{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:FK5N6LLYMU4VRGNGX7XG3OZ5K7","short_pith_number":"pith:FK5N6LLY","schema_version":"1.0","canonical_sha256":"2abadf2d7865395899a6bfee6dbb3d57da994e762c1630c757f3104f7c671a9a","source":{"kind":"arxiv","id":"1207.0144","version":1},"attestation_state":"computed","paper":{"title":"Mining Statistically Significant Substrings using the Chi-Square Statistic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arnab Bhattacharya, Mayank Sachan","submitted_at":"2012-06-30T20:22:30Z","abstract_excerpt":"The problem of identification of statistically significant patterns in a sequence of data has been applied to many domains such as intrusion detection systems, financial models, web-click records, automated monitoring systems, computational biology, cryptology, and text analysis. An observed pattern of events is deemed to be statistically significant if it is unlikely to have occurred due to randomness or chance alone. We use the chi-square statistic as a quantitative measure of statistical significance. Given a string of characters generated from a memoryless Bernoulli model, the problem is t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1207.0144","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-06-30T20:22:30Z","cross_cats_sorted":[],"title_canon_sha256":"cb9eb33b59c5bd54c41017b8dc039cc70358c80bb29c2390ceff7a7c9f59ecc8","abstract_canon_sha256":"449c9cacbe8c5e0e617b36a986e37440f3a409abba1e0be8cda8c70f67d1b220"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:00.165512Z","signature_b64":"39kVmUKzVmPPxlyqe38sPfBHEaHxxi2snwfMfzPqNcZuES4qFr1X2eab08nCrwFOgzk8DfR/x51jPSbXiG+6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2abadf2d7865395899a6bfee6dbb3d57da994e762c1630c757f3104f7c671a9a","last_reissued_at":"2026-05-18T03:52:00.164565Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:00.164565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mining Statistically Significant Substrings using the Chi-Square Statistic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arnab Bhattacharya, Mayank Sachan","submitted_at":"2012-06-30T20:22:30Z","abstract_excerpt":"The problem of identification of statistically significant patterns in a sequence of data has been applied to many domains such as intrusion detection systems, financial models, web-click records, automated monitoring systems, computational biology, cryptology, and text analysis. An observed pattern of events is deemed to be statistically significant if it is unlikely to have occurred due to randomness or chance alone. We use the chi-square statistic as a quantitative measure of statistical significance. Given a string of characters generated from a memoryless Bernoulli model, the problem is t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.0144","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1207.0144","created_at":"2026-05-18T03:52:00.164731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.0144v1","created_at":"2026-05-18T03:52:00.164731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.0144","created_at":"2026-05-18T03:52:00.164731+00:00"},{"alias_kind":"pith_short_12","alias_value":"FK5N6LLYMU4V","created_at":"2026-05-18T12:27:06.952714+00:00"},{"alias_kind":"pith_short_16","alias_value":"FK5N6LLYMU4VRGNG","created_at":"2026-05-18T12:27:06.952714+00:00"},{"alias_kind":"pith_short_8","alias_value":"FK5N6LLY","created_at":"2026-05-18T12:27:06.952714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7","json":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7.json","graph_json":"https://pith.science/api/pith-number/FK5N6LLYMU4VRGNGX7XG3OZ5K7/graph.json","events_json":"https://pith.science/api/pith-number/FK5N6LLYMU4VRGNGX7XG3OZ5K7/events.json","paper":"https://pith.science/paper/FK5N6LLY"},"agent_actions":{"view_html":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7","download_json":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7.json","view_paper":"https://pith.science/paper/FK5N6LLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.0144&json=true","fetch_graph":"https://pith.science/api/pith-number/FK5N6LLYMU4VRGNGX7XG3OZ5K7/graph.json","fetch_events":"https://pith.science/api/pith-number/FK5N6LLYMU4VRGNGX7XG3OZ5K7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7/action/storage_attestation","attest_author":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7/action/author_attestation","sign_citation":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7/action/citation_signature","submit_replication":"https://pith.science/pith/FK5N6LLYMU4VRGNGX7XG3OZ5K7/action/replication_record"}},"created_at":"2026-05-18T03:52:00.164731+00:00","updated_at":"2026-05-18T03:52:00.164731+00:00"}