{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5NOSDOS7OONPGITDIJVROJK3FH","short_pith_number":"pith:5NOSDOS7","schema_version":"1.0","canonical_sha256":"eb5d21ba5f739af32263426b17255b29dcd371343d5db0a54326c48a790a9e4e","source":{"kind":"arxiv","id":"1807.10394","version":1},"attestation_state":"computed","paper":{"title":"On the Natural Structure of Amino Acid Patterns in Families of Protein Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.BM","authors_text":"Diego U. Ferreiro, Pablo Turjanski","submitted_at":"2018-07-26T22:59:48Z","abstract_excerpt":"All known terrestrial proteins are coded as continuous strings of ~20 amino acids. The patterns formed by the repetitions of elements in groups of finite sequences describes the natural architectures of protein families. We present a method to search for patterns and groupings of patterns in protein sequences using a mathematically precise definition for 'repetition', an efficient algorithmic implementation and a robust scoring system with no adjustable parameters. We show that the sequence patterns can be well-separated into disjoint classes according to their recurrence in nested structures."},"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":"1807.10394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2018-07-26T22:59:48Z","cross_cats_sorted":[],"title_canon_sha256":"460e64b89937a0a1fefac53e80e4b13d0e07f31de017af6566d535f511a65283","abstract_canon_sha256":"887e71570f6c8c5a9785a246932d42444e813dc517a3e1ec042e65c4f2cfe540"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:40.736992Z","signature_b64":"SH3sBpmBLKa/92DeF6eLYGKcwLZSNs0s1KbMuGN9qZ66Cjq1qExH3OC7eAdYORaQ/KMzAdVz7NDqQM72d9zuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb5d21ba5f739af32263426b17255b29dcd371343d5db0a54326c48a790a9e4e","last_reissued_at":"2026-05-18T00:09:40.736481Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:40.736481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Natural Structure of Amino Acid Patterns in Families of Protein Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.BM","authors_text":"Diego U. Ferreiro, Pablo Turjanski","submitted_at":"2018-07-26T22:59:48Z","abstract_excerpt":"All known terrestrial proteins are coded as continuous strings of ~20 amino acids. The patterns formed by the repetitions of elements in groups of finite sequences describes the natural architectures of protein families. We present a method to search for patterns and groupings of patterns in protein sequences using a mathematically precise definition for 'repetition', an efficient algorithmic implementation and a robust scoring system with no adjustable parameters. We show that the sequence patterns can be well-separated into disjoint classes according to their recurrence in nested structures."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10394","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":""},"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":"1807.10394","created_at":"2026-05-18T00:09:40.736567+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.10394v1","created_at":"2026-05-18T00:09:40.736567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10394","created_at":"2026-05-18T00:09:40.736567+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NOSDOS7OONP","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NOSDOS7OONPGITD","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NOSDOS7","created_at":"2026-05-18T12:32:08.215937+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/5NOSDOS7OONPGITDIJVROJK3FH","json":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH.json","graph_json":"https://pith.science/api/pith-number/5NOSDOS7OONPGITDIJVROJK3FH/graph.json","events_json":"https://pith.science/api/pith-number/5NOSDOS7OONPGITDIJVROJK3FH/events.json","paper":"https://pith.science/paper/5NOSDOS7"},"agent_actions":{"view_html":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH","download_json":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH.json","view_paper":"https://pith.science/paper/5NOSDOS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.10394&json=true","fetch_graph":"https://pith.science/api/pith-number/5NOSDOS7OONPGITDIJVROJK3FH/graph.json","fetch_events":"https://pith.science/api/pith-number/5NOSDOS7OONPGITDIJVROJK3FH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH/action/storage_attestation","attest_author":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH/action/author_attestation","sign_citation":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH/action/citation_signature","submit_replication":"https://pith.science/pith/5NOSDOS7OONPGITDIJVROJK3FH/action/replication_record"}},"created_at":"2026-05-18T00:09:40.736567+00:00","updated_at":"2026-05-18T00:09:40.736567+00:00"}