{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WUFDF3AAVD2UOYEPTI7GDXFS6L","short_pith_number":"pith:WUFDF3AA","schema_version":"1.0","canonical_sha256":"b50a32ec00a8f547608f9a3e61dcb2f2ea6bdbf9fcf79b1553095c9e83c4fb22","source":{"kind":"arxiv","id":"2103.02753","version":1},"attestation_state":"computed","paper":{"title":"Malware Classification with GMM-HMM Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Jing Zhao, Mark Stamp, Samanvitha Basole","submitted_at":"2021-03-03T23:23:48Z","abstract_excerpt":"Discrete hidden Markov models (HMM) are often applied to malware detection and classification problems. However, the continuous analog of discrete HMMs, that is, Gaussian mixture model-HMMs (GMM-HMM), are rarely considered in the field of cybersecurity. In this paper, we use GMM-HMMs for malware classification and we compare our results to those obtained using discrete HMMs. As features, we consider opcode sequences and entropy-based sequences. For our opcode features, GMM-HMMs produce results that are comparable to those obtained using discrete HMMs, whereas for our entropy-based features, GM"},"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":"2103.02753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-03-03T23:23:48Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"295698b3bb9fe6ed69d84e84f2879f67fc91aec6a9748ea10c8645d3df978c1b","abstract_canon_sha256":"00903d9124b600b209e385b1e9c06e59a731acc8b3e93c41edce15932f126bf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:20.699249Z","signature_b64":"SroltuwZ2EL5CTCGT0qQaTuCbY87kqLzMA5/6cXbDsmi5tXg8t9fJz6nRGBpvug4MwIkjkketvLOYE1M6S1uCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b50a32ec00a8f547608f9a3e61dcb2f2ea6bdbf9fcf79b1553095c9e83c4fb22","last_reissued_at":"2026-07-05T02:20:20.698862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:20.698862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Malware Classification with GMM-HMM Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CR","authors_text":"Jing Zhao, Mark Stamp, Samanvitha Basole","submitted_at":"2021-03-03T23:23:48Z","abstract_excerpt":"Discrete hidden Markov models (HMM) are often applied to malware detection and classification problems. However, the continuous analog of discrete HMMs, that is, Gaussian mixture model-HMMs (GMM-HMM), are rarely considered in the field of cybersecurity. In this paper, we use GMM-HMMs for malware classification and we compare our results to those obtained using discrete HMMs. As features, we consider opcode sequences and entropy-based sequences. For our opcode features, GMM-HMMs produce results that are comparable to those obtained using discrete HMMs, whereas for our entropy-based features, GM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02753","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/2103.02753/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.02753","created_at":"2026-07-05T02:20:20.698919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.02753v1","created_at":"2026-07-05T02:20:20.698919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02753","created_at":"2026-07-05T02:20:20.698919+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUFDF3AAVD2U","created_at":"2026-07-05T02:20:20.698919+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUFDF3AAVD2UOYEP","created_at":"2026-07-05T02:20:20.698919+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUFDF3AA","created_at":"2026-07-05T02:20:20.698919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18932","citing_title":"Malware Classification using a Hybrid Hidden Markov Model-Convolutional Neural Network","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L","json":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L.json","graph_json":"https://pith.science/api/pith-number/WUFDF3AAVD2UOYEPTI7GDXFS6L/graph.json","events_json":"https://pith.science/api/pith-number/WUFDF3AAVD2UOYEPTI7GDXFS6L/events.json","paper":"https://pith.science/paper/WUFDF3AA"},"agent_actions":{"view_html":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L","download_json":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L.json","view_paper":"https://pith.science/paper/WUFDF3AA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.02753&json=true","fetch_graph":"https://pith.science/api/pith-number/WUFDF3AAVD2UOYEPTI7GDXFS6L/graph.json","fetch_events":"https://pith.science/api/pith-number/WUFDF3AAVD2UOYEPTI7GDXFS6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L/action/storage_attestation","attest_author":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L/action/author_attestation","sign_citation":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L/action/citation_signature","submit_replication":"https://pith.science/pith/WUFDF3AAVD2UOYEPTI7GDXFS6L/action/replication_record"}},"created_at":"2026-07-05T02:20:20.698919+00:00","updated_at":"2026-07-05T02:20:20.698919+00:00"}