{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X4UIW47EFXBWYD5CAOB6GL2I5T","short_pith_number":"pith:X4UIW47E","schema_version":"1.0","canonical_sha256":"bf288b73e42dc36c0fa20383e32f48eceecd1c7b8053f1528cadc043ab8a33e6","source":{"kind":"arxiv","id":"2501.13921","version":3},"attestation_state":"computed","paper":{"title":"The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chia-Sheng Liu, Da-shan Shiu, MediaTek Research: Chan-Jan Hsu, Meng-Hsi Chen, Muxi Chen, Po-chun Hsu, Yi-Chang Chen","submitted_at":"2025-01-23T18:59:02Z","abstract_excerpt":"Llama-Breeze2 (hereinafter referred to as Breeze2) is a suite of advanced multi-modal language models, available in 3B and 8B parameter configurations, specifically designed to enhance Traditional Chinese language representation. Building upon the Llama 3.2 model family, we continue the pre-training of Breeze2 on an extensive corpus to enhance the linguistic and cultural heritage of Traditional Chinese. In addition to language modeling capabilities, we significantly augment the models with function calling and vision understanding capabilities. At the time of this publication, as far as we are"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.13921","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T18:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"b17d58bbb375e022b98d3b7ddafdfcaf5ff223917fb9ce529b7337f2a3e4fbe4","abstract_canon_sha256":"788c510158ade3a8b0891c53c967b4809ba7e18f5bb3e0a8059e5bc979694ed7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:52.105756Z","signature_b64":"rKPY1S916IdCBnyuTZc7X/2CMiFn40qQnb6EDmEEnWcHorhGbzuwktb/9nQXpjThbzjAK8yNBA+kzXe/NimHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf288b73e42dc36c0fa20383e32f48eceecd1c7b8053f1528cadc043ab8a33e6","last_reissued_at":"2026-07-05T10:12:52.105177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:52.105177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chia-Sheng Liu, Da-shan Shiu, MediaTek Research: Chan-Jan Hsu, Meng-Hsi Chen, Muxi Chen, Po-chun Hsu, Yi-Chang Chen","submitted_at":"2025-01-23T18:59:02Z","abstract_excerpt":"Llama-Breeze2 (hereinafter referred to as Breeze2) is a suite of advanced multi-modal language models, available in 3B and 8B parameter configurations, specifically designed to enhance Traditional Chinese language representation. Building upon the Llama 3.2 model family, we continue the pre-training of Breeze2 on an extensive corpus to enhance the linguistic and cultural heritage of Traditional Chinese. In addition to language modeling capabilities, we significantly augment the models with function calling and vision understanding capabilities. At the time of this publication, as far as we are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13921","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/2501.13921/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.13921","created_at":"2026-07-05T10:12:52.105235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13921v3","created_at":"2026-07-05T10:12:52.105235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13921","created_at":"2026-07-05T10:12:52.105235+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4UIW47EFXBW","created_at":"2026-07-05T10:12:52.105235+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4UIW47EFXBWYD5C","created_at":"2026-07-05T10:12:52.105235+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4UIW47E","created_at":"2026-07-05T10:12:52.105235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09603","citing_title":"Automated IEP Generation from Traditional Chinese Parent-Teacher Interviews via Corpus-Grounded Feature Diffusion","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10065","citing_title":"ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T","json":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T.json","graph_json":"https://pith.science/api/pith-number/X4UIW47EFXBWYD5CAOB6GL2I5T/graph.json","events_json":"https://pith.science/api/pith-number/X4UIW47EFXBWYD5CAOB6GL2I5T/events.json","paper":"https://pith.science/paper/X4UIW47E"},"agent_actions":{"view_html":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T","download_json":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T.json","view_paper":"https://pith.science/paper/X4UIW47E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13921&json=true","fetch_graph":"https://pith.science/api/pith-number/X4UIW47EFXBWYD5CAOB6GL2I5T/graph.json","fetch_events":"https://pith.science/api/pith-number/X4UIW47EFXBWYD5CAOB6GL2I5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T/action/storage_attestation","attest_author":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T/action/author_attestation","sign_citation":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T/action/citation_signature","submit_replication":"https://pith.science/pith/X4UIW47EFXBWYD5CAOB6GL2I5T/action/replication_record"}},"created_at":"2026-07-05T10:12:52.105235+00:00","updated_at":"2026-07-05T10:12:52.105235+00:00"}