{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2009:GRTMJWMV34JRCX2KE564ALXYSR","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":"31f21cb8c31d34925d038b13e359be4d5839106b4b32d350ab088912b8a13daf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2009-01-21T07:59:27Z","title_canon_sha256":"ffe1f17f738e22150f2d4682bf49a16b22fd7367fa4388412cc86e59bedfbf47"},"schema_version":"1.0","source":{"id":"0901.3198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"0901.3198","created_at":"2026-05-18T04:31:31Z"},{"alias_kind":"arxiv_version","alias_value":"0901.3198v1","created_at":"2026-05-18T04:31:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0901.3198","created_at":"2026-05-18T04:31:31Z"},{"alias_kind":"pith_short_12","alias_value":"GRTMJWMV34JR","created_at":"2026-05-18T12:25:59Z"},{"alias_kind":"pith_short_16","alias_value":"GRTMJWMV34JRCX2K","created_at":"2026-05-18T12:25:59Z"},{"alias_kind":"pith_short_8","alias_value":"GRTMJWMV","created_at":"2026-05-18T12:25:59Z"}],"graph_snapshots":[{"event_id":"sha256:7b569095c98c0a05dfbd6f1f52eec415510c1a3fac92612234a1111d741a1d96","target":"graph","created_at":"2026-05-18T04:31:31Z","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"},"paper":{"abstract_excerpt":"We apply the concept of subset seeds proposed in [1] to similarity search in protein sequences. The main question studied is the design of efficient seed alphabets to construct seeds with optimal sensitivity/selectivity trade-offs. We propose several different design methods and use them to construct several alphabets. We then perform a comparative analysis of seeds built over those alphabets and compare them with the standard BLASTP seeding method [2], [3], as well as with the family of vector seeds proposed in [4]. While the formalism of subset seeds is less expressive (but less costly to im","authors_text":"Anna Gambin, Eugenia Furletova (IMPB), Ewa Szczurek (MPI), Gregory Kucherov (LIFL, INRIA Lille - Nord Europe), Laurent No\\'e (LIFL, Mikhail A. Roytberg (IMPB), Slawomir Lasota","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2009-01-21T07:59:27Z","title":"On subset seeds for protein alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0901.3198","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":"sha256:39a5f3aebce990f92ba3a39f805c6d21a268fc93f039fde77da2f9901083086d","target":"record","created_at":"2026-05-18T04:31:31Z","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":"31f21cb8c31d34925d038b13e359be4d5839106b4b32d350ab088912b8a13daf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2009-01-21T07:59:27Z","title_canon_sha256":"ffe1f17f738e22150f2d4682bf49a16b22fd7367fa4388412cc86e59bedfbf47"},"schema_version":"1.0","source":{"id":"0901.3198","kind":"arxiv","version":1}},"canonical_sha256":"3466c4d995df13115f4a277dc02ef8947d33934b1fb452ca541a07b95c5cb139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3466c4d995df13115f4a277dc02ef8947d33934b1fb452ca541a07b95c5cb139","first_computed_at":"2026-05-18T04:31:31.396434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:31:31.396434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1OxqFmgW8/YcOnOBGfn7MsqgywaSBEh6M2jlzCLzfWJ0hxvY+k83A/rlozwdXrMOogMVTY9aZbeiM4/WaLFODA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:31:31.396999Z","signed_message":"canonical_sha256_bytes"},"source_id":"0901.3198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39a5f3aebce990f92ba3a39f805c6d21a268fc93f039fde77da2f9901083086d","sha256:7b569095c98c0a05dfbd6f1f52eec415510c1a3fac92612234a1111d741a1d96"],"state_sha256":"7304dd49e5edacaaa8b6a76f7b069b56e7d3f01a8847c4a6e4905a49b1b3d925"}