{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QNTGU3UMIRM6VFNUVLXH33EL4D","short_pith_number":"pith:QNTGU3UM","schema_version":"1.0","canonical_sha256":"83666a6e8c4459ea95b4aaee7dec8be0e264a0abb6e3d5e7c88214abf3dc0534","source":{"kind":"arxiv","id":"2605.16331","version":1},"attestation_state":"computed","paper":{"title":"Retrieval and competition: how a protein foundation model starts a protein","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Oliver M. Crook, Piotr Jedryszek","submitted_at":"2026-05-05T17:51:21Z","abstract_excerpt":"Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction reflects recognition of biological evidence or retrieval of a statistical default. We examine this distinction for a near-universal biological rule, that proteins begin with methionine, by tracing the computational pathway through which ESM2-8M produces this prediction. The model does not detect methionine at the masked position. Instead, it retrieves a methionine-favouring signal from a reference representation at the beginning-of-sequence token vi"},"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":"2605.16331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2026-05-05T17:51:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc10ea47bebe4e0d2f081dec87323245924eb1290ab321c937a5b44677450b2a","abstract_canon_sha256":"75ae23e5694652e5ab9362e4077b008627efc7bca1d48ef18ec0b91fc9586670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:17.199679Z","signature_b64":"5z3CUjikkDfXsq/5Yt/31endyoP7qP1uAJ/duTMolxAKeZoL62J0D1x/dKtUC/JpHz7g6U0PBoLNXSpmCozbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83666a6e8c4459ea95b4aaee7dec8be0e264a0abb6e3d5e7c88214abf3dc0534","last_reissued_at":"2026-05-20T00:02:17.199179Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:17.199179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval and competition: how a protein foundation model starts a protein","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.BM","authors_text":"Oliver M. Crook, Piotr Jedryszek","submitted_at":"2026-05-05T17:51:21Z","abstract_excerpt":"Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction reflects recognition of biological evidence or retrieval of a statistical default. We examine this distinction for a near-universal biological rule, that proteins begin with methionine, by tracing the computational pathway through which ESM2-8M produces this prediction. The model does not detect methionine at the masked position. Instead, it retrieves a methionine-favouring signal from a reference representation at the beginning-of-sequence token vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16331","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/2605.16331/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":"2605.16331","created_at":"2026-05-20T00:02:17.199253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16331v1","created_at":"2026-05-20T00:02:17.199253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16331","created_at":"2026-05-20T00:02:17.199253+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNTGU3UMIRM6","created_at":"2026-05-20T00:02:17.199253+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNTGU3UMIRM6VFNU","created_at":"2026-05-20T00:02:17.199253+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNTGU3UM","created_at":"2026-05-20T00:02:17.199253+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/QNTGU3UMIRM6VFNUVLXH33EL4D","json":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D.json","graph_json":"https://pith.science/api/pith-number/QNTGU3UMIRM6VFNUVLXH33EL4D/graph.json","events_json":"https://pith.science/api/pith-number/QNTGU3UMIRM6VFNUVLXH33EL4D/events.json","paper":"https://pith.science/paper/QNTGU3UM"},"agent_actions":{"view_html":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D","download_json":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D.json","view_paper":"https://pith.science/paper/QNTGU3UM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16331&json=true","fetch_graph":"https://pith.science/api/pith-number/QNTGU3UMIRM6VFNUVLXH33EL4D/graph.json","fetch_events":"https://pith.science/api/pith-number/QNTGU3UMIRM6VFNUVLXH33EL4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/action/storage_attestation","attest_author":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/action/author_attestation","sign_citation":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/action/citation_signature","submit_replication":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/action/replication_record"}},"created_at":"2026-05-20T00:02:17.199253+00:00","updated_at":"2026-05-20T00:02:17.199253+00:00"}