{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:N5YYGRJ5LBSRJYW7SVRASSOCA5","short_pith_number":"pith:N5YYGRJ5","canonical_record":{"source":{"id":"2009.14467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2020-09-30T06:31:41Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"25eb3c8f9be1cc4d92daeeb89c4b0fca4e1a618cb46e65458b33bec1b48882b8","abstract_canon_sha256":"2e613dc73bc478a187626c890bc90bf4f338bd64e050e31a0bcd201a18175fce"},"schema_version":"1.0"},"canonical_sha256":"6f7183453d586514e2df95620949c20760ed1387acbeba190863184ff60f4ff1","source":{"kind":"arxiv","id":"2009.14467","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.14467","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2009.14467v1","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14467","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"N5YYGRJ5LBSR","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"pith_short_16","alias_value":"N5YYGRJ5LBSRJYW7","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"pith_short_8","alias_value":"N5YYGRJ5","created_at":"2026-07-05T01:39:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:N5YYGRJ5LBSRJYW7SVRASSOCA5","target":"record","payload":{"canonical_record":{"source":{"id":"2009.14467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2020-09-30T06:31:41Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"25eb3c8f9be1cc4d92daeeb89c4b0fca4e1a618cb46e65458b33bec1b48882b8","abstract_canon_sha256":"2e613dc73bc478a187626c890bc90bf4f338bd64e050e31a0bcd201a18175fce"},"schema_version":"1.0"},"canonical_sha256":"6f7183453d586514e2df95620949c20760ed1387acbeba190863184ff60f4ff1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:19.780383Z","signature_b64":"XR4FPP5dKDv7YjN+RmFjT3pF38UBAsu+CeTfaLVdxFQDZzETZqx+Kn/pxmhi05uwBbgnKtN7LHB5gQnK4hhJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f7183453d586514e2df95620949c20760ed1387acbeba190863184ff60f4ff1","last_reissued_at":"2026-07-05T01:39:19.779908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:19.779908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.14467","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":"2026-07-05T01:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlFod7N7KZcpr7z31dhfxez/BsS1QuEBZe9G8DXGrh52V0pTafWGnm7u672CElxLRZBRb7iKq3s9sO+Ogb1ECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:05:25.085008Z"},"content_sha256":"06e16ee4525b6d463b0f24c5f6881a2d9d66b7d1e88413c16426346a5ea95d96","schema_version":"1.0","event_id":"sha256:06e16ee4525b6d463b0f24c5f6881a2d9d66b7d1e88413c16426346a5ea95d96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:N5YYGRJ5LBSRJYW7SVRASSOCA5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributed Many-to-Many Protein Sequence Alignment using Sparse Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.DC","authors_text":"Ariful Azad, Aydin Buluc, Georgios Pavlopoulos, Giulia Guidi, Oguz Selvitopi, Saliya Ekanayake","submitted_at":"2020-09-30T06:31:41Z","abstract_excerpt":"Identifying similar protein sequences is a core step in many computational biology pipelines such as detection of homologous protein sequences, generation of similarity protein graphs for downstream analysis, functional annotation and gene location. Performance and scalability of protein similarity searches have proven to be a bottleneck in many bioinformatics pipelines due to increases in cheap and abundant sequencing data. This work presents a new distributed-memory software, PASTIS. PASTIS relies on sparse matrix computations for efficient identification of possibly similar proteins. We use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14467","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/2009.14467/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":"2026-07-05T01:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vyNDQvfyeawCyheT8F4FLB7PvibAoktJhyzXarTp0P6Ez7x4twYpSJ85gqta3BoKbOI5BJV//ycvOBSpHM7dAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:05:25.085395Z"},"content_sha256":"0b82df290037a06eade6a09830d271591d2108b7968709fe01102150ef7b6f13","schema_version":"1.0","event_id":"sha256:0b82df290037a06eade6a09830d271591d2108b7968709fe01102150ef7b6f13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5YYGRJ5LBSRJYW7SVRASSOCA5/bundle.json","state_url":"https://pith.science/pith/N5YYGRJ5LBSRJYW7SVRASSOCA5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5YYGRJ5LBSRJYW7SVRASSOCA5/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":"2026-07-07T09:05:25Z","links":{"resolver":"https://pith.science/pith/N5YYGRJ5LBSRJYW7SVRASSOCA5","bundle":"https://pith.science/pith/N5YYGRJ5LBSRJYW7SVRASSOCA5/bundle.json","state":"https://pith.science/pith/N5YYGRJ5LBSRJYW7SVRASSOCA5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5YYGRJ5LBSRJYW7SVRASSOCA5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N5YYGRJ5LBSRJYW7SVRASSOCA5","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":"2e613dc73bc478a187626c890bc90bf4f338bd64e050e31a0bcd201a18175fce","cross_cats_sorted":["q-bio.GN"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2020-09-30T06:31:41Z","title_canon_sha256":"25eb3c8f9be1cc4d92daeeb89c4b0fca4e1a618cb46e65458b33bec1b48882b8"},"schema_version":"1.0","source":{"id":"2009.14467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.14467","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2009.14467v1","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14467","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"N5YYGRJ5LBSR","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"pith_short_16","alias_value":"N5YYGRJ5LBSRJYW7","created_at":"2026-07-05T01:39:19Z"},{"alias_kind":"pith_short_8","alias_value":"N5YYGRJ5","created_at":"2026-07-05T01:39:19Z"}],"graph_snapshots":[{"event_id":"sha256:0b82df290037a06eade6a09830d271591d2108b7968709fe01102150ef7b6f13","target":"graph","created_at":"2026-07-05T01:39:19Z","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/2009.14467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying similar protein sequences is a core step in many computational biology pipelines such as detection of homologous protein sequences, generation of similarity protein graphs for downstream analysis, functional annotation and gene location. Performance and scalability of protein similarity searches have proven to be a bottleneck in many bioinformatics pipelines due to increases in cheap and abundant sequencing data. This work presents a new distributed-memory software, PASTIS. PASTIS relies on sparse matrix computations for efficient identification of possibly similar proteins. We use","authors_text":"Ariful Azad, Aydin Buluc, Georgios Pavlopoulos, Giulia Guidi, Oguz Selvitopi, Saliya Ekanayake","cross_cats":["q-bio.GN"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2020-09-30T06:31:41Z","title":"Distributed Many-to-Many Protein Sequence Alignment using Sparse Matrices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14467","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":"sha256:06e16ee4525b6d463b0f24c5f6881a2d9d66b7d1e88413c16426346a5ea95d96","target":"record","created_at":"2026-07-05T01:39:19Z","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":"2e613dc73bc478a187626c890bc90bf4f338bd64e050e31a0bcd201a18175fce","cross_cats_sorted":["q-bio.GN"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2020-09-30T06:31:41Z","title_canon_sha256":"25eb3c8f9be1cc4d92daeeb89c4b0fca4e1a618cb46e65458b33bec1b48882b8"},"schema_version":"1.0","source":{"id":"2009.14467","kind":"arxiv","version":1}},"canonical_sha256":"6f7183453d586514e2df95620949c20760ed1387acbeba190863184ff60f4ff1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f7183453d586514e2df95620949c20760ed1387acbeba190863184ff60f4ff1","first_computed_at":"2026-07-05T01:39:19.779908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:19.779908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XR4FPP5dKDv7YjN+RmFjT3pF38UBAsu+CeTfaLVdxFQDZzETZqx+Kn/pxmhi05uwBbgnKtN7LHB5gQnK4hhJBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:19.780383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.14467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06e16ee4525b6d463b0f24c5f6881a2d9d66b7d1e88413c16426346a5ea95d96","sha256:0b82df290037a06eade6a09830d271591d2108b7968709fe01102150ef7b6f13"],"state_sha256":"17b272b1f788380688d026a51942849ff751449729abdfd55cc8a33229740778"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ki825d2OPnZl16SUIpgvZeoCwuQ/M5tZQaoMFhtu3+jS2ueq84IAfOQ5/xPkH9NfMBh7kYWpf8YnR+yJSixRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:05:25.087231Z","bundle_sha256":"665214e49bee2a4ca96f1ce742197f487f68483f88cb6d9c08286379bfb380ff"}}