{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TFKQSQ42Q52VWBZVFB6OKAJIAL","short_pith_number":"pith:TFKQSQ42","canonical_record":{"source":{"id":"2309.06643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-09-12T23:45:59Z","cross_cats_sorted":[],"title_canon_sha256":"b31d01ba30d0d1f831ee108ff236a674b882f18be8e2f3f3a118596aa975881f","abstract_canon_sha256":"5a9b3fb09d73dba3e87ee2cb19c95cf821629d2b2acc147057a295aaafa918ea"},"schema_version":"1.0"},"canonical_sha256":"995509439a87755b0735287ce5012802c481db36fad4db8e83ea578fb8612c9c","source":{"kind":"arxiv","id":"2309.06643","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06643","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06643v1","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06643","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"TFKQSQ42Q52V","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"TFKQSQ42Q52VWBZV","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"TFKQSQ42","created_at":"2026-07-05T06:50:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TFKQSQ42Q52VWBZVFB6OKAJIAL","target":"record","payload":{"canonical_record":{"source":{"id":"2309.06643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-09-12T23:45:59Z","cross_cats_sorted":[],"title_canon_sha256":"b31d01ba30d0d1f831ee108ff236a674b882f18be8e2f3f3a118596aa975881f","abstract_canon_sha256":"5a9b3fb09d73dba3e87ee2cb19c95cf821629d2b2acc147057a295aaafa918ea"},"schema_version":"1.0"},"canonical_sha256":"995509439a87755b0735287ce5012802c481db36fad4db8e83ea578fb8612c9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:20.655261Z","signature_b64":"/4me4oskG/izS0LGcyPCYN+RfpwvVTIQgHIm7ZO8kk2nO6mMQ2SLQ3gXTtPhJ3F/3T/vVGk9xlVprHqZnJi9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"995509439a87755b0735287ce5012802c481db36fad4db8e83ea578fb8612c9c","last_reissued_at":"2026-07-05T06:50:20.654771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:20.654771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.06643","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mqy3rthk0+qyhP/JAzCSeVAHGcKcjy52azGZXusMkMyO95EQ/kFouNLlr4AQthSlUsspEJS8jFBimxyrAAKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:07:01.437552Z"},"content_sha256":"f91977fb13af95bec8d9104436e3105102dc4020535d095d2d49eda7db042b82","schema_version":"1.0","event_id":"sha256:f91977fb13af95bec8d9104436e3105102dc4020535d095d2d49eda7db042b82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TFKQSQ42Q52VWBZVFB6OKAJIAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised Classification of Malware Families Under Extreme Class Imbalance via Hierarchical Non-Negative Matrix Factorization with Automatic Model Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Boian S. Alexandrov, Charles Nicholas, Edward Raff, Maksim E. Eren, Manish Bhattarai, Robert J. Joyce","submitted_at":"2023-09-12T23:45:59Z","abstract_excerpt":"Identification of the family to which a malware specimen belongs is essential in understanding the behavior of the malware and developing mitigation strategies. Solutions proposed by prior work, however, are often not practicable due to the lack of realistic evaluation factors. These factors include learning under class imbalance, the ability to identify new malware, and the cost of production-quality labeled data. In practice, deployed models face prominent, rare, and new malware families. At the same time, obtaining a large quantity of up-to-date labeled malware for training a model can be e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06643","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/2309.06643/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:50:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3SSmDCjoM22t43kN5abL1VaPgRTrXB7NtdtT6ixle5s9L5AMK4cD/yX5/dQsyUsE/huRE+/TCVYQo3a/tSFzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:07:01.437917Z"},"content_sha256":"b22a21e2ec0e6eef1b122a3ad1153e7b4229cf0174ecf7b63b4c3b671ddfe49a","schema_version":"1.0","event_id":"sha256:b22a21e2ec0e6eef1b122a3ad1153e7b4229cf0174ecf7b63b4c3b671ddfe49a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TFKQSQ42Q52VWBZVFB6OKAJIAL/bundle.json","state_url":"https://pith.science/pith/TFKQSQ42Q52VWBZVFB6OKAJIAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TFKQSQ42Q52VWBZVFB6OKAJIAL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T21:07:01Z","links":{"resolver":"https://pith.science/pith/TFKQSQ42Q52VWBZVFB6OKAJIAL","bundle":"https://pith.science/pith/TFKQSQ42Q52VWBZVFB6OKAJIAL/bundle.json","state":"https://pith.science/pith/TFKQSQ42Q52VWBZVFB6OKAJIAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TFKQSQ42Q52VWBZVFB6OKAJIAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TFKQSQ42Q52VWBZVFB6OKAJIAL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5a9b3fb09d73dba3e87ee2cb19c95cf821629d2b2acc147057a295aaafa918ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-09-12T23:45:59Z","title_canon_sha256":"b31d01ba30d0d1f831ee108ff236a674b882f18be8e2f3f3a118596aa975881f"},"schema_version":"1.0","source":{"id":"2309.06643","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06643","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06643v1","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06643","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"TFKQSQ42Q52V","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"TFKQSQ42Q52VWBZV","created_at":"2026-07-05T06:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"TFKQSQ42","created_at":"2026-07-05T06:50:20Z"}],"graph_snapshots":[{"event_id":"sha256:b22a21e2ec0e6eef1b122a3ad1153e7b4229cf0174ecf7b63b4c3b671ddfe49a","target":"graph","created_at":"2026-07-05T06:50:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2309.06643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identification of the family to which a malware specimen belongs is essential in understanding the behavior of the malware and developing mitigation strategies. Solutions proposed by prior work, however, are often not practicable due to the lack of realistic evaluation factors. These factors include learning under class imbalance, the ability to identify new malware, and the cost of production-quality labeled data. In practice, deployed models face prominent, rare, and new malware families. At the same time, obtaining a large quantity of up-to-date labeled malware for training a model can be e","authors_text":"Boian S. Alexandrov, Charles Nicholas, Edward Raff, Maksim E. Eren, Manish Bhattarai, Robert J. Joyce","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-09-12T23:45:59Z","title":"Semi-supervised Classification of Malware Families Under Extreme Class Imbalance via Hierarchical Non-Negative Matrix Factorization with Automatic Model Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06643","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f91977fb13af95bec8d9104436e3105102dc4020535d095d2d49eda7db042b82","target":"record","created_at":"2026-07-05T06:50:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5a9b3fb09d73dba3e87ee2cb19c95cf821629d2b2acc147057a295aaafa918ea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-09-12T23:45:59Z","title_canon_sha256":"b31d01ba30d0d1f831ee108ff236a674b882f18be8e2f3f3a118596aa975881f"},"schema_version":"1.0","source":{"id":"2309.06643","kind":"arxiv","version":1}},"canonical_sha256":"995509439a87755b0735287ce5012802c481db36fad4db8e83ea578fb8612c9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"995509439a87755b0735287ce5012802c481db36fad4db8e83ea578fb8612c9c","first_computed_at":"2026-07-05T06:50:20.654771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:20.654771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/4me4oskG/izS0LGcyPCYN+RfpwvVTIQgHIm7ZO8kk2nO6mMQ2SLQ3gXTtPhJ3F/3T/vVGk9xlVprHqZnJi9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:20.655261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.06643","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f91977fb13af95bec8d9104436e3105102dc4020535d095d2d49eda7db042b82","sha256:b22a21e2ec0e6eef1b122a3ad1153e7b4229cf0174ecf7b63b4c3b671ddfe49a"],"state_sha256":"3625241e7c30d7ab7d563ffc8fed335196c1463c7d982ddda30e2696d2eae3b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qauqyd8o9JvE0NIKSBHAFh7Ks9Jd6xaY0TeYvnGQUSHCSl7A69/LmDLsAAEfc/HsbI6+JUnz4I3xwsAaXblrDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:07:01.441983Z","bundle_sha256":"68ad6134f9e7c45aeb94e65640311045a4917bb52f7d30ddca136ed13f61e2ae"}}