{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXS4J4OKFKDG373LSOUL4NHZZL","short_pith_number":"pith:MXS4J4OK","schema_version":"1.0","canonical_sha256":"65e5c4f1ca2a866dff6b93a8be34f9caf266720ef7876c5ac14d67f106c07100","source":{"kind":"arxiv","id":"2507.02959","version":1},"attestation_state":"computed","paper":{"title":"A Novel Active Learning Approach to Label One Million Unknown Malware Variants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ahmed Bensaoud, Jugal Kalita","submitted_at":"2025-06-30T04:18:31Z","abstract_excerpt":"Active learning for classification seeks to reduce the cost of labeling samples by finding unlabeled examples about which the current model is least certain and sending them to an annotator/expert to label. Bayesian theory can provide a probabilistic view of deep neural network models by asserting a prior distribution over model parameters and estimating the uncertainties by posterior distribution over these parameters. This paper proposes two novel active learning approaches to label one million malware examples belonging to different unknown modern malware families. The first model is Incept"},"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":"2507.02959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-30T04:18:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d22436b012fdce7292ebf74ff4c09b610a5af956b2a90fcd9cf181bebc25fc26","abstract_canon_sha256":"dc5b3e58220a3117e7a59f608146971b73c8396845064de9e93c4dae38f007e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:49.546586Z","signature_b64":"I+OO6WDEGXbrtDP0jnu7w/ye8uVY53D9TP1KpXIc/LwdShWBGWIl/v/J6l8Wj+bab8OfQciL+M0dL2FkkjkgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65e5c4f1ca2a866dff6b93a8be34f9caf266720ef7876c5ac14d67f106c07100","last_reissued_at":"2026-07-05T11:31:49.546083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:49.546083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel Active Learning Approach to Label One Million Unknown Malware Variants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ahmed Bensaoud, Jugal Kalita","submitted_at":"2025-06-30T04:18:31Z","abstract_excerpt":"Active learning for classification seeks to reduce the cost of labeling samples by finding unlabeled examples about which the current model is least certain and sending them to an annotator/expert to label. Bayesian theory can provide a probabilistic view of deep neural network models by asserting a prior distribution over model parameters and estimating the uncertainties by posterior distribution over these parameters. This paper proposes two novel active learning approaches to label one million malware examples belonging to different unknown modern malware families. The first model is Incept"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02959","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/2507.02959/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":"2507.02959","created_at":"2026-07-05T11:31:49.546141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02959v1","created_at":"2026-07-05T11:31:49.546141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02959","created_at":"2026-07-05T11:31:49.546141+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXS4J4OKFKDG","created_at":"2026-07-05T11:31:49.546141+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXS4J4OKFKDG373L","created_at":"2026-07-05T11:31:49.546141+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXS4J4OK","created_at":"2026-07-05T11:31:49.546141+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/MXS4J4OKFKDG373LSOUL4NHZZL","json":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL.json","graph_json":"https://pith.science/api/pith-number/MXS4J4OKFKDG373LSOUL4NHZZL/graph.json","events_json":"https://pith.science/api/pith-number/MXS4J4OKFKDG373LSOUL4NHZZL/events.json","paper":"https://pith.science/paper/MXS4J4OK"},"agent_actions":{"view_html":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL","download_json":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL.json","view_paper":"https://pith.science/paper/MXS4J4OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02959&json=true","fetch_graph":"https://pith.science/api/pith-number/MXS4J4OKFKDG373LSOUL4NHZZL/graph.json","fetch_events":"https://pith.science/api/pith-number/MXS4J4OKFKDG373LSOUL4NHZZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL/action/storage_attestation","attest_author":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL/action/author_attestation","sign_citation":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL/action/citation_signature","submit_replication":"https://pith.science/pith/MXS4J4OKFKDG373LSOUL4NHZZL/action/replication_record"}},"created_at":"2026-07-05T11:31:49.546141+00:00","updated_at":"2026-07-05T11:31:49.546141+00:00"}