{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PXL72CDF2H5F2TJT5PZPMKLGSB","short_pith_number":"pith:PXL72CDF","canonical_record":{"source":{"id":"2401.01786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2024-01-03T15:27:10Z","cross_cats_sorted":["math.IT","q-bio.GN"],"title_canon_sha256":"976478b8c6cef17a0cf5287e1c112110f388a564066ec41ab498847dcfccfbcb","abstract_canon_sha256":"875d4222b1c3244a8b7d73c70e5ec6cdf601870848882606fc543b0c102a66bd"},"schema_version":"1.0"},"canonical_sha256":"7dd7fd0865d1fa5d4d33ebf2f62966904c538dd32ba760a8cb63a41112b0c92f","source":{"kind":"arxiv","id":"2401.01786","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01786","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01786v1","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01786","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"pith_short_12","alias_value":"PXL72CDF2H5F","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"pith_short_16","alias_value":"PXL72CDF2H5F2TJT","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"pith_short_8","alias_value":"PXL72CDF","created_at":"2026-07-05T07:29:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PXL72CDF2H5F2TJT5PZPMKLGSB","target":"record","payload":{"canonical_record":{"source":{"id":"2401.01786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2024-01-03T15:27:10Z","cross_cats_sorted":["math.IT","q-bio.GN"],"title_canon_sha256":"976478b8c6cef17a0cf5287e1c112110f388a564066ec41ab498847dcfccfbcb","abstract_canon_sha256":"875d4222b1c3244a8b7d73c70e5ec6cdf601870848882606fc543b0c102a66bd"},"schema_version":"1.0"},"canonical_sha256":"7dd7fd0865d1fa5d4d33ebf2f62966904c538dd32ba760a8cb63a41112b0c92f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:57.210643Z","signature_b64":"IN85gfZWMqXCzipskLsGhjc+8EQOofjEWoTKIionmwY9av68IHtigA5Zr1GcsiR9LtRHmkPCjFoj24yo3PIAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dd7fd0865d1fa5d4d33ebf2f62966904c538dd32ba760a8cb63a41112b0c92f","last_reissued_at":"2026-07-05T07:29:57.210267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:57.210267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.01786","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":"2026-07-05T07:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pf97IM/eb1CP0EiMmLPGhHuktnAYnNrlOCj4ljG4jnJ1dEEX91vzl6VRSXXEY7A2neXLzH3Z2rj/ZKQ9rpBTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:04:35.937161Z"},"content_sha256":"bb6a1d7ea775149db92c1ff11c2929513362f7116de44d0d083dc5fde2866d73","schema_version":"1.0","event_id":"sha256:bb6a1d7ea775149db92c1ff11c2929513362f7116de44d0d083dc5fde2866d73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PXL72CDF2H5F2TJT5PZPMKLGSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An experimental sorting method for improving metagenomic data encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.IT","q-bio.GN"],"primary_cat":"cs.IT","authors_text":"Armando J. Pinho, Diogo Pratas","submitted_at":"2024-01-03T15:27:10Z","abstract_excerpt":"Minimizing data storage poses a significant challenge in large-scale metagenomic projects. In this paper, we present a new method for improving the encoding of FASTQ files generated by metagenomic sequencing. This method incorporates metagenomic classification followed by a recursive filter for clustering reads by DNA sequence similarity to improve the overall reference-free compression. In the results, we show an overall improvement in the compression of several datasets. As hypothesized, we show a progressive compression gain for higher coverage depth and number of identified species. Additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01786","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/2401.01786/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":"2026-07-05T07:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhl+cBLGTw6nEEzWsj+fRKfPBJwH9FRIK/xA6lNMnM5ukVBvp4tXzxahTifeI+JrlVWVYA3j90hM1sqKkkTECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:04:35.937688Z"},"content_sha256":"b22fc0e749aea01b0e82a5778bb30a2f5f256f2e5dc1ef141e0f314b26d62a6c","schema_version":"1.0","event_id":"sha256:b22fc0e749aea01b0e82a5778bb30a2f5f256f2e5dc1ef141e0f314b26d62a6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/bundle.json","state_url":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/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":"2026-08-19T05:04:35Z","links":{"resolver":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB","bundle":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/bundle.json","state":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PXL72CDF2H5F2TJT5PZPMKLGSB","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":"875d4222b1c3244a8b7d73c70e5ec6cdf601870848882606fc543b0c102a66bd","cross_cats_sorted":["math.IT","q-bio.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2024-01-03T15:27:10Z","title_canon_sha256":"976478b8c6cef17a0cf5287e1c112110f388a564066ec41ab498847dcfccfbcb"},"schema_version":"1.0","source":{"id":"2401.01786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01786","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01786v1","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01786","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"pith_short_12","alias_value":"PXL72CDF2H5F","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"pith_short_16","alias_value":"PXL72CDF2H5F2TJT","created_at":"2026-07-05T07:29:57Z"},{"alias_kind":"pith_short_8","alias_value":"PXL72CDF","created_at":"2026-07-05T07:29:57Z"}],"graph_snapshots":[{"event_id":"sha256:b22fc0e749aea01b0e82a5778bb30a2f5f256f2e5dc1ef141e0f314b26d62a6c","target":"graph","created_at":"2026-07-05T07:29:57Z","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/2401.01786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Minimizing data storage poses a significant challenge in large-scale metagenomic projects. In this paper, we present a new method for improving the encoding of FASTQ files generated by metagenomic sequencing. This method incorporates metagenomic classification followed by a recursive filter for clustering reads by DNA sequence similarity to improve the overall reference-free compression. In the results, we show an overall improvement in the compression of several datasets. As hypothesized, we show a progressive compression gain for higher coverage depth and number of identified species. Additi","authors_text":"Armando J. Pinho, Diogo Pratas","cross_cats":["math.IT","q-bio.GN"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2024-01-03T15:27:10Z","title":"An experimental sorting method for improving metagenomic data encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01786","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:bb6a1d7ea775149db92c1ff11c2929513362f7116de44d0d083dc5fde2866d73","target":"record","created_at":"2026-07-05T07:29:57Z","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":"875d4222b1c3244a8b7d73c70e5ec6cdf601870848882606fc543b0c102a66bd","cross_cats_sorted":["math.IT","q-bio.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2024-01-03T15:27:10Z","title_canon_sha256":"976478b8c6cef17a0cf5287e1c112110f388a564066ec41ab498847dcfccfbcb"},"schema_version":"1.0","source":{"id":"2401.01786","kind":"arxiv","version":1}},"canonical_sha256":"7dd7fd0865d1fa5d4d33ebf2f62966904c538dd32ba760a8cb63a41112b0c92f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dd7fd0865d1fa5d4d33ebf2f62966904c538dd32ba760a8cb63a41112b0c92f","first_computed_at":"2026-07-05T07:29:57.210267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:57.210267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IN85gfZWMqXCzipskLsGhjc+8EQOofjEWoTKIionmwY9av68IHtigA5Zr1GcsiR9LtRHmkPCjFoj24yo3PIAAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:57.210643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb6a1d7ea775149db92c1ff11c2929513362f7116de44d0d083dc5fde2866d73","sha256:b22fc0e749aea01b0e82a5778bb30a2f5f256f2e5dc1ef141e0f314b26d62a6c"],"state_sha256":"a5b1a0eb08cf284aafd38ff707fae8d2c6eb57938d07a5c4e122f1cb3ca28b7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nN/hTJlpdEeeKL3SxiUSBw2h/fYP1Zg0dG4VhiC4uVRSK1cDuNZfiFp8Yb+rpx8Ny4dHlPpjyUekGvz6jeaTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:04:35.943241Z","bundle_sha256":"588b965c655059206e019ab543438731f5896d3b30130945cf3a6252ec13e116"}}