{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CI3SDZHPPKDWVKCNT5XHCRVE3P","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":"37e2bb89517226e13e12210df877125c022781f17f5ea4846979bc468d44d1cb","cross_cats_sorted":["cs.CL","cs.DC","q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-16T19:04:45Z","title_canon_sha256":"415cabf268ab056835ea4ef2305eda3dd36f3c0ef2f6f08d628387757e07252e"},"schema_version":"1.0","source":{"id":"2301.06568","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.06568","created_at":"2026-07-05T05:33:33Z"},{"alias_kind":"arxiv_version","alias_value":"2301.06568v1","created_at":"2026-07-05T05:33:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.06568","created_at":"2026-07-05T05:33:33Z"},{"alias_kind":"pith_short_12","alias_value":"CI3SDZHPPKDW","created_at":"2026-07-05T05:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"CI3SDZHPPKDWVKCN","created_at":"2026-07-05T05:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"CI3SDZHP","created_at":"2026-07-05T05:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:efbaff87bbb650f72a405ec15e312946a3123b84f01047b1a856200f2e9625c0","target":"graph","created_at":"2026-07-05T05:33:33Z","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/2301.06568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ahmed Elnaggar, Burkhard Rost, Charlotte Rochereau, Hazem Essam, Mohamed Elkerdawy, Wafaa Salah-Eldin, Walid Moustafa","cross_cats":["cs.CL","cs.DC","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-16T19:04:45Z","title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.06568","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:f0bc7c407d2341494ae9ce81c68f6647047873961a91f4e8cb62f3fae9f81c5b","target":"record","created_at":"2026-07-05T05:33:33Z","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":"37e2bb89517226e13e12210df877125c022781f17f5ea4846979bc468d44d1cb","cross_cats_sorted":["cs.CL","cs.DC","q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-16T19:04:45Z","title_canon_sha256":"415cabf268ab056835ea4ef2305eda3dd36f3c0ef2f6f08d628387757e07252e"},"schema_version":"1.0","source":{"id":"2301.06568","kind":"arxiv","version":1}},"canonical_sha256":"123721e4ef7a876aa84d9f6e7146a4dbe6b9a05fe16789730c514a5cdf43f01d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"123721e4ef7a876aa84d9f6e7146a4dbe6b9a05fe16789730c514a5cdf43f01d","first_computed_at":"2026-07-05T05:33:33.265516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:33.265516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RHfcvwveKtkWYdCKimc6uROFhpCMC2IfI1djq7mwbYdOanVi91PzWnpFxnp/mRKN+BlhD05v2MXXPAdF5t+oAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:33.265904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.06568","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0bc7c407d2341494ae9ce81c68f6647047873961a91f4e8cb62f3fae9f81c5b","sha256:efbaff87bbb650f72a405ec15e312946a3123b84f01047b1a856200f2e9625c0"],"state_sha256":"40953c5e3a081731c6bff255c36315802c59c326bb4de6e7f4c45f97c32866aa"}