMJEZOHXB3KZKJIDUZG74SPCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZMJEZOHXB3KZKJIDUZG74SPCY/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":"2026-06-30T00:57:59Z","links":{"resolver":"https://pith.science/pith/XZMJEZOHXB3KZKJIDUZG74SPCY","bundle":"https://pith.science/pith/XZMJEZOHXB3KZKJIDUZG74SPCY/bundle.json","state":"https://pith.science/pith/XZMJEZOHXB3KZKJIDUZG74SPCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZMJEZOHXB3KZKJIDUZG74SPCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XZMJEZOHXB3KZKJIDUZG74SPCY","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":"3085ae44fe7cd62dc1e94c43e3cc951315e8a1ba67eefa5ef9b829d7c20f09f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T14:23:55Z","title_canon_sha256":"47327f41095d8013696d7e1fe05679e6c7637f2760fe85984eb14b87f536f70f"},"schema_version":"1.0","source":{"id":"2012.15621","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15621","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15621v3","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15621","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"XZMJEZOHXB3K","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"XZMJEZOHXB3KZKJI","created_at":"2026-06-10T01:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"XZMJEZOH","created_at":"2026-06-10T01:10:54Z"}],"graph_snapshots":[{"event_id":"sha256:9470a8a67dc724b25981107b6f5ff07cb0756dd61a600088a55d4f0e049b5ecb","target":"graph","created_at":"2026-06-10T01:10:54Z","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/2012.15621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Korean is often referred to as a low-resource language in the research community. While this claim is partially true, it is also because the availability of resources is inadequately advertised and curated. This work curates and reviews a list of Korean corpora, first describing institution-level resource development, then further iterate through a list of current open datasets for different types of tasks. We then propose a direction on how open-source dataset construction and releases should be done for less-resourced languages to promote research.","authors_text":"Sangwhan Moon, Won Ik Cho, Youngsook Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T14:23:55Z","title":"Open Korean Corpora: A Practical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15621","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":"sha256:6d71b8b8424a32bb5499f04de468036b835be599284c942b998c3d4756c7916e","target":"record","created_at":"2026-06-10T01:10:54Z","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":"3085ae44fe7cd62dc1e94c43e3cc951315e8a1ba67eefa5ef9b829d7c20f09f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T14:23:55Z","title_canon_sha256":"47327f41095d8013696d7e1fe05679e6c7637f2760fe85984eb14b87f536f70f"},"schema_version":"1.0","source":{"id":"2012.15621","kind":"arxiv","version":3}},"canonical_sha256":"be589265c7b876aca9281d326ff24f160a842b4eec3e2f374f7f6f24480569b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be589265c7b876aca9281d326ff24f160a842b4eec3e2f374f7f6f24480569b7","first_computed_at":"2026-06-10T01:10:54.998472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:54.998472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+UU5QnDcWlUgg93MOpyfuZxtaZa8fVLWXZjVBK4O4c1mWy2VR27pOKfN9ef97ILqfbZv+JwkZUkv5nuU8M86AA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:54.999357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15621","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d71b8b8424a32bb5499f04de468036b835be599284c942b998c3d4756c7916e","sha256:9470a8a67dc724b25981107b6f5ff07cb0756dd61a600088a55d4f0e049b5ecb"],"state_sha256":"7190944b1b583698fbbbb21094f3c94a895e9d0610c26de4aa1aed2c758a3fb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gadGzU4wGErsTb/gBuZwlQNgmqN8PdKIVckRJNRiBh+ZfctGBSkI09oBgmPXpHkjH+8YOx+5XSSur0oadiIkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T00:57:59.073568Z","bundle_sha256":"373bcd9089bebfdb46faafa548348a7a8aafd42b995a71825eaef597b2705a36"}}