{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5S43UXYZLJ66JGITOKT5EQO5N4","short_pith_number":"pith:5S43UXYZ","canonical_record":{"source":{"id":"2507.10920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T02:26:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a9025704c27c51d03f2c741e8ebf88d291a35832e2b8bed23132c6f46064498","abstract_canon_sha256":"054e16a50f2a069ae3efc584ad5bca3e28628e975ec9ef0dccc697848f28c7b0"},"schema_version":"1.0"},"canonical_sha256":"ecb9ba5f195a7de4991372a7d241dd6f32f7ef5b0d180a8dc276a0b3df3bea3a","source":{"kind":"arxiv","id":"2507.10920","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10920","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10920v1","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10920","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"pith_short_12","alias_value":"5S43UXYZLJ66","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"pith_short_16","alias_value":"5S43UXYZLJ66JGIT","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"pith_short_8","alias_value":"5S43UXYZ","created_at":"2026-07-05T11:37:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5S43UXYZLJ66JGITOKT5EQO5N4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T02:26:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a9025704c27c51d03f2c741e8ebf88d291a35832e2b8bed23132c6f46064498","abstract_canon_sha256":"054e16a50f2a069ae3efc584ad5bca3e28628e975ec9ef0dccc697848f28c7b0"},"schema_version":"1.0"},"canonical_sha256":"ecb9ba5f195a7de4991372a7d241dd6f32f7ef5b0d180a8dc276a0b3df3bea3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:28.481183Z","signature_b64":"SkjmBNZtIcV56GF7yMGk9IDWZ5WuvpYo4KgyTvElWfEHPPl0y9FcWPnKx91yYWWMJGnTYvVnhmj8mQhZ8uufBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecb9ba5f195a7de4991372a7d241dd6f32f7ef5b0d180a8dc276a0b3df3bea3a","last_reissued_at":"2026-07-05T11:37:28.480572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:28.480572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10920","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":"2026-07-05T11:37:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dMedE13U/b/1va8hzVGvZNa8oQ5T2xrJPivrV9rr2e6CFUmNDSl+YeAkLx47YjPIs1eiS71LZagpmx1kUeVmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:20:08.190062Z"},"content_sha256":"c83b53bcc9e65605150abc9331170a165c0f7f948bbd0b5e87cb87301faeff26","schema_version":"1.0","event_id":"sha256:c83b53bcc9e65605150abc9331170a165c0f7f948bbd0b5e87cb87301faeff26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5S43UXYZLJ66JGITOKT5EQO5N4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HanjaBridge: Resolving Semantic Ambiguity in Korean LLMs via Hanja-Augmented Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Seungho Choi","submitted_at":"2025-07-15T02:26:47Z","abstract_excerpt":"Large language models (LLMs) often show poor performance in low-resource languages like Korean, partly due to unique linguistic challenges such as homophonous Sino-Korean words that are indistinguishable in Hangul script. To address this semantic ambiguity, we propose HanjaBridge, a novel meaning-injection technique integrated into a continual pre-training (CPT) framework. Instead of deterministically mapping a word to a single Hanja (Chinese character), HanjaBridge presents the model with all possible Hanja candidates for a given homograph, encouraging the model to learn contextual disambigua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10920","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/2507.10920/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":"2026-07-05T11:37:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXDG7ZElq9hDTwFOl895EuzfqVOchLwqmCmVaZgW3xbe+ajr5evSueLOsUu9MasjSSEpn2OWo6YMoWAAlRVOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:20:08.190949Z"},"content_sha256":"16e6db2fd7801b391415153327495edd9f5ae04c6eacdd4af231d8dcfc352430","schema_version":"1.0","event_id":"sha256:16e6db2fd7801b391415153327495edd9f5ae04c6eacdd4af231d8dcfc352430"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5S43UXYZLJ66JGITOKT5EQO5N4/bundle.json","state_url":"https://pith.science/pith/5S43UXYZLJ66JGITOKT5EQO5N4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5S43UXYZLJ66JGITOKT5EQO5N4/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":"2026-08-11T02:20:08Z","links":{"resolver":"https://pith.science/pith/5S43UXYZLJ66JGITOKT5EQO5N4","bundle":"https://pith.science/pith/5S43UXYZLJ66JGITOKT5EQO5N4/bundle.json","state":"https://pith.science/pith/5S43UXYZLJ66JGITOKT5EQO5N4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5S43UXYZLJ66JGITOKT5EQO5N4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5S43UXYZLJ66JGITOKT5EQO5N4","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":"054e16a50f2a069ae3efc584ad5bca3e28628e975ec9ef0dccc697848f28c7b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T02:26:47Z","title_canon_sha256":"0a9025704c27c51d03f2c741e8ebf88d291a35832e2b8bed23132c6f46064498"},"schema_version":"1.0","source":{"id":"2507.10920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10920","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10920v1","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10920","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"pith_short_12","alias_value":"5S43UXYZLJ66","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"pith_short_16","alias_value":"5S43UXYZLJ66JGIT","created_at":"2026-07-05T11:37:28Z"},{"alias_kind":"pith_short_8","alias_value":"5S43UXYZ","created_at":"2026-07-05T11:37:28Z"}],"graph_snapshots":[{"event_id":"sha256:16e6db2fd7801b391415153327495edd9f5ae04c6eacdd4af231d8dcfc352430","target":"graph","created_at":"2026-07-05T11:37:28Z","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/2507.10920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often show poor performance in low-resource languages like Korean, partly due to unique linguistic challenges such as homophonous Sino-Korean words that are indistinguishable in Hangul script. To address this semantic ambiguity, we propose HanjaBridge, a novel meaning-injection technique integrated into a continual pre-training (CPT) framework. Instead of deterministically mapping a word to a single Hanja (Chinese character), HanjaBridge presents the model with all possible Hanja candidates for a given homograph, encouraging the model to learn contextual disambigua","authors_text":"Seungho Choi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T02:26:47Z","title":"HanjaBridge: Resolving Semantic Ambiguity in Korean LLMs via Hanja-Augmented Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10920","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:c83b53bcc9e65605150abc9331170a165c0f7f948bbd0b5e87cb87301faeff26","target":"record","created_at":"2026-07-05T11:37:28Z","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":"054e16a50f2a069ae3efc584ad5bca3e28628e975ec9ef0dccc697848f28c7b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-15T02:26:47Z","title_canon_sha256":"0a9025704c27c51d03f2c741e8ebf88d291a35832e2b8bed23132c6f46064498"},"schema_version":"1.0","source":{"id":"2507.10920","kind":"arxiv","version":1}},"canonical_sha256":"ecb9ba5f195a7de4991372a7d241dd6f32f7ef5b0d180a8dc276a0b3df3bea3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecb9ba5f195a7de4991372a7d241dd6f32f7ef5b0d180a8dc276a0b3df3bea3a","first_computed_at":"2026-07-05T11:37:28.480572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:28.480572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SkjmBNZtIcV56GF7yMGk9IDWZ5WuvpYo4KgyTvElWfEHPPl0y9FcWPnKx91yYWWMJGnTYvVnhmj8mQhZ8uufBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:28.481183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c83b53bcc9e65605150abc9331170a165c0f7f948bbd0b5e87cb87301faeff26","sha256:16e6db2fd7801b391415153327495edd9f5ae04c6eacdd4af231d8dcfc352430"],"state_sha256":"7b1a474d588edfe5730fcc92c0a4b54678093cd802c650c7760f2be357fdccbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEukYKtxaGGCcxCESTsQzOorLM+xayTxW1Q7Ja3084ryv7adBpLSlopiblRLTSeXFDSLpyzvuiT0vlDgjSchBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:20:08.288844Z","bundle_sha256":"36e9519ad44afda6278bf8c480475cc3a1ff4976b3bf24d554231fe90acf3f68"}}