{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KMZPJKVRWPNVXVMEBLUZ2QG7SL","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":"4332d0f43758313581bb04962d286593113ec78c1da43478eda56cc82ce045d3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T09:24:58Z","title_canon_sha256":"f3ef022410769d6bb38c0f4e99d148cdc28f5de1ceff03fbbebaa44bd4aa9e2a"},"schema_version":"1.0","source":{"id":"2501.18223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18223","created_at":"2026-07-05T10:07:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18223v1","created_at":"2026-07-05T10:07:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18223","created_at":"2026-07-05T10:07:31Z"},{"alias_kind":"pith_short_12","alias_value":"KMZPJKVRWPNV","created_at":"2026-07-05T10:07:31Z"},{"alias_kind":"pith_short_16","alias_value":"KMZPJKVRWPNVXVME","created_at":"2026-07-05T10:07:31Z"},{"alias_kind":"pith_short_8","alias_value":"KMZPJKVR","created_at":"2026-07-05T10:07:31Z"}],"graph_snapshots":[{"event_id":"sha256:5bea5599a45ca8c1b43b64bcac482eaf4972bc5a4a5d3e105dd49860dddd5190","target":"graph","created_at":"2026-07-05T10:07:31Z","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/2501.18223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we expand upon the FLIP benchmark-designed for evaluating protein fitness prediction models in small, specialized prediction tasks-by assessing the performance of state-of-the-art large protein language models, including ESM-2 and SaProt on the FLIP dataset. Unlike larger, more diverse benchmarks such as ProteinGym, which cover a broad spectrum of tasks, FLIP focuses on constrained settings where data availability is limited. This makes it an ideal framework to evaluate model performance in scenarios with scarce task-specific data. We investigate whether recent advances in prote","authors_text":"Alicia Lozano-Diez, Daniel Ramos, Doroteo T. Toledano, Joaquin Gonzalez-Rodriguez, Manuel F. Mollon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T09:24:58Z","title":"Exploring Large Protein Language Models in Constrained Evaluation Scenarios within the FLIP Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18223","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:a8a1d6694ff7eb2d8fce8798cb6d39bf3702b4665b8789ba5ccef2f6697fdb95","target":"record","created_at":"2026-07-05T10:07:31Z","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":"4332d0f43758313581bb04962d286593113ec78c1da43478eda56cc82ce045d3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T09:24:58Z","title_canon_sha256":"f3ef022410769d6bb38c0f4e99d148cdc28f5de1ceff03fbbebaa44bd4aa9e2a"},"schema_version":"1.0","source":{"id":"2501.18223","kind":"arxiv","version":1}},"canonical_sha256":"5332f4aab1b3db5bd5840ae99d40df92c5d09fce0b7215683e2a6980dc8957f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5332f4aab1b3db5bd5840ae99d40df92c5d09fce0b7215683e2a6980dc8957f6","first_computed_at":"2026-07-05T10:07:31.253614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:31.253614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wF9h2yJq4u3tLsrmIy/LTpFpdRCzI6OM1GB6Uq4l13rKg9k3O3ctT+0yAv3F+nTPWZk0jfqh117T+eZFv4bbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:31.254074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8a1d6694ff7eb2d8fce8798cb6d39bf3702b4665b8789ba5ccef2f6697fdb95","sha256:5bea5599a45ca8c1b43b64bcac482eaf4972bc5a4a5d3e105dd49860dddd5190"],"state_sha256":"21261c74358138cde852f98efebac79e565e8ef51cb911cbc490ef4cc0801d58"}