{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XVEZYALXZUXKZDBIOQT7CZPBFR","short_pith_number":"pith:XVEZYALX","canonical_record":{"source":{"id":"2607.20443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:23:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ffa95e75684d37f7f83ae8cd235925d2e0b981bbf58222c51269bc67647b671a","abstract_canon_sha256":"e5e4929000b0f41d8ef299a2740afe2907e3dbc23d0068ded5debe3b58e4191b"},"schema_version":"1.0"},"canonical_sha256":"bd499c0177cd2eac8c287427f165e12c4e167994e38c75fa2e810f2315beb5f0","source":{"kind":"arxiv","id":"2607.20443","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20443","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20443v1","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20443","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"pith_short_12","alias_value":"XVEZYALXZUXK","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"pith_short_16","alias_value":"XVEZYALXZUXKZDBI","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"pith_short_8","alias_value":"XVEZYALX","created_at":"2026-07-24T00:23:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XVEZYALXZUXKZDBIOQT7CZPBFR","target":"record","payload":{"canonical_record":{"source":{"id":"2607.20443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:23:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ffa95e75684d37f7f83ae8cd235925d2e0b981bbf58222c51269bc67647b671a","abstract_canon_sha256":"e5e4929000b0f41d8ef299a2740afe2907e3dbc23d0068ded5debe3b58e4191b"},"schema_version":"1.0"},"canonical_sha256":"bd499c0177cd2eac8c287427f165e12c4e167994e38c75fa2e810f2315beb5f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:15.701835Z","signature_b64":"Pl3UeyNSr3rDmPAG9tjEb4lEaGK8j5WPiAPwvgyAbmzW7BDuHnmvCj+u0ieZ5bpMVhVQZLn3/bBKJOVIobugDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd499c0177cd2eac8c287427f165e12c4e167994e38c75fa2e810f2315beb5f0","last_reissued_at":"2026-07-24T00:23:15.700876Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:15.700876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.20443","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-24T00:23:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u+9IyhYsRcbQ+OtbgpEwwfPWo0GirKHmKSWaUy5mVQov/eQD/mr8I5q9d81KQAgdBwuXuwiDlBS/sSsqs2nwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:50:28.139762Z"},"content_sha256":"0d908ff13cd548ddda16e8c8131ba47637b7c87cd38173c1bdd6a5450092ba7b","schema_version":"1.0","event_id":"sha256:0d908ff13cd548ddda16e8c8131ba47637b7c87cd38173c1bdd6a5450092ba7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XVEZYALXZUXKZDBIOQT7CZPBFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Daekeun Kim","submitted_at":"2026-05-12T15:23:59Z","abstract_excerpt":"We release GLAN-QnA-KR, a 303,581-row openly redistributable Korean instruction-QA corpus produced via the seedless taxonomy-driven GLAN synthesis pipeline with Microsoft's Phi-3.5-MoE-instruct as the producer model (generation: 2024-12; release: 2024-12; licence: OpenRAIL). The corpus spans a flat taxonomy of 1,084 English-labelled disciplines paired with Korean question/answer text, a 100-900 difficulty scale, and a median of 313 question characters and 1,098 answer characters per record. Two properties are atypical for synthetic instruction data at this scale: (i) exact duplicate questions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20443","kind":"arxiv","version":1},"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/2607.20443/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":"2026-07-24T00:23:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j1XY4rvluheFn5aWiGDtLSWr5w/lFcBGq8IxpvqdNdyHD3F5NSziI6/3YXXiO9ZI8WxRJ/0K5/x1c6xS+Q4/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:50:28.140294Z"},"content_sha256":"98e97858d38072cecd3dd90958a7e5609965e3d3ab411438e67f358d1e370a21","schema_version":"1.0","event_id":"sha256:98e97858d38072cecd3dd90958a7e5609965e3d3ab411438e67f358d1e370a21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVEZYALXZUXKZDBIOQT7CZPBFR/bundle.json","state_url":"https://pith.science/pith/XVEZYALXZUXKZDBIOQT7CZPBFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVEZYALXZUXKZDBIOQT7CZPBFR/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":"2026-08-04T08:50:28Z","links":{"resolver":"https://pith.science/pith/XVEZYALXZUXKZDBIOQT7CZPBFR","bundle":"https://pith.science/pith/XVEZYALXZUXKZDBIOQT7CZPBFR/bundle.json","state":"https://pith.science/pith/XVEZYALXZUXKZDBIOQT7CZPBFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVEZYALXZUXKZDBIOQT7CZPBFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XVEZYALXZUXKZDBIOQT7CZPBFR","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":"e5e4929000b0f41d8ef299a2740afe2907e3dbc23d0068ded5debe3b58e4191b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:23:59Z","title_canon_sha256":"ffa95e75684d37f7f83ae8cd235925d2e0b981bbf58222c51269bc67647b671a"},"schema_version":"1.0","source":{"id":"2607.20443","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20443","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20443v1","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20443","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"pith_short_12","alias_value":"XVEZYALXZUXK","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"pith_short_16","alias_value":"XVEZYALXZUXKZDBI","created_at":"2026-07-24T00:23:15Z"},{"alias_kind":"pith_short_8","alias_value":"XVEZYALX","created_at":"2026-07-24T00:23:15Z"}],"graph_snapshots":[{"event_id":"sha256:98e97858d38072cecd3dd90958a7e5609965e3d3ab411438e67f358d1e370a21","target":"graph","created_at":"2026-07-24T00:23:15Z","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/2607.20443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We release GLAN-QnA-KR, a 303,581-row openly redistributable Korean instruction-QA corpus produced via the seedless taxonomy-driven GLAN synthesis pipeline with Microsoft's Phi-3.5-MoE-instruct as the producer model (generation: 2024-12; release: 2024-12; licence: OpenRAIL). The corpus spans a flat taxonomy of 1,084 English-labelled disciplines paired with Korean question/answer text, a 100-900 difficulty scale, and a median of 313 question characters and 1,098 answer characters per record. Two properties are atypical for synthetic instruction data at this scale: (i) exact duplicate questions ","authors_text":"Daekeun Kim","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:23:59Z","title":"GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20443","kind":"arxiv","version":1},"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":"sha256:0d908ff13cd548ddda16e8c8131ba47637b7c87cd38173c1bdd6a5450092ba7b","target":"record","created_at":"2026-07-24T00:23:15Z","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":"e5e4929000b0f41d8ef299a2740afe2907e3dbc23d0068ded5debe3b58e4191b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:23:59Z","title_canon_sha256":"ffa95e75684d37f7f83ae8cd235925d2e0b981bbf58222c51269bc67647b671a"},"schema_version":"1.0","source":{"id":"2607.20443","kind":"arxiv","version":1}},"canonical_sha256":"bd499c0177cd2eac8c287427f165e12c4e167994e38c75fa2e810f2315beb5f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd499c0177cd2eac8c287427f165e12c4e167994e38c75fa2e810f2315beb5f0","first_computed_at":"2026-07-24T00:23:15.700876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:15.700876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pl3UeyNSr3rDmPAG9tjEb4lEaGK8j5WPiAPwvgyAbmzW7BDuHnmvCj+u0ieZ5bpMVhVQZLn3/bBKJOVIobugDw==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:15.701835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20443","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d908ff13cd548ddda16e8c8131ba47637b7c87cd38173c1bdd6a5450092ba7b","sha256:98e97858d38072cecd3dd90958a7e5609965e3d3ab411438e67f358d1e370a21"],"state_sha256":"a650ca2acb2f9770f87665463280aec312404ca88d9e0280ad0536882b3ec5c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8J7N+cVAXZCQdpXu1ViOJSuxovfUyD8rasCY35Ook4Ok/bKNL4TZSjgf9pIi/iLw1j0YcnXRsJZcSSywQzmeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:50:28.144201Z","bundle_sha256":"9ced78b4a181b99ebd2766160167ae58109696a67bb3131ec3f5efceecf2448a"}}