{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:WXF5QJRI7SIUIEHEMZ3SVBKTDJ","short_pith_number":"pith:WXF5QJRI","canonical_record":{"source":{"id":"1409.6384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-09-23T01:27:56Z","cross_cats_sorted":[],"title_canon_sha256":"e7311dec299e5409e4e90fbd95569d4821ac9c758c44718274277e155c06d826","abstract_canon_sha256":"6e59c899c2658aeb056e0bc723858951b228c42cd77144a32a3c28eea7ffec3f"},"schema_version":"1.0"},"canonical_sha256":"b5cbd82628fc914410e466772a85531a57ca18039f5e2169bb3ef55a83a49b1b","source":{"kind":"arxiv","id":"1409.6384","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.6384","created_at":"2026-05-18T01:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"1409.6384v2","created_at":"2026-05-18T01:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.6384","created_at":"2026-05-18T01:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"WXF5QJRI7SIU","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WXF5QJRI7SIUIEHE","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WXF5QJRI","created_at":"2026-05-18T12:28:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:WXF5QJRI7SIUIEHEMZ3SVBKTDJ","target":"record","payload":{"canonical_record":{"source":{"id":"1409.6384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-09-23T01:27:56Z","cross_cats_sorted":[],"title_canon_sha256":"e7311dec299e5409e4e90fbd95569d4821ac9c758c44718274277e155c06d826","abstract_canon_sha256":"6e59c899c2658aeb056e0bc723858951b228c42cd77144a32a3c28eea7ffec3f"},"schema_version":"1.0"},"canonical_sha256":"b5cbd82628fc914410e466772a85531a57ca18039f5e2169bb3ef55a83a49b1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:47.406409Z","signature_b64":"GMPcHylchFY0ugLFDHKVgcH3u4H2R5bf6KrAnYGyW2F4blejXhUwRIvsGRBaPJEiG0T9l2eJD0JVw1yXTdExBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5cbd82628fc914410e466772a85531a57ca18039f5e2169bb3ef55a83a49b1b","last_reissued_at":"2026-05-18T01:20:47.405892Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:47.405892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1409.6384","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:20:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E7bl+XiDJBsWH9ABpeJJPLPqihumeAUgD+9/ymZjxlAKnhevyn3L+Q8ehVd6iJG8hleC+kr/Tp8EyNeLikmGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:50:30.209249Z"},"content_sha256":"f0e424cedc743d3ce7076e274fd5b554aae943b8538ee605c02b9457831a1111","schema_version":"1.0","event_id":"sha256:f0e424cedc743d3ce7076e274fd5b554aae943b8538ee605c02b9457831a1111"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:WXF5QJRI7SIUIEHEMZ3SVBKTDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond the E-value: stratified statistics for protein domain prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Alejandro Ochoa, John D. Storey, Manuel Llin\\'as, Mona Singh","submitted_at":"2014-09-23T01:27:56Z","abstract_excerpt":"E-values have been the dominant statistic for protein sequence analysis for the past two decades: from identifying statistically significant local sequence alignments to evaluating matches to hidden Markov models describing protein domain families. Here we formally show that for \"stratified\" multiple hypothesis testing problems, controlling the local False Discovery Rate (lFDR) per stratum, or partition, yields the most predictions across the data at any given threshold on the FDR or E-value over all strata combined. For the important problem of protein domain prediction, a key step in charact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.6384","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:20:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xptWpRf9szLkd1lBjD+9uUkA5dFMqg8Qers1/prIvk1dK/brq3seeHYW7dRZDlgfL+SktakBK9eRr91uy+NxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:50:30.209898Z"},"content_sha256":"64239d0a80bb739e5d86c9c5d8a82900d768dbd4ef4a6299cd1a1dd0e74597a0","schema_version":"1.0","event_id":"sha256:64239d0a80bb739e5d86c9c5d8a82900d768dbd4ef4a6299cd1a1dd0e74597a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXF5QJRI7SIUIEHEMZ3SVBKTDJ/bundle.json","state_url":"https://pith.science/pith/WXF5QJRI7SIUIEHEMZ3SVBKTDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXF5QJRI7SIUIEHEMZ3SVBKTDJ/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":"2026-05-31T19:50:30Z","links":{"resolver":"https://pith.science/pith/WXF5QJRI7SIUIEHEMZ3SVBKTDJ","bundle":"https://pith.science/pith/WXF5QJRI7SIUIEHEMZ3SVBKTDJ/bundle.json","state":"https://pith.science/pith/WXF5QJRI7SIUIEHEMZ3SVBKTDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXF5QJRI7SIUIEHEMZ3SVBKTDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:WXF5QJRI7SIUIEHEMZ3SVBKTDJ","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":"6e59c899c2658aeb056e0bc723858951b228c42cd77144a32a3c28eea7ffec3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-09-23T01:27:56Z","title_canon_sha256":"e7311dec299e5409e4e90fbd95569d4821ac9c758c44718274277e155c06d826"},"schema_version":"1.0","source":{"id":"1409.6384","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.6384","created_at":"2026-05-18T01:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"1409.6384v2","created_at":"2026-05-18T01:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.6384","created_at":"2026-05-18T01:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"WXF5QJRI7SIU","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WXF5QJRI7SIUIEHE","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WXF5QJRI","created_at":"2026-05-18T12:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:64239d0a80bb739e5d86c9c5d8a82900d768dbd4ef4a6299cd1a1dd0e74597a0","target":"graph","created_at":"2026-05-18T01:20:47Z","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":"E-values have been the dominant statistic for protein sequence analysis for the past two decades: from identifying statistically significant local sequence alignments to evaluating matches to hidden Markov models describing protein domain families. Here we formally show that for \"stratified\" multiple hypothesis testing problems, controlling the local False Discovery Rate (lFDR) per stratum, or partition, yields the most predictions across the data at any given threshold on the FDR or E-value over all strata combined. For the important problem of protein domain prediction, a key step in charact","authors_text":"Alejandro Ochoa, John D. Storey, Manuel Llin\\'as, Mona Singh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-09-23T01:27:56Z","title":"Beyond the E-value: stratified statistics for protein domain prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.6384","kind":"arxiv","version":2},"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:f0e424cedc743d3ce7076e274fd5b554aae943b8538ee605c02b9457831a1111","target":"record","created_at":"2026-05-18T01:20:47Z","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":"6e59c899c2658aeb056e0bc723858951b228c42cd77144a32a3c28eea7ffec3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2014-09-23T01:27:56Z","title_canon_sha256":"e7311dec299e5409e4e90fbd95569d4821ac9c758c44718274277e155c06d826"},"schema_version":"1.0","source":{"id":"1409.6384","kind":"arxiv","version":2}},"canonical_sha256":"b5cbd82628fc914410e466772a85531a57ca18039f5e2169bb3ef55a83a49b1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5cbd82628fc914410e466772a85531a57ca18039f5e2169bb3ef55a83a49b1b","first_computed_at":"2026-05-18T01:20:47.405892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:47.405892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GMPcHylchFY0ugLFDHKVgcH3u4H2R5bf6KrAnYGyW2F4blejXhUwRIvsGRBaPJEiG0T9l2eJD0JVw1yXTdExBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:47.406409Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.6384","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0e424cedc743d3ce7076e274fd5b554aae943b8538ee605c02b9457831a1111","sha256:64239d0a80bb739e5d86c9c5d8a82900d768dbd4ef4a6299cd1a1dd0e74597a0"],"state_sha256":"b31d347e725c35a034c8b23a3a638a61a1aff9da0dfdad17e5214774af6d2d42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffyQZGgUe8U1JC9GNGPvHbwRlCdTqxk4+pW2XDZMCKgdlbaIfBT1QSem3Pi7tfozT6f+dcvYxsGwVvRTwCaoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:50:30.213869Z","bundle_sha256":"52863d94888836e148b25a6d31e26dfd4c04f783e574b0723e68a55f00c5f244"}}