{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:53LTHGWGCAERV4OIXSG3OIRWHA","short_pith_number":"pith:53LTHGWG","canonical_record":{"source":{"id":"1508.03772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-08-15T22:12:22Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"45794db1a19e3dbee5248dc19ad17cc31137d8639719c510a4af99871cd172a8","abstract_canon_sha256":"214d7d72a9307ac3d3d8d4b73129cbb25deec5be5f9cbadff5537d3345e91eed"},"schema_version":"1.0"},"canonical_sha256":"eed7339ac610091af1c8bc8db7223638126fef9cb4710e1259504e0a0d0ad234","source":{"kind":"arxiv","id":"1508.03772","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.03772","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"1508.03772v1","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03772","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"53LTHGWGCAER","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"53LTHGWGCAERV4OI","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"53LTHGWG","created_at":"2026-05-18T12:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:53LTHGWGCAERV4OIXSG3OIRWHA","target":"record","payload":{"canonical_record":{"source":{"id":"1508.03772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-08-15T22:12:22Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"45794db1a19e3dbee5248dc19ad17cc31137d8639719c510a4af99871cd172a8","abstract_canon_sha256":"214d7d72a9307ac3d3d8d4b73129cbb25deec5be5f9cbadff5537d3345e91eed"},"schema_version":"1.0"},"canonical_sha256":"eed7339ac610091af1c8bc8db7223638126fef9cb4710e1259504e0a0d0ad234","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:15.265258Z","signature_b64":"2FXD0k8tFYEtclihSYX6KqExw3ipRvtB0YejIItLlhAOYyOqgIewsdiD8s81+kri1BdQkV4hzafCwGetvKMbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eed7339ac610091af1c8bc8db7223638126fef9cb4710e1259504e0a0d0ad234","last_reissued_at":"2026-05-18T01:35:15.264681Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:15.264681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.03772","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":"2026-05-18T01:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zFdUfl6TJGHiRwE43j0k6E0M6axpxsvxFesIBa1faYBHMD0fgirRWrCpYZfwxGjaRIoziyaTrZRuZc89KMjzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T17:43:41.225910Z"},"content_sha256":"d06da8d540e4b070192321c07e387b881180217239831dd436ca622792e86786","schema_version":"1.0","event_id":"sha256:d06da8d540e4b070192321c07e387b881180217239831dd436ca622792e86786"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:53LTHGWGCAERV4OIXSG3OIRWHA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic, statistical and algorithmic aspects of the similarity of texts and application to Gospels comparison","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"stat.ME","authors_text":"Gane Samb Lo, Soumaila Dembele","submitted_at":"2015-08-15T22:12:22Z","abstract_excerpt":"The fundamental problem of similarity studies, in the frame of data-mining, is to examine and detect similar items in articles, papers, books, with huge sizes. In this paper, we are interested in the probabilistic, and the statistical and the algorithmic aspects in studies of texts. We will be using the approach of $k$\\textit{-shinglings}, a $k$\\textit{-shingling} being defined as a sequence of $k$ consecutive characters that are extracted from a text ($k\\geq 1$ ). The main stake in this field is to find accurate and quick algorithms to compute the similarity in short times. This will be achie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03772","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":"2026-05-18T01:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+hCpOIUKKQIxEDl1STc5o18QItWN7inpVpgsuAf2Ky2z+569P+QWIPPKyGJkMjr5MxE2GL+Ing1DCz7zpvQSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T17:43:41.226255Z"},"content_sha256":"a848e1f438ec1d639a6752ffe0459c5cfbda48196dfb801c4c69436a22bf3604","schema_version":"1.0","event_id":"sha256:a848e1f438ec1d639a6752ffe0459c5cfbda48196dfb801c4c69436a22bf3604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53LTHGWGCAERV4OIXSG3OIRWHA/bundle.json","state_url":"https://pith.science/pith/53LTHGWGCAERV4OIXSG3OIRWHA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53LTHGWGCAERV4OIXSG3OIRWHA/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":"2026-06-25T17:43:41Z","links":{"resolver":"https://pith.science/pith/53LTHGWGCAERV4OIXSG3OIRWHA","bundle":"https://pith.science/pith/53LTHGWGCAERV4OIXSG3OIRWHA/bundle.json","state":"https://pith.science/pith/53LTHGWGCAERV4OIXSG3OIRWHA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53LTHGWGCAERV4OIXSG3OIRWHA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:53LTHGWGCAERV4OIXSG3OIRWHA","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":"214d7d72a9307ac3d3d8d4b73129cbb25deec5be5f9cbadff5537d3345e91eed","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-08-15T22:12:22Z","title_canon_sha256":"45794db1a19e3dbee5248dc19ad17cc31137d8639719c510a4af99871cd172a8"},"schema_version":"1.0","source":{"id":"1508.03772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.03772","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"1508.03772v1","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03772","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"53LTHGWGCAER","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"53LTHGWGCAERV4OI","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"53LTHGWG","created_at":"2026-05-18T12:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:a848e1f438ec1d639a6752ffe0459c5cfbda48196dfb801c4c69436a22bf3604","target":"graph","created_at":"2026-05-18T01:35:15Z","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":"The fundamental problem of similarity studies, in the frame of data-mining, is to examine and detect similar items in articles, papers, books, with huge sizes. In this paper, we are interested in the probabilistic, and the statistical and the algorithmic aspects in studies of texts. We will be using the approach of $k$\\textit{-shinglings}, a $k$\\textit{-shingling} being defined as a sequence of $k$ consecutive characters that are extracted from a text ($k\\geq 1$ ). The main stake in this field is to find accurate and quick algorithms to compute the similarity in short times. This will be achie","authors_text":"Gane Samb Lo, Soumaila Dembele","cross_cats":["math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-08-15T22:12:22Z","title":"Probabilistic, statistical and algorithmic aspects of the similarity of texts and application to Gospels comparison"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03772","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:d06da8d540e4b070192321c07e387b881180217239831dd436ca622792e86786","target":"record","created_at":"2026-05-18T01:35:15Z","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":"214d7d72a9307ac3d3d8d4b73129cbb25deec5be5f9cbadff5537d3345e91eed","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-08-15T22:12:22Z","title_canon_sha256":"45794db1a19e3dbee5248dc19ad17cc31137d8639719c510a4af99871cd172a8"},"schema_version":"1.0","source":{"id":"1508.03772","kind":"arxiv","version":1}},"canonical_sha256":"eed7339ac610091af1c8bc8db7223638126fef9cb4710e1259504e0a0d0ad234","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eed7339ac610091af1c8bc8db7223638126fef9cb4710e1259504e0a0d0ad234","first_computed_at":"2026-05-18T01:35:15.264681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:15.264681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2FXD0k8tFYEtclihSYX6KqExw3ipRvtB0YejIItLlhAOYyOqgIewsdiD8s81+kri1BdQkV4hzafCwGetvKMbCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:15.265258Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.03772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d06da8d540e4b070192321c07e387b881180217239831dd436ca622792e86786","sha256:a848e1f438ec1d639a6752ffe0459c5cfbda48196dfb801c4c69436a22bf3604"],"state_sha256":"8f201fc6924aece979ef5bd15c035f652061a3760a08597cbf5e2c993664eb21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9IIDW+sTFmZQ31DJryZ6UTeVGryQtaAKMIANtS7CJICduwlHWs0KkQ++FKhJWUdGU521dwpNSayV5tDn4lU/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T17:43:41.228196Z","bundle_sha256":"55d5a4ff04925b8e67bdfe859a984541858f67e273e14ad22056c11ce35f5db6"}}