{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KVRLZ3M6UBYNVTXBMXIATKVXY6","short_pith_number":"pith:KVRLZ3M6","schema_version":"1.0","canonical_sha256":"5562bced9ea070dacee165d009aab7c7b53cd3af15c9591ad35c6b27ea6db9b3","source":{"kind":"arxiv","id":"2605.30963","version":1},"attestation_state":"computed","paper":{"title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Bowen Zhou, Changze Lv, Dahua Lin, Dongyu Xue, Hao Wang, Hao Zhou, Jiangtao Feng, Jixiang Yu, Ka-Chun Wong, Keyue Qiu, Lei Bai, Lihao Wang, Lijun Wu, Wei-Ying Ma, Xiaoqing Zheng, Xinbo Zhang, Ya-Qin Zhang, Yawen Ouyang, Yixin Wu, Yuxuan Song, Zhiqiang Gao, Zihan Zhou","submitted_at":"2026-05-29T07:58:08Z","abstract_excerpt":"We present AMix-2, a protein-text foundation model that establishes protein as a native modality in large language models (LLMs), unifying protein understanding and sequence design within a single foundation model. AMix-2 is built upon two key ideas: (1) a unified protein-text formulation that embeds natural language and protein sequence in a shared token space, enabling one model to perform biological reasoning and conditional design instead of separate downstream task-specialized models; and (2) a block-wise diffusion language modeling backbone that combines causal generation across blocks w"},"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":"2605.30963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.BM","submitted_at":"2026-05-29T07:58:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a33ea7644466a8315c8e8f077f34899242adbde850d654daeed9fc5fd318bd0","abstract_canon_sha256":"9ca26bdfc794a4be0fe107e0012f4dd7384f2a9890ff27997f82d0f35d6ba2d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:27.727098Z","signature_b64":"MHn9eshWv6CqFfgWz/Dky7zVNoJ8uoXClQv9BzL7tI2MNbQGGIwimY8jR7rIiu48YParLLvQXXMae9k3frj+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5562bced9ea070dacee165d009aab7c7b53cd3af15c9591ad35c6b27ea6db9b3","last_reissued_at":"2026-06-01T01:03:27.726603Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:27.726603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Bowen Zhou, Changze Lv, Dahua Lin, Dongyu Xue, Hao Wang, Hao Zhou, Jiangtao Feng, Jixiang Yu, Ka-Chun Wong, Keyue Qiu, Lei Bai, Lihao Wang, Lijun Wu, Wei-Ying Ma, Xiaoqing Zheng, Xinbo Zhang, Ya-Qin Zhang, Yawen Ouyang, Yixin Wu, Yuxuan Song, Zhiqiang Gao, Zihan Zhou","submitted_at":"2026-05-29T07:58:08Z","abstract_excerpt":"We present AMix-2, a protein-text foundation model that establishes protein as a native modality in large language models (LLMs), unifying protein understanding and sequence design within a single foundation model. AMix-2 is built upon two key ideas: (1) a unified protein-text formulation that embeds natural language and protein sequence in a shared token space, enabling one model to perform biological reasoning and conditional design instead of separate downstream task-specialized models; and (2) a block-wise diffusion language modeling backbone that combines causal generation across blocks w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30963","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/2605.30963/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":"2605.30963","created_at":"2026-06-01T01:03:27.726680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30963v1","created_at":"2026-06-01T01:03:27.726680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30963","created_at":"2026-06-01T01:03:27.726680+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVRLZ3M6UBYN","created_at":"2026-06-01T01:03:27.726680+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVRLZ3M6UBYNVTXB","created_at":"2026-06-01T01:03:27.726680+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVRLZ3M6","created_at":"2026-06-01T01:03:27.726680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6","json":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6.json","graph_json":"https://pith.science/api/pith-number/KVRLZ3M6UBYNVTXBMXIATKVXY6/graph.json","events_json":"https://pith.science/api/pith-number/KVRLZ3M6UBYNVTXBMXIATKVXY6/events.json","paper":"https://pith.science/paper/KVRLZ3M6"},"agent_actions":{"view_html":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6","download_json":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6.json","view_paper":"https://pith.science/paper/KVRLZ3M6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30963&json=true","fetch_graph":"https://pith.science/api/pith-number/KVRLZ3M6UBYNVTXBMXIATKVXY6/graph.json","fetch_events":"https://pith.science/api/pith-number/KVRLZ3M6UBYNVTXBMXIATKVXY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6/action/storage_attestation","attest_author":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6/action/author_attestation","sign_citation":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6/action/citation_signature","submit_replication":"https://pith.science/pith/KVRLZ3M6UBYNVTXBMXIATKVXY6/action/replication_record"}},"created_at":"2026-06-01T01:03:27.726680+00:00","updated_at":"2026-06-01T01:03:27.726680+00:00"}