{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BUE2MKVX7KGN4XCRFA7C55X3DB","short_pith_number":"pith:BUE2MKVX","canonical_record":{"source":{"id":"2605.15110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:27:04Z","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"title_canon_sha256":"bbbbfc0e9e9b3697afb002596557a249f2541ec5c582514ccddde682b5ec4bfd","abstract_canon_sha256":"fa6d1826ba253257cd6cc70167a9ff5f760394c5565e5844c31a6f654783a752"},"schema_version":"1.0"},"canonical_sha256":"0d09a62ab7fa8cde5c51283e2ef6fb185d9a9277828cd32ae26ca3b0626f4d9f","source":{"kind":"arxiv","id":"2605.15110","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15110","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15110v1","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15110","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"BUE2MKVX7KGN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BUE2MKVX7KGN4XCR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BUE2MKVX","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BUE2MKVX7KGN4XCRFA7C55X3DB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:27:04Z","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"title_canon_sha256":"bbbbfc0e9e9b3697afb002596557a249f2541ec5c582514ccddde682b5ec4bfd","abstract_canon_sha256":"fa6d1826ba253257cd6cc70167a9ff5f760394c5565e5844c31a6f654783a752"},"schema_version":"1.0"},"canonical_sha256":"0d09a62ab7fa8cde5c51283e2ef6fb185d9a9277828cd32ae26ca3b0626f4d9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:54.101210Z","signature_b64":"e2jGUYdNp4RbpAeUj1qnheBGvEACyXzv7Zss9gxyYM3cdu8BCOsLwEjtrVrv1eWjzEMLaOFqO+PG8J/90csXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d09a62ab7fa8cde5c51283e2ef6fb185d9a9277828cd32ae26ca3b0626f4d9f","last_reissued_at":"2026-05-17T23:38:54.100546Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:54.100546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15110","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":"2026-05-17T23:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wAtunIgi/IiIZFgEJwM5HqnwDLZq0XzbbqieINTb7jWAklFs6vWUJ/69ccvSF589hrVM3EyaYVoZND8a+UJbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T02:41:15.589977Z"},"content_sha256":"a2a0c792abbdeb0464916b7e74d2dfb6ee8e79bfe7332f933393c61ce4f45ecc","schema_version":"1.0","event_id":"sha256:a2a0c792abbdeb0464916b7e74d2dfb6ee8e79bfe7332f933393c61ce4f45ecc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BUE2MKVX7KGN4XCRFA7C55X3DB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proposal and study of statistical features for string similarity computation and classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"A. Conci, D. Casanova, E. Clua, E.O. Rodrigues, F. Favarim, M. TEIXEIRA, Panos Liatsis, V. Pegorini","submitted_at":"2026-05-14T17:27:04Z","abstract_excerpt":"Adaptations of features commonly applied in the field of visual computing, co-occurrence matrix (COM) and run-length matrix (RLM), are proposed for the similarity computation of strings in general (words, phrases, codes and texts). The proposed features are not sensitive to language related information. These are purely statistical and can be used in any context with any language or grammatical structure. Other statistical measures that are commonly employed in the field such as longest common subsequence, maximal consecutive longest common subsequence, mutual information and edit distances ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15110","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":""},"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":"2026-05-17T23:38:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jt5K9ed5Iun3cuAcuXPAqTNP0+2WEpip3i385EQCXvcvTAVmMFw1jpA3akoMGtZ1rD80p93lhNhdow91wdLZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T02:41:15.590545Z"},"content_sha256":"f5459da2dd59b9374342392732be7a3ab9c4c40879a9444e65beef22c7ceffa0","schema_version":"1.0","event_id":"sha256:f5459da2dd59b9374342392732be7a3ab9c4c40879a9444e65beef22c7ceffa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUE2MKVX7KGN4XCRFA7C55X3DB/bundle.json","state_url":"https://pith.science/pith/BUE2MKVX7KGN4XCRFA7C55X3DB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUE2MKVX7KGN4XCRFA7C55X3DB/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":"2026-06-26T02:41:15Z","links":{"resolver":"https://pith.science/pith/BUE2MKVX7KGN4XCRFA7C55X3DB","bundle":"https://pith.science/pith/BUE2MKVX7KGN4XCRFA7C55X3DB/bundle.json","state":"https://pith.science/pith/BUE2MKVX7KGN4XCRFA7C55X3DB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUE2MKVX7KGN4XCRFA7C55X3DB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BUE2MKVX7KGN4XCRFA7C55X3DB","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":"fa6d1826ba253257cd6cc70167a9ff5f760394c5565e5844c31a6f654783a752","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:27:04Z","title_canon_sha256":"bbbbfc0e9e9b3697afb002596557a249f2541ec5c582514ccddde682b5ec4bfd"},"schema_version":"1.0","source":{"id":"2605.15110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15110","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15110v1","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15110","created_at":"2026-05-17T23:38:54Z"},{"alias_kind":"pith_short_12","alias_value":"BUE2MKVX7KGN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BUE2MKVX7KGN4XCR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BUE2MKVX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:f5459da2dd59b9374342392732be7a3ab9c4c40879a9444e65beef22c7ceffa0","target":"graph","created_at":"2026-05-17T23:38:54Z","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":"Adaptations of features commonly applied in the field of visual computing, co-occurrence matrix (COM) and run-length matrix (RLM), are proposed for the similarity computation of strings in general (words, phrases, codes and texts). The proposed features are not sensitive to language related information. These are purely statistical and can be used in any context with any language or grammatical structure. Other statistical measures that are commonly employed in the field such as longest common subsequence, maximal consecutive longest common subsequence, mutual information and edit distances ar","authors_text":"A. Conci, D. Casanova, E. Clua, E.O. Rodrigues, F. Favarim, M. TEIXEIRA, Panos Liatsis, V. Pegorini","cross_cats":["cs.CL","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:27:04Z","title":"Proposal and study of statistical features for string similarity computation and classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15110","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:a2a0c792abbdeb0464916b7e74d2dfb6ee8e79bfe7332f933393c61ce4f45ecc","target":"record","created_at":"2026-05-17T23:38:54Z","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":"fa6d1826ba253257cd6cc70167a9ff5f760394c5565e5844c31a6f654783a752","cross_cats_sorted":["cs.CL","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:27:04Z","title_canon_sha256":"bbbbfc0e9e9b3697afb002596557a249f2541ec5c582514ccddde682b5ec4bfd"},"schema_version":"1.0","source":{"id":"2605.15110","kind":"arxiv","version":1}},"canonical_sha256":"0d09a62ab7fa8cde5c51283e2ef6fb185d9a9277828cd32ae26ca3b0626f4d9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d09a62ab7fa8cde5c51283e2ef6fb185d9a9277828cd32ae26ca3b0626f4d9f","first_computed_at":"2026-05-17T23:38:54.100546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:54.100546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e2jGUYdNp4RbpAeUj1qnheBGvEACyXzv7Zss9gxyYM3cdu8BCOsLwEjtrVrv1eWjzEMLaOFqO+PG8J/90csXCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:54.101210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2a0c792abbdeb0464916b7e74d2dfb6ee8e79bfe7332f933393c61ce4f45ecc","sha256:f5459da2dd59b9374342392732be7a3ab9c4c40879a9444e65beef22c7ceffa0"],"state_sha256":"72148dc14c755798c7699f873badd174bde16fab2095a40e9ddb6ed7af25e5aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"erPU9MfqswIJPjTPnvCz+ZipoUa69eRc6TbzBKKM4UCK8O+Nk/MB/xSWTyEl8OBpO1fYSsHPSshQfMOWjsSxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T02:41:15.593507Z","bundle_sha256":"1244aff1e919a58df5d0a9e633d9c5ff28cb89c97ca6090a4aee39e757034416"}}