{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QNTGU3UMIRM6VFNUVLXH33EL4D","short_pith_number":"pith:QNTGU3UM","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"},"canonical_sha256":"83666a6e8c4459ea95b4aaee7dec8be0e264a0abb6e3d5e7c88214abf3dc0534","source":{"kind":"arxiv","id":"2605.16331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16331","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16331v1","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16331","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"QNTGU3UMIRM6","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"QNTGU3UMIRM6VFNU","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"QNTGU3UM","created_at":"2026-05-20T00:02:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QNTGU3UMIRM6VFNUVLXH33EL4D","target":"record","payload":{"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"},"canonical_sha256":"83666a6e8c4459ea95b4aaee7dec8be0e264a0abb6e3d5e7c88214abf3dc0534","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"},"source_kind":"arxiv","source_id":"2605.16331","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGZETroV4roq47+wTeSVpI9PnqAMQe0ZTL4++CKJmRUe8fP8NIcgN8e31VK7WF4/Yv5yQuyJvnfVCL1QQxFKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:01:17.095623Z"},"content_sha256":"32d893ff7d1960174a1a71e3e3c0b527dffe4316d162a0276863e905db1a3984","schema_version":"1.0","event_id":"sha256:32d893ff7d1960174a1a71e3e3c0b527dffe4316d162a0276863e905db1a3984"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QNTGU3UMIRM6VFNUVLXH33EL4D","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kgm+PQR6BxTMzL9uBITYkRN6oLFLBkSDV4OewcPijjdpynnFiz1KCJ7KjYQrGsrYZgmb9YUbJEI2W3ReB6neBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:01:17.095986Z"},"content_sha256":"004ec11f246e9f10769c66a07ea019eacd07533d5c186c584ac33bca08c064b9","schema_version":"1.0","event_id":"sha256:004ec11f246e9f10769c66a07ea019eacd07533d5c186c584ac33bca08c064b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/bundle.json","state_url":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T15:01:17Z","links":{"resolver":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D","bundle":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/bundle.json","state":"https://pith.science/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNTGU3UMIRM6VFNUVLXH33EL4D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QNTGU3UMIRM6VFNUVLXH33EL4D","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":"75ae23e5694652e5ab9362e4077b008627efc7bca1d48ef18ec0b91fc9586670","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2026-05-05T17:51:21Z","title_canon_sha256":"bc10ea47bebe4e0d2f081dec87323245924eb1290ab321c937a5b44677450b2a"},"schema_version":"1.0","source":{"id":"2605.16331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16331","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16331v1","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16331","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_12","alias_value":"QNTGU3UMIRM6","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_16","alias_value":"QNTGU3UMIRM6VFNU","created_at":"2026-05-20T00:02:17Z"},{"alias_kind":"pith_short_8","alias_value":"QNTGU3UM","created_at":"2026-05-20T00:02:17Z"}],"graph_snapshots":[{"event_id":"sha256:004ec11f246e9f10769c66a07ea019eacd07533d5c186c584ac33bca08c064b9","target":"graph","created_at":"2026-05-20T00:02:17Z","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/2605.16331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Oliver M. Crook, Piotr Jedryszek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2026-05-05T17:51:21Z","title":"Retrieval and competition: how a protein foundation model starts a protein"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16331","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":"sha256:32d893ff7d1960174a1a71e3e3c0b527dffe4316d162a0276863e905db1a3984","target":"record","created_at":"2026-05-20T00:02:17Z","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":"75ae23e5694652e5ab9362e4077b008627efc7bca1d48ef18ec0b91fc9586670","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2026-05-05T17:51:21Z","title_canon_sha256":"bc10ea47bebe4e0d2f081dec87323245924eb1290ab321c937a5b44677450b2a"},"schema_version":"1.0","source":{"id":"2605.16331","kind":"arxiv","version":1}},"canonical_sha256":"83666a6e8c4459ea95b4aaee7dec8be0e264a0abb6e3d5e7c88214abf3dc0534","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83666a6e8c4459ea95b4aaee7dec8be0e264a0abb6e3d5e7c88214abf3dc0534","first_computed_at":"2026-05-20T00:02:17.199179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:17.199179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5z3CUjikkDfXsq/5Yt/31endyoP7qP1uAJ/duTMolxAKeZoL62J0D1x/dKtUC/JpHz7g6U0PBoLNXSpmCozbAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:17.199679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32d893ff7d1960174a1a71e3e3c0b527dffe4316d162a0276863e905db1a3984","sha256:004ec11f246e9f10769c66a07ea019eacd07533d5c186c584ac33bca08c064b9"],"state_sha256":"c647b82220b7d1ed958ba622bcb4e3abee9e049deb1f24aa27838888c688698c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdM/oqYn70bgsYG/WmxffM8lInvxPsiSTj6Ul0qcW1ZCUi5Zw3O8k0UAkdN2ajo2lVALCwb6C7Ii58cvEC1KBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:01:17.097926Z","bundle_sha256":"365565f1ac7e1f18406bc41c3058c7923d73052bc0f8d5678e63847c419fe229"}}