{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:555OQ7Y3CFYSQP4CPFJLJKT6XZ","short_pith_number":"pith:555OQ7Y3","schema_version":"1.0","canonical_sha256":"ef7ae87f1b1171283f827952b4aa7ebe6fbbba1d96b4e14c36e9e32c74c1a186","source":{"kind":"arxiv","id":"2111.15031","version":1},"attestation_state":"computed","paper":{"title":"MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Charles Nicholas, Dev Amlani, Edward Raff, Robert J. Joyce","submitted_at":"2021-11-29T23:59:50Z","abstract_excerpt":"Malware family classification is a significant issue with public safety and research implications that has been hindered by the high cost of expert labels. The vast majority of corpora use noisy labeling approaches that obstruct definitive quantification of results and study of deeper interactions. In order to provide the data needed to advance further, we have created the Malware Open-source Threat Intelligence Family (MOTIF) dataset. MOTIF contains 3,095 malware samples from 454 families, making it the largest and most diverse public malware dataset with ground truth family labels to date, n"},"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":"2111.15031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T23:59:50Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"84bf59754c9f822c0f794a4b91026c09c97ea886e884769af92efc654009f998","abstract_canon_sha256":"de4233fcccd473c86edaa4e6753f390cf9cbffa7c6c72b4f6df5bdfd2353d4cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:22.171380Z","signature_b64":"TaO3LchmuxJzw6yK72/7HgbDEPE73wsozi+VorqI+entOyeiU5XX3WYJdGV3BiYxa11vNbr8qs1Xm3jWFnJmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7ae87f1b1171283f827952b4aa7ebe6fbbba1d96b4e14c36e9e32c74c1a186","last_reissued_at":"2026-07-05T03:36:22.170895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:22.170895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Charles Nicholas, Dev Amlani, Edward Raff, Robert J. Joyce","submitted_at":"2021-11-29T23:59:50Z","abstract_excerpt":"Malware family classification is a significant issue with public safety and research implications that has been hindered by the high cost of expert labels. The vast majority of corpora use noisy labeling approaches that obstruct definitive quantification of results and study of deeper interactions. In order to provide the data needed to advance further, we have created the Malware Open-source Threat Intelligence Family (MOTIF) dataset. MOTIF contains 3,095 malware samples from 454 families, making it the largest and most diverse public malware dataset with ground truth family labels to date, n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15031","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/2111.15031/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":"2111.15031","created_at":"2026-07-05T03:36:22.170957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.15031v1","created_at":"2026-07-05T03:36:22.170957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15031","created_at":"2026-07-05T03:36:22.170957+00:00"},{"alias_kind":"pith_short_12","alias_value":"555OQ7Y3CFYS","created_at":"2026-07-05T03:36:22.170957+00:00"},{"alias_kind":"pith_short_16","alias_value":"555OQ7Y3CFYSQP4C","created_at":"2026-07-05T03:36:22.170957+00:00"},{"alias_kind":"pith_short_8","alias_value":"555OQ7Y3","created_at":"2026-07-05T03:36:22.170957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01445","citing_title":"Hamm-Grams: An Algorithm for Mining Regular Expressions of Bytes","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21615","citing_title":"ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04227","citing_title":"Mobile GUI Agents under Real-world Threats: Are We There Yet?","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ","json":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ.json","graph_json":"https://pith.science/api/pith-number/555OQ7Y3CFYSQP4CPFJLJKT6XZ/graph.json","events_json":"https://pith.science/api/pith-number/555OQ7Y3CFYSQP4CPFJLJKT6XZ/events.json","paper":"https://pith.science/paper/555OQ7Y3"},"agent_actions":{"view_html":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ","download_json":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ.json","view_paper":"https://pith.science/paper/555OQ7Y3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.15031&json=true","fetch_graph":"https://pith.science/api/pith-number/555OQ7Y3CFYSQP4CPFJLJKT6XZ/graph.json","fetch_events":"https://pith.science/api/pith-number/555OQ7Y3CFYSQP4CPFJLJKT6XZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ/action/storage_attestation","attest_author":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ/action/author_attestation","sign_citation":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ/action/citation_signature","submit_replication":"https://pith.science/pith/555OQ7Y3CFYSQP4CPFJLJKT6XZ/action/replication_record"}},"created_at":"2026-07-05T03:36:22.170957+00:00","updated_at":"2026-07-05T03:36:22.170957+00:00"}