{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CI3SDZHPPKDWVKCNT5XHCRVE3P","short_pith_number":"pith:CI3SDZHP","schema_version":"1.0","canonical_sha256":"123721e4ef7a876aa84d9f6e7146a4dbe6b9a05fe16789730c514a5cdf43f01d","source":{"kind":"arxiv","id":"2301.06568","version":1},"attestation_state":"computed","paper":{"title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.DC","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ahmed Elnaggar, Burkhard Rost, Charlotte Rochereau, Hazem Essam, Mohamed Elkerdawy, Wafaa Salah-Eldin, Walid Moustafa","submitted_at":"2023-01-16T19:04:45Z","abstract_excerpt":"As opposed to scaling-up protein language models (PLMs), we seek improving performance via protein-specific optimization. Although the proportionality between the language model size and the richness of its learned representations is validated, we prioritize accessibility and pursue a path of data-efficient, cost-reduced, and knowledge-guided optimization. Through over twenty experiments ranging from masking, architecture, and pre-training data, we derive insights from protein-specific experimentation into building a model that interprets the language of life, optimally. We present Ankh, the f"},"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":"2301.06568","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-16T19:04:45Z","cross_cats_sorted":["cs.CL","cs.DC","q-bio.QM"],"title_canon_sha256":"415cabf268ab056835ea4ef2305eda3dd36f3c0ef2f6f08d628387757e07252e","abstract_canon_sha256":"37e2bb89517226e13e12210df877125c022781f17f5ea4846979bc468d44d1cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:33.265904Z","signature_b64":"RHfcvwveKtkWYdCKimc6uROFhpCMC2IfI1djq7mwbYdOanVi91PzWnpFxnp/mRKN+BlhD05v2MXXPAdF5t+oAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"123721e4ef7a876aa84d9f6e7146a4dbe6b9a05fe16789730c514a5cdf43f01d","last_reissued_at":"2026-07-05T05:33:33.265516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:33.265516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.DC","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ahmed Elnaggar, Burkhard Rost, Charlotte Rochereau, Hazem Essam, Mohamed Elkerdawy, Wafaa Salah-Eldin, Walid Moustafa","submitted_at":"2023-01-16T19:04:45Z","abstract_excerpt":"As opposed to scaling-up protein language models (PLMs), we seek improving performance via protein-specific optimization. Although the proportionality between the language model size and the richness of its learned representations is validated, we prioritize accessibility and pursue a path of data-efficient, cost-reduced, and knowledge-guided optimization. Through over twenty experiments ranging from masking, architecture, and pre-training data, we derive insights from protein-specific experimentation into building a model that interprets the language of life, optimally. We present Ankh, the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06568","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/2301.06568/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":"2301.06568","created_at":"2026-07-05T05:33:33.265577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.06568v1","created_at":"2026-07-05T05:33:33.265577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06568","created_at":"2026-07-05T05:33:33.265577+00:00"},{"alias_kind":"pith_short_12","alias_value":"CI3SDZHPPKDW","created_at":"2026-07-05T05:33:33.265577+00:00"},{"alias_kind":"pith_short_16","alias_value":"CI3SDZHPPKDWVKCN","created_at":"2026-07-05T05:33:33.265577+00:00"},{"alias_kind":"pith_short_8","alias_value":"CI3SDZHP","created_at":"2026-07-05T05:33:33.265577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02386","citing_title":"AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2510.11752","citing_title":"Fast and Interpretable Protein Substructure Alignment via Optimal Transport","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12845","citing_title":"Multimodal Protein Language Models for Enzyme Kinetic Parameters: From Substrate Recognition to Conformational Adaptation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P","json":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P.json","graph_json":"https://pith.science/api/pith-number/CI3SDZHPPKDWVKCNT5XHCRVE3P/graph.json","events_json":"https://pith.science/api/pith-number/CI3SDZHPPKDWVKCNT5XHCRVE3P/events.json","paper":"https://pith.science/paper/CI3SDZHP"},"agent_actions":{"view_html":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P","download_json":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P.json","view_paper":"https://pith.science/paper/CI3SDZHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.06568&json=true","fetch_graph":"https://pith.science/api/pith-number/CI3SDZHPPKDWVKCNT5XHCRVE3P/graph.json","fetch_events":"https://pith.science/api/pith-number/CI3SDZHPPKDWVKCNT5XHCRVE3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P/action/storage_attestation","attest_author":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P/action/author_attestation","sign_citation":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P/action/citation_signature","submit_replication":"https://pith.science/pith/CI3SDZHPPKDWVKCNT5XHCRVE3P/action/replication_record"}},"created_at":"2026-07-05T05:33:33.265577+00:00","updated_at":"2026-07-05T05:33:33.265577+00:00"}