{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E55TT6MIPEPGMPXA6BMHLKFMIU","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":"28c7ad61d9d634dd9040dc11cf5c82b9ef342c9e9c9e7898d36965c38af7c4dd","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T19:04:34Z","title_canon_sha256":"ae4dd9afaa958182f5ab538f8a06900b9b6e0c2a0df091d5b8fb17a2a359f737"},"schema_version":"1.0","source":{"id":"2606.12609","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12609","created_at":"2026-06-12T00:07:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12609v1","created_at":"2026-06-12T00:07:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12609","created_at":"2026-06-12T00:07:56Z"},{"alias_kind":"pith_short_12","alias_value":"E55TT6MIPEPG","created_at":"2026-06-12T00:07:56Z"},{"alias_kind":"pith_short_16","alias_value":"E55TT6MIPEPGMPXA","created_at":"2026-06-12T00:07:56Z"},{"alias_kind":"pith_short_8","alias_value":"E55TT6MI","created_at":"2026-06-12T00:07:56Z"}],"graph_snapshots":[{"event_id":"sha256:7019d60163f6f2270013459a470187fb5daef4ecc6eb089605b109c9b8199e73","target":"graph","created_at":"2026-06-12T00:07:56Z","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/2606.12609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein language models are trained on highly imbalanced datasets, raising the question of how they represent underrepresented biological sequences. Using viral proteins as a case study across ESM model families, we identify a dominant nativeness axis in embedding space, aligned with masked reconstruction perplexity, that orders sequences from well-modeled cellular proteins through viral proteins to shuffled and random sequences. Scaling contracts this axis unevenly across viral families. Despite this, protein language model embeddings retain viral-specific signal: viral proteins remain linear","authors_text":"Arthur Bigot, Core Francisco Park, Dianzhuo Wang, Eugene Shakhnovich, Harmon Bhasin","cross_cats":["q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T19:04:34Z","title":"Viral Proteins Reveal Geometry of Protein Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12609","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":"sha256:4d55e26f7635c0e1b3143bc20cf9015d19fe028a485923257646729a18f05ea7","target":"record","created_at":"2026-06-12T00:07:56Z","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":"28c7ad61d9d634dd9040dc11cf5c82b9ef342c9e9c9e7898d36965c38af7c4dd","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T19:04:34Z","title_canon_sha256":"ae4dd9afaa958182f5ab538f8a06900b9b6e0c2a0df091d5b8fb17a2a359f737"},"schema_version":"1.0","source":{"id":"2606.12609","kind":"arxiv","version":1}},"canonical_sha256":"277b39f988791e663ee0f05875a8ac453b8a403189bd7875e075b98e0ea2d3f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"277b39f988791e663ee0f05875a8ac453b8a403189bd7875e075b98e0ea2d3f8","first_computed_at":"2026-06-12T00:07:56.290148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T00:07:56.290148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kOmtsp3im4fWZJ59GnqDpCohqM6DUKcUFDWJDrHGIRBL0rtrbhmeGX1jnamTbK8cHaThC3tzhwONV+VCTpAYDQ==","signature_status":"signed_v1","signed_at":"2026-06-12T00:07:56.290550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12609","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d55e26f7635c0e1b3143bc20cf9015d19fe028a485923257646729a18f05ea7","sha256:7019d60163f6f2270013459a470187fb5daef4ecc6eb089605b109c9b8199e73"],"state_sha256":"2c424643d8231261902f141a44761c66711fd81e6ad1c4d63c41774700f44d10"}