{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TC2HAAPWIIVXLEP7HZRAOEOAVR","short_pith_number":"pith:TC2HAAPW","canonical_record":{"source":{"id":"2008.03979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T09:26:00Z","cross_cats_sorted":[],"title_canon_sha256":"7f70aef7a9bb0e4cf63bee640d8e68ec3a2ac94cf079ef0e1ea7fe6e334d10a4","abstract_canon_sha256":"60107ac2a124f580d68fa8c7ab9cb9882e1aba98e19f523bd3cbe663ef170ec6"},"schema_version":"1.0"},"canonical_sha256":"98b47001f6422b7591ff3e620711c0ac49a1ba527cb09563aafa9bde06f078cc","source":{"kind":"arxiv","id":"2008.03979","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03979","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03979v2","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03979","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"TC2HAAPWIIVX","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"TC2HAAPWIIVXLEP7","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"TC2HAAPW","created_at":"2026-07-05T01:26:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TC2HAAPWIIVXLEP7HZRAOEOAVR","target":"record","payload":{"canonical_record":{"source":{"id":"2008.03979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T09:26:00Z","cross_cats_sorted":[],"title_canon_sha256":"7f70aef7a9bb0e4cf63bee640d8e68ec3a2ac94cf079ef0e1ea7fe6e334d10a4","abstract_canon_sha256":"60107ac2a124f580d68fa8c7ab9cb9882e1aba98e19f523bd3cbe663ef170ec6"},"schema_version":"1.0"},"canonical_sha256":"98b47001f6422b7591ff3e620711c0ac49a1ba527cb09563aafa9bde06f078cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:23.972036Z","signature_b64":"+MqRM3q+iHq06BoyzjQTRP+9YxnRqTerQ+vNrq4tEkmfMLEb6akf4jih3sq4QNGWqsDRt6BFf5Ad2DQGFKdFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98b47001f6422b7591ff3e620711c0ac49a1ba527cb09563aafa9bde06f078cc","last_reissued_at":"2026-07-05T01:26:23.971565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:23.971565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.03979","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":"2026-07-05T01:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbLsHF99JZwIHzBjHP6o0PdZotK2dKviyaWyRcTTG8TLdqa5LdoncysXBRr8op+K4HpgLTaf9cRd7i+8jTqGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:45:29.627900Z"},"content_sha256":"f5c4e64346b65a117db7a383eba6f2e90257bb1234ff7c1280459e2fbf9d4153","schema_version":"1.0","event_id":"sha256:f5c4e64346b65a117db7a383eba6f2e90257bb1234ff7c1280459e2fbf9d4153"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TC2HAAPWIIVXLEP7HZRAOEOAVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KR-BERT: A Small-Scale Korean-Specific Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hansol Jang, Hyopil Shin, Sangah Lee, Suzi Park, Yunmee Baik","submitted_at":"2020-08-10T09:26:00Z","abstract_excerpt":"Since the appearance of BERT, recent works including XLNet and RoBERTa utilize sentence embedding models pre-trained by large corpora and a large number of parameters. Because such models have large hardware and a huge amount of data, they take a long time to pre-train. Therefore it is important to attempt to make smaller models that perform comparatively. In this paper, we trained a Korean-specific model KR-BERT, utilizing a smaller vocabulary and dataset. Since Korean is one of the morphologically rich languages with poor resources using non-Latin alphabets, it is also important to capture l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03979","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/2008.03979/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":"2026-07-05T01:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBVx/0oCOYbUDfWQhxGmet+SvfKgDZAroNhHh4v4epI3zLAa+yQOkAiGqYf8PxbJt9CovsjN+MaMQcKIvIzDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:45:29.628677Z"},"content_sha256":"b1b60f3997c43709a66498cb958d26b937d9c829e4de4b3c49aaefe3c519c6a8","schema_version":"1.0","event_id":"sha256:b1b60f3997c43709a66498cb958d26b937d9c829e4de4b3c49aaefe3c519c6a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TC2HAAPWIIVXLEP7HZRAOEOAVR/bundle.json","state_url":"https://pith.science/pith/TC2HAAPWIIVXLEP7HZRAOEOAVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TC2HAAPWIIVXLEP7HZRAOEOAVR/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":"2026-08-16T20:45:29Z","links":{"resolver":"https://pith.science/pith/TC2HAAPWIIVXLEP7HZRAOEOAVR","bundle":"https://pith.science/pith/TC2HAAPWIIVXLEP7HZRAOEOAVR/bundle.json","state":"https://pith.science/pith/TC2HAAPWIIVXLEP7HZRAOEOAVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TC2HAAPWIIVXLEP7HZRAOEOAVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TC2HAAPWIIVXLEP7HZRAOEOAVR","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":"60107ac2a124f580d68fa8c7ab9cb9882e1aba98e19f523bd3cbe663ef170ec6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T09:26:00Z","title_canon_sha256":"7f70aef7a9bb0e4cf63bee640d8e68ec3a2ac94cf079ef0e1ea7fe6e334d10a4"},"schema_version":"1.0","source":{"id":"2008.03979","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03979","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03979v2","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03979","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"TC2HAAPWIIVX","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"TC2HAAPWIIVXLEP7","created_at":"2026-07-05T01:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"TC2HAAPW","created_at":"2026-07-05T01:26:23Z"}],"graph_snapshots":[{"event_id":"sha256:b1b60f3997c43709a66498cb958d26b937d9c829e4de4b3c49aaefe3c519c6a8","target":"graph","created_at":"2026-07-05T01:26:23Z","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/2008.03979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since the appearance of BERT, recent works including XLNet and RoBERTa utilize sentence embedding models pre-trained by large corpora and a large number of parameters. Because such models have large hardware and a huge amount of data, they take a long time to pre-train. Therefore it is important to attempt to make smaller models that perform comparatively. In this paper, we trained a Korean-specific model KR-BERT, utilizing a smaller vocabulary and dataset. Since Korean is one of the morphologically rich languages with poor resources using non-Latin alphabets, it is also important to capture l","authors_text":"Hansol Jang, Hyopil Shin, Sangah Lee, Suzi Park, Yunmee Baik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T09:26:00Z","title":"KR-BERT: A Small-Scale Korean-Specific Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03979","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:f5c4e64346b65a117db7a383eba6f2e90257bb1234ff7c1280459e2fbf9d4153","target":"record","created_at":"2026-07-05T01:26:23Z","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":"60107ac2a124f580d68fa8c7ab9cb9882e1aba98e19f523bd3cbe663ef170ec6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-10T09:26:00Z","title_canon_sha256":"7f70aef7a9bb0e4cf63bee640d8e68ec3a2ac94cf079ef0e1ea7fe6e334d10a4"},"schema_version":"1.0","source":{"id":"2008.03979","kind":"arxiv","version":2}},"canonical_sha256":"98b47001f6422b7591ff3e620711c0ac49a1ba527cb09563aafa9bde06f078cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98b47001f6422b7591ff3e620711c0ac49a1ba527cb09563aafa9bde06f078cc","first_computed_at":"2026-07-05T01:26:23.971565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:26:23.971565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+MqRM3q+iHq06BoyzjQTRP+9YxnRqTerQ+vNrq4tEkmfMLEb6akf4jih3sq4QNGWqsDRt6BFf5Ad2DQGFKdFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:26:23.972036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03979","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5c4e64346b65a117db7a383eba6f2e90257bb1234ff7c1280459e2fbf9d4153","sha256:b1b60f3997c43709a66498cb958d26b937d9c829e4de4b3c49aaefe3c519c6a8"],"state_sha256":"c598d849265fc7332de3c08889b3b05e4dad6993c9235821ec90192e2ce3396e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RSvTZBM3Y04Yn0v3Q33aUMSmr8EjtgKiAOANKQtPBYO7LXsIcWmpOtddEKsIRrKR8dacy+bIxutthS1ISIMWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:45:29.633690Z","bundle_sha256":"bb2250bb3253b497cc8e7bf7ee96e323fdc9bf048fb6e57c72c59d2d326f5887"}}