{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M2K5H5C56PBOKUAP4J2M7UPYPD","short_pith_number":"pith:M2K5H5C5","canonical_record":{"source":{"id":"2608.02348","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-03T15:01:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b12d03dbfcef5a88c4840e5dfe31244d49a728870804c922b172790b0ae540fa","abstract_canon_sha256":"cb78bba029ef84995cb9109f84d3c31f87d5457d900460699c4580e1074ce01c"},"schema_version":"1.0"},"canonical_sha256":"6695d3f45df3c2e5500fe274cfd1f878ce9ab00183b9c4d5efa9f910b6ae3fa1","source":{"kind":"arxiv","id":"2608.02348","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02348","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02348v1","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02348","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"M2K5H5C56PBO","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"pith_short_16","alias_value":"M2K5H5C56PBOKUAP","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"pith_short_8","alias_value":"M2K5H5C5","created_at":"2026-08-04T02:12:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M2K5H5C56PBOKUAP4J2M7UPYPD","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02348","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-03T15:01:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b12d03dbfcef5a88c4840e5dfe31244d49a728870804c922b172790b0ae540fa","abstract_canon_sha256":"cb78bba029ef84995cb9109f84d3c31f87d5457d900460699c4580e1074ce01c"},"schema_version":"1.0"},"canonical_sha256":"6695d3f45df3c2e5500fe274cfd1f878ce9ab00183b9c4d5efa9f910b6ae3fa1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:12:00.278264Z","signature_b64":"npnuGrpXnJuspBeDy02KSf+gMb5XIGz9OdrZouysqWk64TgWNJigSJ2lVfO0RQ3Hi3nqGl5/aWH8sDVq8CHbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6695d3f45df3c2e5500fe274cfd1f878ce9ab00183b9c4d5efa9f910b6ae3fa1","last_reissued_at":"2026-08-04T02:12:00.276527Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:12:00.276527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02348","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":"2026-08-04T02:12:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sUTP1nnmCy6YSS2gREzP4C6/DFJHqQguHd+jBrS6izWrklgKTf2hOWIZeW4xWSZzdQJK2iZU9aQB5eyT5Jd+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:39:04.187633Z"},"content_sha256":"32cb46eca9631de9a80c00ac21280feedb8c1a22df2f166290c23d806a5fc18d","schema_version":"1.0","event_id":"sha256:32cb46eca9631de9a80c00ac21280feedb8c1a22df2f166290c23d806a5fc18d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M2K5H5C56PBOKUAP4J2M7UPYPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Daniela Chud\\'a, Martin Mocko","submitted_at":"2026-08-03T15:01:00Z","abstract_excerpt":"Malware clustering is a critical task in cybersecurity that helps discover threats and analyze evolving malware families. While self-supervised learning (SSL) and tabular representation learning (TRL) have achieved breakthroughs in other domains, their application to binary program clustering (the task of clustering all incoming samples regardless of label) remains largely unexplored. This study presents the first systematic investigation of SSL and TRL methods for binary program clustering, conducted in two phases on the public Ember and Bodmas datasets. In Phase 1, we establish a performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02348","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/2608.02348/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":"2026-08-04T02:12:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJkKK/ZZbFBx2+acw4HbImjAUiEqnDVsRDsazELxTJS+D8zHoZcoeBMwTr+luh4EZDYb48hZ9jUgkb9CYBWWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:39:04.188559Z"},"content_sha256":"b5c20dd893c17b6a1246cd1b6206a3050c793aeacecd73e08b864b97cfcfaf66","schema_version":"1.0","event_id":"sha256:b5c20dd893c17b6a1246cd1b6206a3050c793aeacecd73e08b864b97cfcfaf66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2K5H5C56PBOKUAP4J2M7UPYPD/bundle.json","state_url":"https://pith.science/pith/M2K5H5C56PBOKUAP4J2M7UPYPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2K5H5C56PBOKUAP4J2M7UPYPD/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":"2026-08-09T17:39:04Z","links":{"resolver":"https://pith.science/pith/M2K5H5C56PBOKUAP4J2M7UPYPD","bundle":"https://pith.science/pith/M2K5H5C56PBOKUAP4J2M7UPYPD/bundle.json","state":"https://pith.science/pith/M2K5H5C56PBOKUAP4J2M7UPYPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2K5H5C56PBOKUAP4J2M7UPYPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M2K5H5C56PBOKUAP4J2M7UPYPD","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":"cb78bba029ef84995cb9109f84d3c31f87d5457d900460699c4580e1074ce01c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-03T15:01:00Z","title_canon_sha256":"b12d03dbfcef5a88c4840e5dfe31244d49a728870804c922b172790b0ae540fa"},"schema_version":"1.0","source":{"id":"2608.02348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02348","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02348v1","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02348","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"M2K5H5C56PBO","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"pith_short_16","alias_value":"M2K5H5C56PBOKUAP","created_at":"2026-08-04T02:12:00Z"},{"alias_kind":"pith_short_8","alias_value":"M2K5H5C5","created_at":"2026-08-04T02:12:00Z"}],"graph_snapshots":[{"event_id":"sha256:b5c20dd893c17b6a1246cd1b6206a3050c793aeacecd73e08b864b97cfcfaf66","target":"graph","created_at":"2026-08-04T02:12:00Z","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/2608.02348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Malware clustering is a critical task in cybersecurity that helps discover threats and analyze evolving malware families. While self-supervised learning (SSL) and tabular representation learning (TRL) have achieved breakthroughs in other domains, their application to binary program clustering (the task of clustering all incoming samples regardless of label) remains largely unexplored. This study presents the first systematic investigation of SSL and TRL methods for binary program clustering, conducted in two phases on the public Ember and Bodmas datasets. In Phase 1, we establish a performance","authors_text":"Daniela Chud\\'a, Martin Mocko","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-03T15:01:00Z","title":"Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02348","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":"sha256:32cb46eca9631de9a80c00ac21280feedb8c1a22df2f166290c23d806a5fc18d","target":"record","created_at":"2026-08-04T02:12:00Z","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":"cb78bba029ef84995cb9109f84d3c31f87d5457d900460699c4580e1074ce01c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-03T15:01:00Z","title_canon_sha256":"b12d03dbfcef5a88c4840e5dfe31244d49a728870804c922b172790b0ae540fa"},"schema_version":"1.0","source":{"id":"2608.02348","kind":"arxiv","version":1}},"canonical_sha256":"6695d3f45df3c2e5500fe274cfd1f878ce9ab00183b9c4d5efa9f910b6ae3fa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6695d3f45df3c2e5500fe274cfd1f878ce9ab00183b9c4d5efa9f910b6ae3fa1","first_computed_at":"2026-08-04T02:12:00.276527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:12:00.276527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"npnuGrpXnJuspBeDy02KSf+gMb5XIGz9OdrZouysqWk64TgWNJigSJ2lVfO0RQ3Hi3nqGl5/aWH8sDVq8CHbAg==","signature_status":"signed_v1","signed_at":"2026-08-04T02:12:00.278264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32cb46eca9631de9a80c00ac21280feedb8c1a22df2f166290c23d806a5fc18d","sha256:b5c20dd893c17b6a1246cd1b6206a3050c793aeacecd73e08b864b97cfcfaf66"],"state_sha256":"1f4dae454a90246f477948c788315967cd3759d1c55eb7e4fecfb918443b5bca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71TQvTmvjOqrnKyD6Cpi9PsMsRNwTo3xqvARZmh7uO5U01Rc5dq2bLOnEIXknrjAnN+CY9QPlucCiMcrfEj7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:39:04.252920Z","bundle_sha256":"e1595cb8f9bfd3afbfabbcdd5a6c31b10f587ab947f1421ce98ce4d70dab04a7"}}