{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6HHZAYCJTH2HAXUHLX4QD47VFE","short_pith_number":"pith:6HHZAYCJ","canonical_record":{"source":{"id":"2311.17487","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T09:48:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e23c7f876e78e532ffb4ea9d7327fb0272acc69922aa89ad555905212cf9cc0a","abstract_canon_sha256":"870ffc24e9ef5d905d11f04641868ba7444d95493b1f4a937c0ef79083a8b699"},"schema_version":"1.0"},"canonical_sha256":"f1cf90604999f4705e875df901f3f5290cbeaa1a0083406d9d8192a3c8cf94a8","source":{"kind":"arxiv","id":"2311.17487","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17487","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17487v1","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17487","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"6HHZAYCJTH2H","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"6HHZAYCJTH2HAXUH","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"6HHZAYCJ","created_at":"2026-07-05T07:18:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6HHZAYCJTH2HAXUHLX4QD47VFE","target":"record","payload":{"canonical_record":{"source":{"id":"2311.17487","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T09:48:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e23c7f876e78e532ffb4ea9d7327fb0272acc69922aa89ad555905212cf9cc0a","abstract_canon_sha256":"870ffc24e9ef5d905d11f04641868ba7444d95493b1f4a937c0ef79083a8b699"},"schema_version":"1.0"},"canonical_sha256":"f1cf90604999f4705e875df901f3f5290cbeaa1a0083406d9d8192a3c8cf94a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:14.431164Z","signature_b64":"/cfaktjB3HOvDtRihGl86gqwJRRki2hPxaqpOEOQNTAQjdXvAaRYVQhqfx1tYcMjVyv8htjPVD17Qv/uCNRSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1cf90604999f4705e875df901f3f5290cbeaa1a0083406d9d8192a3c8cf94a8","last_reissued_at":"2026-07-05T07:18:14.430618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:14.430618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.17487","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":"2026-07-05T07:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+71BUque1aP8/1w+iWunotCdCYx+2HwufojJHxclHnBbtVfbJboAwE2ReDhpN9jN5V8XdlwaMnmtX9917xdTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:34:27.826578Z"},"content_sha256":"c1e3e320bea17cbccd831f40350c49b45d9a9536af9381cab77547cb52a251b8","schema_version":"1.0","event_id":"sha256:c1e3e320bea17cbccd831f40350c49b45d9a9536af9381cab77547cb52a251b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6HHZAYCJTH2HAXUHLX4QD47VFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yen-Ting Lin, Yun-Nung Chen","submitted_at":"2023-11-29T09:48:34Z","abstract_excerpt":"In the realm of language models, the nuanced linguistic and cultural intricacies of Traditional Chinese, as spoken in Taiwan, have been largely overlooked. This paper introduces Taiwan LLM, a pioneering Large Language Model that specifically caters to the Traditional Chinese language, with a focus on the variant used in Taiwan. Leveraging a comprehensive pretraining corpus and instruction-finetuning datasets, we have developed a model that not only understands the complexities of Traditional Chinese but also embodies the cultural context of Taiwan. Taiwan LLM represents the first of its kind, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17487","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/2311.17487/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":"2026-07-05T07:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nb+zrlqTkclINAqOOTESm3qYSZNcRYF/sOREJtvEohxZDWYH6c/WkstffvUxjmFAHcy8jiOrixXa+JATYxpdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:34:27.826965Z"},"content_sha256":"374b9262cc94669289ef377cca7f4b4cd813dbbb516a7a7eb557d9847a612a0a","schema_version":"1.0","event_id":"sha256:374b9262cc94669289ef377cca7f4b4cd813dbbb516a7a7eb557d9847a612a0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HHZAYCJTH2HAXUHLX4QD47VFE/bundle.json","state_url":"https://pith.science/pith/6HHZAYCJTH2HAXUHLX4QD47VFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HHZAYCJTH2HAXUHLX4QD47VFE/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":"2026-07-05T13:34:27Z","links":{"resolver":"https://pith.science/pith/6HHZAYCJTH2HAXUHLX4QD47VFE","bundle":"https://pith.science/pith/6HHZAYCJTH2HAXUHLX4QD47VFE/bundle.json","state":"https://pith.science/pith/6HHZAYCJTH2HAXUHLX4QD47VFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HHZAYCJTH2HAXUHLX4QD47VFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6HHZAYCJTH2HAXUHLX4QD47VFE","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":"870ffc24e9ef5d905d11f04641868ba7444d95493b1f4a937c0ef79083a8b699","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T09:48:34Z","title_canon_sha256":"e23c7f876e78e532ffb4ea9d7327fb0272acc69922aa89ad555905212cf9cc0a"},"schema_version":"1.0","source":{"id":"2311.17487","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17487","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17487v1","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17487","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"6HHZAYCJTH2H","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"6HHZAYCJTH2HAXUH","created_at":"2026-07-05T07:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"6HHZAYCJ","created_at":"2026-07-05T07:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:374b9262cc94669289ef377cca7f4b4cd813dbbb516a7a7eb557d9847a612a0a","target":"graph","created_at":"2026-07-05T07:18:14Z","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/2311.17487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the realm of language models, the nuanced linguistic and cultural intricacies of Traditional Chinese, as spoken in Taiwan, have been largely overlooked. This paper introduces Taiwan LLM, a pioneering Large Language Model that specifically caters to the Traditional Chinese language, with a focus on the variant used in Taiwan. Leveraging a comprehensive pretraining corpus and instruction-finetuning datasets, we have developed a model that not only understands the complexities of Traditional Chinese but also embodies the cultural context of Taiwan. Taiwan LLM represents the first of its kind, ","authors_text":"Yen-Ting Lin, Yun-Nung Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T09:48:34Z","title":"Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17487","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:c1e3e320bea17cbccd831f40350c49b45d9a9536af9381cab77547cb52a251b8","target":"record","created_at":"2026-07-05T07:18:14Z","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":"870ffc24e9ef5d905d11f04641868ba7444d95493b1f4a937c0ef79083a8b699","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T09:48:34Z","title_canon_sha256":"e23c7f876e78e532ffb4ea9d7327fb0272acc69922aa89ad555905212cf9cc0a"},"schema_version":"1.0","source":{"id":"2311.17487","kind":"arxiv","version":1}},"canonical_sha256":"f1cf90604999f4705e875df901f3f5290cbeaa1a0083406d9d8192a3c8cf94a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1cf90604999f4705e875df901f3f5290cbeaa1a0083406d9d8192a3c8cf94a8","first_computed_at":"2026-07-05T07:18:14.430618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:14.430618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/cfaktjB3HOvDtRihGl86gqwJRRki2hPxaqpOEOQNTAQjdXvAaRYVQhqfx1tYcMjVyv8htjPVD17Qv/uCNRSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:14.431164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17487","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1e3e320bea17cbccd831f40350c49b45d9a9536af9381cab77547cb52a251b8","sha256:374b9262cc94669289ef377cca7f4b4cd813dbbb516a7a7eb557d9847a612a0a"],"state_sha256":"cabab71d5533b0c0a85a0f389da1ba44be0e062b96312a3388dec55db0dd31a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G6UXi4vb9ntCwzhUyUTgAOcZwX6kR/3DFtbQdiijJmJ3bfmrumGriN1anJ6LIUQfq/mvUW5dbjrBFQj/JDkTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:34:27.829500Z","bundle_sha256":"3d6000bbffd337871a9a04957d2e872098c04bf36a60c5b7f83d4293c16e7b3a"}}