{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:SFM5HRVIHYBU3SNQX2V53N5P3L","short_pith_number":"pith:SFM5HRVI","canonical_record":{"source":{"id":"1405.6874","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-05-27T11:34:35Z","cross_cats_sorted":[],"title_canon_sha256":"7ed2e7c2fae01c4c43d09d6f06c7e0080d2d66fdd36abcf3e548562ad8999b79","abstract_canon_sha256":"b6606cf6b667a79d5980dad08f999246744ce5f33d79870700d3f20c33bd2639"},"schema_version":"1.0"},"canonical_sha256":"9159d3c6a83e034dc9b0beabddb7afdae6775c160eaf9fe4277dde4fb2eec481","source":{"kind":"arxiv","id":"1405.6874","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.6874","created_at":"2026-05-18T02:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"1405.6874v2","created_at":"2026-05-18T02:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.6874","created_at":"2026-05-18T02:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"SFM5HRVIHYBU","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"SFM5HRVIHYBU3SNQ","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"SFM5HRVI","created_at":"2026-05-18T12:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:SFM5HRVIHYBU3SNQX2V53N5P3L","target":"record","payload":{"canonical_record":{"source":{"id":"1405.6874","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-05-27T11:34:35Z","cross_cats_sorted":[],"title_canon_sha256":"7ed2e7c2fae01c4c43d09d6f06c7e0080d2d66fdd36abcf3e548562ad8999b79","abstract_canon_sha256":"b6606cf6b667a79d5980dad08f999246744ce5f33d79870700d3f20c33bd2639"},"schema_version":"1.0"},"canonical_sha256":"9159d3c6a83e034dc9b0beabddb7afdae6775c160eaf9fe4277dde4fb2eec481","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:42:36.947843Z","signature_b64":"nhJT2qJ19pxqtjZwlXeQZYLVmR6+S575oGflisCxBHK30YdQMKPvv4kseUiFTdQS4Xo/9bqVEf+9ldLvucotBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9159d3c6a83e034dc9b0beabddb7afdae6775c160eaf9fe4277dde4fb2eec481","last_reissued_at":"2026-05-18T02:42:36.947086Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:42:36.947086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1405.6874","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":"2026-05-18T02:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M3cJzNOjIktgNyHduyrlqHYIJdGNGOfcKaWiE56jlx1qTHFIr3yFNlH+IO+Pnte3Xabysp/JcHd7UHiu8jCPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T13:11:27.384626Z"},"content_sha256":"93cdfddde88888bc1e1a6f43772efddd003b87cdce40a1ce77deaf3918dd8268","schema_version":"1.0","event_id":"sha256:93cdfddde88888bc1e1a6f43772efddd003b87cdce40a1ce77deaf3918dd8268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:SFM5HRVIHYBU3SNQX2V53N5P3L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disk-based genome sequencing data compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"{\\L}ukasz Roguski, Sebastian Deorowicz, Szymon Grabowski","submitted_at":"2014-05-27T11:34:35Z","abstract_excerpt":"Motivation: High-coverage sequencing data have significant, yet hard to exploit, redundancy. Most FASTQ compressors cannot efficiently compress the DNA stream of large datasets, since the redundancy between overlapping reads cannot be easily captured in the (relatively small) main memory. More interesting solutions for this problem are disk-based~(Yanovsky, 2011; Cox et al., 2012), where the better of these two, from Cox~{\\it et al.}~(2012), is based on the Burrows--Wheeler transform (BWT) and achieves 0.518 bits per base for a 134.0 Gb human genome sequencing collection with almost 45-fold co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.6874","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":"2026-05-18T02:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j4PE7e4U9ln4ZnWsZRFjYBhpA/aBPAtQmW0hVCPQd4bq+gYBwmQEJaVSUEOCv9eyR6E8oS2o3aREnnsvq2aqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T13:11:27.384979Z"},"content_sha256":"b7491fa238dee649a3fe1cace404f7bf2cdc5959ce6a62ced04e40e3e226ba92","schema_version":"1.0","event_id":"sha256:b7491fa238dee649a3fe1cace404f7bf2cdc5959ce6a62ced04e40e3e226ba92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SFM5HRVIHYBU3SNQX2V53N5P3L/bundle.json","state_url":"https://pith.science/pith/SFM5HRVIHYBU3SNQX2V53N5P3L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SFM5HRVIHYBU3SNQX2V53N5P3L/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":"2026-06-09T13:11:27Z","links":{"resolver":"https://pith.science/pith/SFM5HRVIHYBU3SNQX2V53N5P3L","bundle":"https://pith.science/pith/SFM5HRVIHYBU3SNQX2V53N5P3L/bundle.json","state":"https://pith.science/pith/SFM5HRVIHYBU3SNQX2V53N5P3L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SFM5HRVIHYBU3SNQX2V53N5P3L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:SFM5HRVIHYBU3SNQX2V53N5P3L","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":"b6606cf6b667a79d5980dad08f999246744ce5f33d79870700d3f20c33bd2639","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-05-27T11:34:35Z","title_canon_sha256":"7ed2e7c2fae01c4c43d09d6f06c7e0080d2d66fdd36abcf3e548562ad8999b79"},"schema_version":"1.0","source":{"id":"1405.6874","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.6874","created_at":"2026-05-18T02:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"1405.6874v2","created_at":"2026-05-18T02:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.6874","created_at":"2026-05-18T02:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"SFM5HRVIHYBU","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"SFM5HRVIHYBU3SNQ","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"SFM5HRVI","created_at":"2026-05-18T12:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:b7491fa238dee649a3fe1cace404f7bf2cdc5959ce6a62ced04e40e3e226ba92","target":"graph","created_at":"2026-05-18T02:42:36Z","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":"Motivation: High-coverage sequencing data have significant, yet hard to exploit, redundancy. Most FASTQ compressors cannot efficiently compress the DNA stream of large datasets, since the redundancy between overlapping reads cannot be easily captured in the (relatively small) main memory. More interesting solutions for this problem are disk-based~(Yanovsky, 2011; Cox et al., 2012), where the better of these two, from Cox~{\\it et al.}~(2012), is based on the Burrows--Wheeler transform (BWT) and achieves 0.518 bits per base for a 134.0 Gb human genome sequencing collection with almost 45-fold co","authors_text":"{\\L}ukasz Roguski, Sebastian Deorowicz, Szymon Grabowski","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-05-27T11:34:35Z","title":"Disk-based genome sequencing data compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.6874","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":"sha256:93cdfddde88888bc1e1a6f43772efddd003b87cdce40a1ce77deaf3918dd8268","target":"record","created_at":"2026-05-18T02:42:36Z","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":"b6606cf6b667a79d5980dad08f999246744ce5f33d79870700d3f20c33bd2639","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2014-05-27T11:34:35Z","title_canon_sha256":"7ed2e7c2fae01c4c43d09d6f06c7e0080d2d66fdd36abcf3e548562ad8999b79"},"schema_version":"1.0","source":{"id":"1405.6874","kind":"arxiv","version":2}},"canonical_sha256":"9159d3c6a83e034dc9b0beabddb7afdae6775c160eaf9fe4277dde4fb2eec481","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9159d3c6a83e034dc9b0beabddb7afdae6775c160eaf9fe4277dde4fb2eec481","first_computed_at":"2026-05-18T02:42:36.947086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:42:36.947086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nhJT2qJ19pxqtjZwlXeQZYLVmR6+S575oGflisCxBHK30YdQMKPvv4kseUiFTdQS4Xo/9bqVEf+9ldLvucotBg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:42:36.947843Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.6874","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93cdfddde88888bc1e1a6f43772efddd003b87cdce40a1ce77deaf3918dd8268","sha256:b7491fa238dee649a3fe1cace404f7bf2cdc5959ce6a62ced04e40e3e226ba92"],"state_sha256":"8f4107398eaa1ca9e3f6c2dbaece493031ed5d3e09a3d167398d72d7a5d25a6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HrqPgfzw//M0u2DcLiN6RqxTEYMl5xhDPEs1gTK8RsI8xskwqLEabqNjwZD2yae8oYYzvsiwuc2vOSXJV815CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T13:11:27.386987Z","bundle_sha256":"828641ec8987b7ce2241e0aab52725c219b1e12bfa40b5542a55b159fbb66aa8"}}