{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UAS47XOBEXJNBG3TJUN4P43UVB","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":"2f53c70b4098df0d165d9918f418b17b64657eb3639c1e2e82d946bc95426e4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2026-05-17T18:01:33Z","title_canon_sha256":"73a176f929982a17643e19e806d90b5a899b4906bd363130a292aae25b4ae9f3"},"schema_version":"1.0","source":{"id":"2605.17574","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17574","created_at":"2026-05-20T00:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17574v1","created_at":"2026-05-20T00:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17574","created_at":"2026-05-20T00:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"UAS47XOBEXJN","created_at":"2026-05-20T00:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"UAS47XOBEXJNBG3T","created_at":"2026-05-20T00:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"UAS47XOB","created_at":"2026-05-20T00:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:9f738a34c0dccac6fc2cebb7a6403b85adc978a91f95f1c74f877bfdbdce1910","target":"graph","created_at":"2026-05-20T00:04:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We show how to use parse indexing to choose pseudo-MEMs to eliminate this risk, with the added benefit that we need not choose k."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the properties of an existing parse index on the text are sufficient to identify a set of pseudo-MEMs that is guaranteed to contain every MEM of length at least k without introducing new parameters or post-hoc filters."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The paper shows how parse indexing can select pseudo-MEMs that contain every MEM of length at least k while eliminating the need to choose k and the risk of discarding important matches."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Parse indexing selects pseudo-MEMs guaranteed to contain every long MEM without picking k."}],"snapshot_sha256":"1ff545324ad907884ee022461cb3ee31493cfd0bd7f422791a909c93598844bb"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"89ba0ce410713d8e5bf339ce633f7c222804cde1ffb01fb39258a4e622aa6576"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.564987Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:12:21.011885Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.592787Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.523849Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17574/integrity.json","findings":[],"snapshot_sha256":"e86ff0fedb5e0e330d4ef368e33eec0f8be4bdad0d79c9c4ce3e3708867d6e01","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Brown et al.\\ (2025) recently proposed a pre-processing step, called $k$-mer based breaking (KeBaB), to speed up searches for long maximal exact matches (MEMs) between patterns and an indexed repetitive text. They fix a parameter $k$ and build a Bloom filter for the distinct $k$-mers in the text. When given a pattern, they quickly separate the $k$-mers in it into those that probably occur in the text and those that certainly do not. They call the maximal substrings of the pattern consisting only of the former $k$-mers {\\em pseudo-MEMs}. These pseudo-MEMs are guaranteed to contain all the MEMs ","authors_text":"Travis Gagie","cross_cats":[],"headline":"Parse indexing selects pseudo-MEMs guaranteed to contain every long MEM without picking k.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2026-05-17T18:01:33Z","title":"Parse indexing for choosing pseudo-MEMs"},"references":{"count":16,"internal_anchors":1,"resolved_work":16,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"KeBaB: k-mer based breaking for finding long MEMs","work_id":"ca78d1ed-b7bc-4381-a54c-311fc0602773","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Faster run-length compressed suffix arrays","work_id":"0fef654e-4f95-4cc9-a557-c8ed6175a2a1","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Fast and small subsampled r-indexes","work_id":"97efe6e6-8e13-43c4-a050-0a21648e9046","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"FM-indexing gram- mars induced by suffix sorting for long patterns","work_id":"22d3b93c-fa34-4d73-be24-d88704f07a9e","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Summary cache: a scalable wide-area web cache sharing protocol.IEEE/ACM Transactions on Networking, 8, 2000","work_id":"82672f92-ae7e-489c-9c36-316d018c0052","year":2000}],"snapshot_sha256":"83fcd1b1b53d3765eb3c365746c74309dcbe873e2604fb0d34ae5b35aeccd35f"},"source":{"id":"2605.17574","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T22:01:57.223425Z","id":"2a700a06-80a6-4189-a363-cf35a47ad8f0","model_set":{"reader":"grok-4.3"},"one_line_summary":"The paper shows how parse indexing can select pseudo-MEMs that contain every MEM of length at least k while eliminating the need to choose k and the risk of discarding important matches.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Parse indexing selects pseudo-MEMs guaranteed to contain every long MEM without picking k.","strongest_claim":"We show how to use parse indexing to choose pseudo-MEMs to eliminate this risk, with the added benefit that we need not choose k.","weakest_assumption":"That the properties of an existing parse index on the text are sufficient to identify a set of pseudo-MEMs that is guaranteed to contain every MEM of length at least k without introducing new parameters or post-hoc filters."}},"verdict_id":"2a700a06-80a6-4189-a363-cf35a47ad8f0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd772bccaafd572fa4bb97e0cc75325b336ef1837f6b45698936805d583c749a","target":"record","created_at":"2026-05-20T00:04:46Z","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":"2f53c70b4098df0d165d9918f418b17b64657eb3639c1e2e82d946bc95426e4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2026-05-17T18:01:33Z","title_canon_sha256":"73a176f929982a17643e19e806d90b5a899b4906bd363130a292aae25b4ae9f3"},"schema_version":"1.0","source":{"id":"2605.17574","kind":"arxiv","version":1}},"canonical_sha256":"a025cfddc125d2d09b734d1bc7f374a84391224420e7b0aebde9e6d7b9f6576c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a025cfddc125d2d09b734d1bc7f374a84391224420e7b0aebde9e6d7b9f6576c","first_computed_at":"2026-05-20T00:04:46.656929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:46.656929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FUMCwJddvWA0ejCadMqlMbi05eH2ZM65dqOfv/f3xZFx8gQQLf+knYYu/dNVoCLbCw0gTJvv+597yX34OchIDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:46.657825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17574","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd772bccaafd572fa4bb97e0cc75325b336ef1837f6b45698936805d583c749a","sha256:9f738a34c0dccac6fc2cebb7a6403b85adc978a91f95f1c74f877bfdbdce1910"],"state_sha256":"f94355ce128ff0f49f7fc6923a19212ec62d0f166a428aa3960d5cf347da4437"}