{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SQ4L2XPCHRYHX42J7MXAMQFSGP","short_pith_number":"pith:SQ4L2XPC","schema_version":"1.0","canonical_sha256":"9438bd5de23c707bf349fb2e0640b233c8827354bc619008829b01073592dd26","source":{"kind":"arxiv","id":"2606.22138","version":1},"attestation_state":"computed","paper":{"title":"BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Chang-Yu Hsieh, Chengping Li, Conghui He, Han Guo, Liang He, Lijun Wu, Qizhi Pei, Rui Yan, Wei Li, Yi Duan, Yiyang Zhao, Zhimeng Zhou","submitted_at":"2026-06-20T16:38:59Z","abstract_excerpt":"We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules and proteins within a single decoder-only architecture. Existing biological foundation models pursue native multimodality and broad entity coverage separately: those that fuse multiple modalities under a shared objective remain confined to a single entity type, while those spanning multiple entity types either omit explicit structural modeling or rely on adapter-based designs in which the model cannot natively generate the very modalities it can re"},"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":"2606.22138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T16:38:59Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.BM"],"title_canon_sha256":"e0322ea1a662db28c11238fc18d415f88c3be12e5dff54115a8c4b2b7748337e","abstract_canon_sha256":"0f5d420916a9f4e8737b44f1263b68392a8f853dacb7ff73141e20df23264153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:29.273009Z","signature_b64":"Wv6vQBrOvl3izbmqQOXOUvWXc5A9sNqYDHXm7T1i495No6q0o5R1J+13mAQLjjeIe5X6qnWtSFP6Y24IlKMCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9438bd5de23c707bf349fb2e0640b233c8827354bc619008829b01073592dd26","last_reissued_at":"2026-06-23T02:13:29.272593Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:29.272593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.BM"],"primary_cat":"cs.CL","authors_text":"Chang-Yu Hsieh, Chengping Li, Conghui He, Han Guo, Liang He, Lijun Wu, Qizhi Pei, Rui Yan, Wei Li, Yi Duan, Yiyang Zhao, Zhimeng Zhou","submitted_at":"2026-06-20T16:38:59Z","abstract_excerpt":"We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules and proteins within a single decoder-only architecture. Existing biological foundation models pursue native multimodality and broad entity coverage separately: those that fuse multiple modalities under a shared objective remain confined to a single entity type, while those spanning multiple entity types either omit explicit structural modeling or rely on adapter-based designs in which the model cannot natively generate the very modalities it can re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22138","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/2606.22138/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":"2606.22138","created_at":"2026-06-23T02:13:29.272647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22138v1","created_at":"2026-06-23T02:13:29.272647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22138","created_at":"2026-06-23T02:13:29.272647+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQ4L2XPCHRYH","created_at":"2026-06-23T02:13:29.272647+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQ4L2XPCHRYHX42J","created_at":"2026-06-23T02:13:29.272647+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQ4L2XPC","created_at":"2026-06-23T02:13:29.272647+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/SQ4L2XPCHRYHX42J7MXAMQFSGP","json":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP.json","graph_json":"https://pith.science/api/pith-number/SQ4L2XPCHRYHX42J7MXAMQFSGP/graph.json","events_json":"https://pith.science/api/pith-number/SQ4L2XPCHRYHX42J7MXAMQFSGP/events.json","paper":"https://pith.science/paper/SQ4L2XPC"},"agent_actions":{"view_html":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP","download_json":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP.json","view_paper":"https://pith.science/paper/SQ4L2XPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22138&json=true","fetch_graph":"https://pith.science/api/pith-number/SQ4L2XPCHRYHX42J7MXAMQFSGP/graph.json","fetch_events":"https://pith.science/api/pith-number/SQ4L2XPCHRYHX42J7MXAMQFSGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP/action/storage_attestation","attest_author":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP/action/author_attestation","sign_citation":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP/action/citation_signature","submit_replication":"https://pith.science/pith/SQ4L2XPCHRYHX42J7MXAMQFSGP/action/replication_record"}},"created_at":"2026-06-23T02:13:29.272647+00:00","updated_at":"2026-06-23T02:13:29.272647+00:00"}