{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PIVSUGF53WX5KM25EEGXHYYXX6","short_pith_number":"pith:PIVSUGF5","canonical_record":{"source":{"id":"1812.11467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-12-30T04:15:29Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"2ab2317c3bcd614731353e2f029ceb65de5fed96611758b0463162e1709f2986","abstract_canon_sha256":"4f5c76107e6dba48f3195408f16ef5270433cdc633a6381dfa9e31ab8e571b45"},"schema_version":"1.0"},"canonical_sha256":"7a2b2a18bdddafd5335d210d73e317bf8ddb3aa994ea1a96da5db5395cd62ebb","source":{"kind":"arxiv","id":"1812.11467","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11467","created_at":"2026-05-17T23:57:11Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11467v1","created_at":"2026-05-17T23:57:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11467","created_at":"2026-05-17T23:57:11Z"},{"alias_kind":"pith_short_12","alias_value":"PIVSUGF53WX5","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PIVSUGF53WX5KM25","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PIVSUGF5","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PIVSUGF53WX5KM25EEGXHYYXX6","target":"record","payload":{"canonical_record":{"source":{"id":"1812.11467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-12-30T04:15:29Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"2ab2317c3bcd614731353e2f029ceb65de5fed96611758b0463162e1709f2986","abstract_canon_sha256":"4f5c76107e6dba48f3195408f16ef5270433cdc633a6381dfa9e31ab8e571b45"},"schema_version":"1.0"},"canonical_sha256":"7a2b2a18bdddafd5335d210d73e317bf8ddb3aa994ea1a96da5db5395cd62ebb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:11.876433Z","signature_b64":"dnq4eIlgUTorK685o5Yl+csPeSe7Q8W7nHQ0i7oIHkRfUdnIsSIB0AGh3A+XveqixlJJziVhIiVCPQmwSqxPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a2b2a18bdddafd5335d210d73e317bf8ddb3aa994ea1a96da5db5395cd62ebb","last_reissued_at":"2026-05-17T23:57:11.875838Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:11.875838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.11467","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":"2026-05-17T23:57:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p8wC6+VKwhM5XuY4cSAbNppMla0X4jAP6UpKMJXDtghur2FJKc7t+ySfyMuCiI4kV3OYXanr45VTi5/EabQiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:32:33.710340Z"},"content_sha256":"fe09c427e41e53892d1ed9334637bf24ab4e32edd29f817bda3977563d35f10d","schema_version":"1.0","event_id":"sha256:fe09c427e41e53892d1ed9334637bf24ab4e32edd29f817bda3977563d35f10d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PIVSUGF53WX5KM25EEGXHYYXX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ATHENA: Automated Tuning of Genomic Error Correction Algorithms using Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.NE","authors_text":"Ashraf Mahgoub, Mustafa Abdallah, Saurabh Bagchi, Somali Chaterji","submitted_at":"2018-12-30T04:15:29Z","abstract_excerpt":"The performance of most error-correction algorithms that operate on genomic sequencer reads is dependent on the proper choice of its configuration parameters, such as the value of k in k-mer based techniques. In this work, we target the problem of finding the best values of these configuration parameters to optimize error correction. We perform this in a data-driven manner, due to the observation that different configuration parameters are optimal for different datasets, i.e., from different instruments and organisms. We use language modeling techniques from the Natural Language Processing (NL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11467","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8S0VLzsrlIrazM8gjhUIwhYZGoefsMUy2YWV3eaTPYplwJ6NeLGAhFarxsaCTZ/K/EPVqUu7gYgoUqOSwL9ZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:32:33.710693Z"},"content_sha256":"7c577132c912f163e61a532783f6c046be0e7ef89ac3e5dc6176a70f7fdf3a75","schema_version":"1.0","event_id":"sha256:7c577132c912f163e61a532783f6c046be0e7ef89ac3e5dc6176a70f7fdf3a75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PIVSUGF53WX5KM25EEGXHYYXX6/bundle.json","state_url":"https://pith.science/pith/PIVSUGF53WX5KM25EEGXHYYXX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PIVSUGF53WX5KM25EEGXHYYXX6/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":"2026-05-28T01:32:33Z","links":{"resolver":"https://pith.science/pith/PIVSUGF53WX5KM25EEGXHYYXX6","bundle":"https://pith.science/pith/PIVSUGF53WX5KM25EEGXHYYXX6/bundle.json","state":"https://pith.science/pith/PIVSUGF53WX5KM25EEGXHYYXX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PIVSUGF53WX5KM25EEGXHYYXX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PIVSUGF53WX5KM25EEGXHYYXX6","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":"4f5c76107e6dba48f3195408f16ef5270433cdc633a6381dfa9e31ab8e571b45","cross_cats_sorted":["q-bio.GN"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-12-30T04:15:29Z","title_canon_sha256":"2ab2317c3bcd614731353e2f029ceb65de5fed96611758b0463162e1709f2986"},"schema_version":"1.0","source":{"id":"1812.11467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.11467","created_at":"2026-05-17T23:57:11Z"},{"alias_kind":"arxiv_version","alias_value":"1812.11467v1","created_at":"2026-05-17T23:57:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11467","created_at":"2026-05-17T23:57:11Z"},{"alias_kind":"pith_short_12","alias_value":"PIVSUGF53WX5","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PIVSUGF53WX5KM25","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PIVSUGF5","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:7c577132c912f163e61a532783f6c046be0e7ef89ac3e5dc6176a70f7fdf3a75","target":"graph","created_at":"2026-05-17T23:57:11Z","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":"The performance of most error-correction algorithms that operate on genomic sequencer reads is dependent on the proper choice of its configuration parameters, such as the value of k in k-mer based techniques. In this work, we target the problem of finding the best values of these configuration parameters to optimize error correction. We perform this in a data-driven manner, due to the observation that different configuration parameters are optimal for different datasets, i.e., from different instruments and organisms. We use language modeling techniques from the Natural Language Processing (NL","authors_text":"Ashraf Mahgoub, Mustafa Abdallah, Saurabh Bagchi, Somali Chaterji","cross_cats":["q-bio.GN"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-12-30T04:15:29Z","title":"ATHENA: Automated Tuning of Genomic Error Correction Algorithms using Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11467","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:fe09c427e41e53892d1ed9334637bf24ab4e32edd29f817bda3977563d35f10d","target":"record","created_at":"2026-05-17T23:57:11Z","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":"4f5c76107e6dba48f3195408f16ef5270433cdc633a6381dfa9e31ab8e571b45","cross_cats_sorted":["q-bio.GN"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-12-30T04:15:29Z","title_canon_sha256":"2ab2317c3bcd614731353e2f029ceb65de5fed96611758b0463162e1709f2986"},"schema_version":"1.0","source":{"id":"1812.11467","kind":"arxiv","version":1}},"canonical_sha256":"7a2b2a18bdddafd5335d210d73e317bf8ddb3aa994ea1a96da5db5395cd62ebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a2b2a18bdddafd5335d210d73e317bf8ddb3aa994ea1a96da5db5395cd62ebb","first_computed_at":"2026-05-17T23:57:11.875838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:11.875838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dnq4eIlgUTorK685o5Yl+csPeSe7Q8W7nHQ0i7oIHkRfUdnIsSIB0AGh3A+XveqixlJJziVhIiVCPQmwSqxPDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:11.876433Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.11467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe09c427e41e53892d1ed9334637bf24ab4e32edd29f817bda3977563d35f10d","sha256:7c577132c912f163e61a532783f6c046be0e7ef89ac3e5dc6176a70f7fdf3a75"],"state_sha256":"13167bce6798209ce428f2c5b74c918953f8a56e280f2aae28c771c54c53ee52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1roiGW9CTYS5qzbm1FjYXqRBO25NDShfCfrNa3Wt9ZWRCsNyCjsLUHXgE94PbPx0ZiUrVUK/oDUnq6zvubZNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:32:33.712770Z","bundle_sha256":"d587f4a3248a2562db4029106b2b81d4978e93885865dc9bb409f342aec7610a"}}