{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SMNR4P5MO4MJ65CXGPKMMCXLPP","short_pith_number":"pith:SMNR4P5M","canonical_record":{"source":{"id":"2101.07117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2021-01-18T15:16:26Z","cross_cats_sorted":[],"title_canon_sha256":"55cfe2a78d3373c7511811110300997729cd8851357a3c2460f37b2801705375","abstract_canon_sha256":"9b29c1138a9e1919b094d22efbf7e101ab1d874e3ac0c9197a900f0d2e4b474e"},"schema_version":"1.0"},"canonical_sha256":"931b1e3fac77189f745733d4c60aeb7bd982c11d6b563013c6e90314506c215d","source":{"kind":"arxiv","id":"2101.07117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.07117","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"arxiv_version","alias_value":"2101.07117v1","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07117","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"pith_short_12","alias_value":"SMNR4P5MO4MJ","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"pith_short_16","alias_value":"SMNR4P5MO4MJ65CX","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"pith_short_8","alias_value":"SMNR4P5M","created_at":"2026-07-05T02:07:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SMNR4P5MO4MJ65CXGPKMMCXLPP","target":"record","payload":{"canonical_record":{"source":{"id":"2101.07117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2021-01-18T15:16:26Z","cross_cats_sorted":[],"title_canon_sha256":"55cfe2a78d3373c7511811110300997729cd8851357a3c2460f37b2801705375","abstract_canon_sha256":"9b29c1138a9e1919b094d22efbf7e101ab1d874e3ac0c9197a900f0d2e4b474e"},"schema_version":"1.0"},"canonical_sha256":"931b1e3fac77189f745733d4c60aeb7bd982c11d6b563013c6e90314506c215d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:40.407986Z","signature_b64":"ihWST7CcXv8KtoOHKgOm6D6bCOFiQ2naU0O1MoqX2MPdOEUPc64kuPl9XVbxoy5zEm9cOp6DjRlEhTzGHIiVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"931b1e3fac77189f745733d4c60aeb7bd982c11d6b563013c6e90314506c215d","last_reissued_at":"2026-07-05T02:07:40.407600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:40.407600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.07117","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":"2026-07-05T02:07:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DqGQVBDvXfuknTyROt3RwNRwAYTbwKODI2qwCccaHXxigDg1hF7OtBYUSFhAkRvsntFTFh3MfPKrq4FuYLW6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:38:23.200492Z"},"content_sha256":"9789359325188277a1f0729b0fdbaea3cfb9d4de207c61583502ea005f6ac110","schema_version":"1.0","event_id":"sha256:9789359325188277a1f0729b0fdbaea3cfb9d4de207c61583502ea005f6ac110"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SMNR4P5MO4MJ65CXGPKMMCXLPP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPRISS: Approximating Frequent $k$-mers by Sampling Reads, and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Diego Santoro, Fabio Vandin, Leonardo Pellegrina","submitted_at":"2021-01-18T15:16:26Z","abstract_excerpt":"The extraction of $k$-mers is a fundamental component in many complex analyses of large next-generation sequencing datasets, including reads classification in genomics and the characterization of RNA-seq datasets. The extraction of all $k$-mers and their frequencies is extremely demanding in terms of running time and memory, owing to the size of the data and to the exponential number of $k$-mers to be considered. However, in several applications, only frequent $k$-mers, which are $k$-mers appearing in a relatively high proportion of the data, are required by the analysis. In this work we prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07117","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/2101.07117/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":"2026-07-05T02:07:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ZP778cSL+MS1nQv+6xfK7mdOuUL9AQtOcD6Ujs/v0a6V20ruWb2CMSEvyQ0Yh4v3kPbazlrC5krISpm8lzOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:38:23.201396Z"},"content_sha256":"c7187b9b5a7d5135f2e0062dab676b2489c3b82ee40493a59a3c37aa95e12be4","schema_version":"1.0","event_id":"sha256:c7187b9b5a7d5135f2e0062dab676b2489c3b82ee40493a59a3c37aa95e12be4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMNR4P5MO4MJ65CXGPKMMCXLPP/bundle.json","state_url":"https://pith.science/pith/SMNR4P5MO4MJ65CXGPKMMCXLPP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMNR4P5MO4MJ65CXGPKMMCXLPP/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":"2026-08-03T15:38:23Z","links":{"resolver":"https://pith.science/pith/SMNR4P5MO4MJ65CXGPKMMCXLPP","bundle":"https://pith.science/pith/SMNR4P5MO4MJ65CXGPKMMCXLPP/bundle.json","state":"https://pith.science/pith/SMNR4P5MO4MJ65CXGPKMMCXLPP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMNR4P5MO4MJ65CXGPKMMCXLPP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SMNR4P5MO4MJ65CXGPKMMCXLPP","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":"9b29c1138a9e1919b094d22efbf7e101ab1d874e3ac0c9197a900f0d2e4b474e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2021-01-18T15:16:26Z","title_canon_sha256":"55cfe2a78d3373c7511811110300997729cd8851357a3c2460f37b2801705375"},"schema_version":"1.0","source":{"id":"2101.07117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.07117","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"arxiv_version","alias_value":"2101.07117v1","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07117","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"pith_short_12","alias_value":"SMNR4P5MO4MJ","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"pith_short_16","alias_value":"SMNR4P5MO4MJ65CX","created_at":"2026-07-05T02:07:40Z"},{"alias_kind":"pith_short_8","alias_value":"SMNR4P5M","created_at":"2026-07-05T02:07:40Z"}],"graph_snapshots":[{"event_id":"sha256:c7187b9b5a7d5135f2e0062dab676b2489c3b82ee40493a59a3c37aa95e12be4","target":"graph","created_at":"2026-07-05T02:07:40Z","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/2101.07117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The extraction of $k$-mers is a fundamental component in many complex analyses of large next-generation sequencing datasets, including reads classification in genomics and the characterization of RNA-seq datasets. The extraction of all $k$-mers and their frequencies is extremely demanding in terms of running time and memory, owing to the size of the data and to the exponential number of $k$-mers to be considered. However, in several applications, only frequent $k$-mers, which are $k$-mers appearing in a relatively high proportion of the data, are required by the analysis. In this work we prese","authors_text":"Diego Santoro, Fabio Vandin, Leonardo Pellegrina","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2021-01-18T15:16:26Z","title":"SPRISS: Approximating Frequent $k$-mers by Sampling Reads, and Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07117","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":"sha256:9789359325188277a1f0729b0fdbaea3cfb9d4de207c61583502ea005f6ac110","target":"record","created_at":"2026-07-05T02:07:40Z","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":"9b29c1138a9e1919b094d22efbf7e101ab1d874e3ac0c9197a900f0d2e4b474e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2021-01-18T15:16:26Z","title_canon_sha256":"55cfe2a78d3373c7511811110300997729cd8851357a3c2460f37b2801705375"},"schema_version":"1.0","source":{"id":"2101.07117","kind":"arxiv","version":1}},"canonical_sha256":"931b1e3fac77189f745733d4c60aeb7bd982c11d6b563013c6e90314506c215d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"931b1e3fac77189f745733d4c60aeb7bd982c11d6b563013c6e90314506c215d","first_computed_at":"2026-07-05T02:07:40.407600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:07:40.407600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ihWST7CcXv8KtoOHKgOm6D6bCOFiQ2naU0O1MoqX2MPdOEUPc64kuPl9XVbxoy5zEm9cOp6DjRlEhTzGHIiVAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:07:40.407986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.07117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9789359325188277a1f0729b0fdbaea3cfb9d4de207c61583502ea005f6ac110","sha256:c7187b9b5a7d5135f2e0062dab676b2489c3b82ee40493a59a3c37aa95e12be4"],"state_sha256":"b57a6aecd1b358ca07658eef65289c1405f495da07b9204930f8fb727a097bc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29yOj67XcgMrHBAvKzb62ZzH+wmBO1pIPrHRZOVEWaPOVzk2teJl191mJhEDm16mHgyhI2ZYEDkPpqoXH+7gAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:38:23.208159Z","bundle_sha256":"f04a0a2a87d735dcc2c411663987a9a7d56c7d550521729f176f82fbcecb387c"}}