{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NPHXEUFAUU6QRXC6776M5MSNXZ","short_pith_number":"pith:NPHXEUFA","canonical_record":{"source":{"id":"2211.09862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-11-17T19:54:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d9fe730b583b061ac027590db8c4600c55167fe66a48c97a2e63ed16da28462","abstract_canon_sha256":"2e44f6f85263e3f82258fa294eb54d21be43c8d3c311093c5eafe1d4ed123e22"},"schema_version":"1.0"},"canonical_sha256":"6bcf7250a0a53d08dc5efffcceb24dbe6143cde94fa905320c9fb9a0224cd4b6","source":{"kind":"arxiv","id":"2211.09862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09862","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09862v1","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09862","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"NPHXEUFAUU6Q","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"pith_short_16","alias_value":"NPHXEUFAUU6QRXC6","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"pith_short_8","alias_value":"NPHXEUFA","created_at":"2026-07-05T05:17:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NPHXEUFAUU6QRXC6776M5MSNXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2211.09862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-11-17T19:54:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d9fe730b583b061ac027590db8c4600c55167fe66a48c97a2e63ed16da28462","abstract_canon_sha256":"2e44f6f85263e3f82258fa294eb54d21be43c8d3c311093c5eafe1d4ed123e22"},"schema_version":"1.0"},"canonical_sha256":"6bcf7250a0a53d08dc5efffcceb24dbe6143cde94fa905320c9fb9a0224cd4b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:14.909604Z","signature_b64":"G9akTqfSmdDeB+QCVqyclUW09SuT3ep01Aads7RzMVqmHltb8ulq0BENlejGa3iZgiJmpbsgkLbRzyfNW2F8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bcf7250a0a53d08dc5efffcceb24dbe6143cde94fa905320c9fb9a0224cd4b6","last_reissued_at":"2026-07-05T05:17:14.909142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:14.909142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.09862","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":"2026-07-05T05:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BnZqq1r46z7MzE3Xfc6lccvQ+O2O9puqjyQ7i8jR37iJCH8EL6pe9Y36Qi9O+9bFxpP2SoQDaTLgwVCSvxOeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:38:54.051914Z"},"content_sha256":"7d93be12cf15c83554089308223f7baf59e44ff911102160dacf6c02ed92e53c","schema_version":"1.0","event_id":"sha256:7d93be12cf15c83554089308223f7baf59e44ff911102160dacf6c02ed92e53c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NPHXEUFAUU6QRXC6776M5MSNXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge distillation for fast and accurate DNA sequence correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Aaron M. Wenger, Alexey Kolesnikov, Anastasiya Belyaeva, Andrew Carroll, Armin T\\\"opfer, Cory Y. McLean, Daniel E. Cook, Daniel Liu, Howard Yang, Joel Shor, Kishwar Shafin, Maria Nattestad, Pi-Chuan Chang, William J. Rowell","submitted_at":"2022-11-17T19:54:18Z","abstract_excerpt":"Accurate genome sequencing can improve our understanding of biology and the genetic basis of disease. The standard approach for generating DNA sequences from PacBio instruments relies on HMM-based models. Here, we introduce Distilled DeepConsensus - a distilled transformer-encoder model for sequence correction, which improves upon the HMM-based methods with runtime constraints in mind. Distilled DeepConsensus is 1.3x faster and 1.5x smaller than its larger counterpart while improving the yield of high quality reads (Q30) over the HMM-based method by 1.69x (vs. 1.73x for larger model). With imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09862","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/2211.09862/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":"2026-07-05T05:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pk7vz+w1q5bzteI6T720KHiMSjDlBoHM6EGfUQp8FRl2jnsACI9uEzgddeZq9XqvzLi/x00hjNiwoKkBWuS7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:38:54.052287Z"},"content_sha256":"2a8cb0c5a29a9c28d56def864f5b5d199134dbda434b40bf54b8f1716bd7d41f","schema_version":"1.0","event_id":"sha256:2a8cb0c5a29a9c28d56def864f5b5d199134dbda434b40bf54b8f1716bd7d41f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NPHXEUFAUU6QRXC6776M5MSNXZ/bundle.json","state_url":"https://pith.science/pith/NPHXEUFAUU6QRXC6776M5MSNXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NPHXEUFAUU6QRXC6776M5MSNXZ/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":"2026-07-07T15:38:54Z","links":{"resolver":"https://pith.science/pith/NPHXEUFAUU6QRXC6776M5MSNXZ","bundle":"https://pith.science/pith/NPHXEUFAUU6QRXC6776M5MSNXZ/bundle.json","state":"https://pith.science/pith/NPHXEUFAUU6QRXC6776M5MSNXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NPHXEUFAUU6QRXC6776M5MSNXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NPHXEUFAUU6QRXC6776M5MSNXZ","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":"2e44f6f85263e3f82258fa294eb54d21be43c8d3c311093c5eafe1d4ed123e22","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-11-17T19:54:18Z","title_canon_sha256":"9d9fe730b583b061ac027590db8c4600c55167fe66a48c97a2e63ed16da28462"},"schema_version":"1.0","source":{"id":"2211.09862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09862","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09862v1","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09862","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"NPHXEUFAUU6Q","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"pith_short_16","alias_value":"NPHXEUFAUU6QRXC6","created_at":"2026-07-05T05:17:14Z"},{"alias_kind":"pith_short_8","alias_value":"NPHXEUFA","created_at":"2026-07-05T05:17:14Z"}],"graph_snapshots":[{"event_id":"sha256:2a8cb0c5a29a9c28d56def864f5b5d199134dbda434b40bf54b8f1716bd7d41f","target":"graph","created_at":"2026-07-05T05:17:14Z","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/2211.09862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate genome sequencing can improve our understanding of biology and the genetic basis of disease. The standard approach for generating DNA sequences from PacBio instruments relies on HMM-based models. Here, we introduce Distilled DeepConsensus - a distilled transformer-encoder model for sequence correction, which improves upon the HMM-based methods with runtime constraints in mind. Distilled DeepConsensus is 1.3x faster and 1.5x smaller than its larger counterpart while improving the yield of high quality reads (Q30) over the HMM-based method by 1.69x (vs. 1.73x for larger model). With imp","authors_text":"Aaron M. Wenger, Alexey Kolesnikov, Anastasiya Belyaeva, Andrew Carroll, Armin T\\\"opfer, Cory Y. McLean, Daniel E. Cook, Daniel Liu, Howard Yang, Joel Shor, Kishwar Shafin, Maria Nattestad, Pi-Chuan Chang, William J. Rowell","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-11-17T19:54:18Z","title":"Knowledge distillation for fast and accurate DNA sequence correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09862","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":"sha256:7d93be12cf15c83554089308223f7baf59e44ff911102160dacf6c02ed92e53c","target":"record","created_at":"2026-07-05T05:17:14Z","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":"2e44f6f85263e3f82258fa294eb54d21be43c8d3c311093c5eafe1d4ed123e22","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2022-11-17T19:54:18Z","title_canon_sha256":"9d9fe730b583b061ac027590db8c4600c55167fe66a48c97a2e63ed16da28462"},"schema_version":"1.0","source":{"id":"2211.09862","kind":"arxiv","version":1}},"canonical_sha256":"6bcf7250a0a53d08dc5efffcceb24dbe6143cde94fa905320c9fb9a0224cd4b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6bcf7250a0a53d08dc5efffcceb24dbe6143cde94fa905320c9fb9a0224cd4b6","first_computed_at":"2026-07-05T05:17:14.909142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:14.909142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G9akTqfSmdDeB+QCVqyclUW09SuT3ep01Aads7RzMVqmHltb8ulq0BENlejGa3iZgiJmpbsgkLbRzyfNW2F8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:14.909604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d93be12cf15c83554089308223f7baf59e44ff911102160dacf6c02ed92e53c","sha256:2a8cb0c5a29a9c28d56def864f5b5d199134dbda434b40bf54b8f1716bd7d41f"],"state_sha256":"d46d7035e6d782c32bd427bd1c31bce3c1a218ed607fcf90e8f04d5720e5a191"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"npR7pyRy13mQJ8pQuU2PzRCiKBovFQA7NY7LuoJFebDihtgJ6WXWNgj7yjv4m0+RAVBnAeZaI0i16Js9jzbzDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:38:54.054269Z","bundle_sha256":"594fc6140a5f50e4da4ecbf927bf7d9041a0d01beb00623acde921a9e2d234ef"}}