{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AYEVJYMVB3TERWQSWMYM3RUXJS","short_pith_number":"pith:AYEVJYMV","schema_version":"1.0","canonical_sha256":"060954e1950ee648da12b330cdc6974c9689577a1a739e33819406a076e62874","source":{"kind":"arxiv","id":"1802.10135","version":1},"attestation_state":"computed","paper":{"title":"Microsoft Malware Classification Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Corina Feuerstein, Elad Yom-Tov, Mansour Ahmadi, Marian Radu, Royi Ronen","submitted_at":"2018-02-22T12:27:38Z","abstract_excerpt":"The Microsoft Malware Classification Challenge was announced in 2015 along with a publication of a huge dataset of nearly 0.5 terabytes, consisting of disassembly and bytecode of more than 20K malware samples. Apart from serving in the Kaggle competition, the dataset has become a standard benchmark for research on modeling malware behaviour. To date, the dataset has been cited in more than 50 research papers. Here we provide a high-level comparison of the publications citing the dataset. The comparison simplifies finding potential research directions in this field and future performance evalua"},"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":"1802.10135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-02-22T12:27:38Z","cross_cats_sorted":[],"title_canon_sha256":"d2cb75e3dc548dcb63a3c31e778b2271f6ec26608a229ad82d1b1e8c4988b8b2","abstract_canon_sha256":"99345bc951e1a15c98446e2ba3af9d621a910af482de52307941cb74bb8febab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:18.062134Z","signature_b64":"MWqsLr6H2A3r7vtN36fmGhuManK/0FLXkpxdV4z1eawd2/W665h7PPlksY/4RyKYiwA1h/6Ro7Ks4v8i591yDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"060954e1950ee648da12b330cdc6974c9689577a1a739e33819406a076e62874","last_reissued_at":"2026-05-18T00:22:18.061520Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:18.061520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Microsoft Malware Classification Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Corina Feuerstein, Elad Yom-Tov, Mansour Ahmadi, Marian Radu, Royi Ronen","submitted_at":"2018-02-22T12:27:38Z","abstract_excerpt":"The Microsoft Malware Classification Challenge was announced in 2015 along with a publication of a huge dataset of nearly 0.5 terabytes, consisting of disassembly and bytecode of more than 20K malware samples. Apart from serving in the Kaggle competition, the dataset has become a standard benchmark for research on modeling malware behaviour. To date, the dataset has been cited in more than 50 research papers. Here we provide a high-level comparison of the publications citing the dataset. The comparison simplifies finding potential research directions in this field and future performance evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10135","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":"1802.10135","created_at":"2026-05-18T00:22:18.061607+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10135v1","created_at":"2026-05-18T00:22:18.061607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10135","created_at":"2026-05-18T00:22:18.061607+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYEVJYMVB3TE","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYEVJYMVB3TERWQS","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYEVJYMV","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05807","citing_title":"LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS","json":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS.json","graph_json":"https://pith.science/api/pith-number/AYEVJYMVB3TERWQSWMYM3RUXJS/graph.json","events_json":"https://pith.science/api/pith-number/AYEVJYMVB3TERWQSWMYM3RUXJS/events.json","paper":"https://pith.science/paper/AYEVJYMV"},"agent_actions":{"view_html":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS","download_json":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS.json","view_paper":"https://pith.science/paper/AYEVJYMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10135&json=true","fetch_graph":"https://pith.science/api/pith-number/AYEVJYMVB3TERWQSWMYM3RUXJS/graph.json","fetch_events":"https://pith.science/api/pith-number/AYEVJYMVB3TERWQSWMYM3RUXJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS/action/storage_attestation","attest_author":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS/action/author_attestation","sign_citation":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS/action/citation_signature","submit_replication":"https://pith.science/pith/AYEVJYMVB3TERWQSWMYM3RUXJS/action/replication_record"}},"created_at":"2026-05-18T00:22:18.061607+00:00","updated_at":"2026-05-18T00:22:18.061607+00:00"}