{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6CANMG7VWKCXF2V3VGS6TS4OTT","short_pith_number":"pith:6CANMG7V","canonical_record":{"source":{"id":"2405.03991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-05-07T04:10:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"534cf54f284e05367a12133c2475640b5fa33485464c8735611a1a90cf937009","abstract_canon_sha256":"72ef74f3453265f493918900e4eb49a84b4d20136fc132ce6ffef9cfcac207e1"},"schema_version":"1.0"},"canonical_sha256":"f080d61bf5b28572eabba9a5e9cb8e9ccc7310d4f32174fdbb346426f8c52c08","source":{"kind":"arxiv","id":"2405.03991","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03991","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03991v2","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03991","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"6CANMG7VWKCX","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"6CANMG7VWKCXF2V3","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"6CANMG7V","created_at":"2026-07-05T09:30:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6CANMG7VWKCXF2V3VGS6TS4OTT","target":"record","payload":{"canonical_record":{"source":{"id":"2405.03991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-05-07T04:10:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"534cf54f284e05367a12133c2475640b5fa33485464c8735611a1a90cf937009","abstract_canon_sha256":"72ef74f3453265f493918900e4eb49a84b4d20136fc132ce6ffef9cfcac207e1"},"schema_version":"1.0"},"canonical_sha256":"f080d61bf5b28572eabba9a5e9cb8e9ccc7310d4f32174fdbb346426f8c52c08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:13.633142Z","signature_b64":"CKmiDhH8LQ+v3Py7/S/ZCeYy4DbNjxmIXV5lWeHbVDMUc0EXHOFspdHzfac5dABUrNWRJbc76alaYkhxiFIXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f080d61bf5b28572eabba9a5e9cb8e9ccc7310d4f32174fdbb346426f8c52c08","last_reissued_at":"2026-07-05T09:30:13.632672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:13.632672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.03991","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQtV0peW714Pm2d/pEtZ/K5tDQ8udGQm9cMRt/xObOg3uPZxtledktly3ZhfUKj61mGpt5NAEqi99LWtb9ijAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T10:12:43.259573Z"},"content_sha256":"f1709d58e502966fa08fe17c05c2225b30e523e9c970f42c8fb89a2bc4f2e4aa","schema_version":"1.0","event_id":"sha256:f1709d58e502966fa08fe17c05c2225b30e523e9c970f42c8fb89a2bc4f2e4aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6CANMG7VWKCXF2V3VGS6TS4OTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assemblage: Automatic Binary Dataset Construction for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chang Liu, Edward Raff, James Holt, Kristopher Micinski, Maya Fuchs, Rebecca Saul, Townsend Southard Pantano, Yihao Sun","submitted_at":"2024-05-07T04:10:01Z","abstract_excerpt":"Binary code is pervasive, and binary analysis is a key task in reverse engineering, malware classification, and vulnerability discovery. Unfortunately, while there exist large corpora of malicious binaries, obtaining high-quality corpora of benign binaries for modern systems has proven challenging (e.g., due to licensing issues). Consequently, machine learning based pipelines for binary analysis utilize either costly commercial corpora (e.g., VirusTotal) or open-source binaries (e.g., coreutils) available in limited quantities. To address these issues, we present Assemblage: an extensible clou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03991","kind":"arxiv","version":2},"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/2405.03991/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":"2026-07-05T09:30:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7VD8a321BZlf026EhT9QQhOJCrT1qsvbaui4CcueeJYFrxJTUSN5gbBZyUJCQtWdTWUjdr7enjUrO0hPrTVZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T10:12:43.259961Z"},"content_sha256":"1eae110373b4d6a31f6cb6878f5dae5dac859957733f3b0a27c1ba6f3b2a09e1","schema_version":"1.0","event_id":"sha256:1eae110373b4d6a31f6cb6878f5dae5dac859957733f3b0a27c1ba6f3b2a09e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CANMG7VWKCXF2V3VGS6TS4OTT/bundle.json","state_url":"https://pith.science/pith/6CANMG7VWKCXF2V3VGS6TS4OTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CANMG7VWKCXF2V3VGS6TS4OTT/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":"2026-07-13T10:12:43Z","links":{"resolver":"https://pith.science/pith/6CANMG7VWKCXF2V3VGS6TS4OTT","bundle":"https://pith.science/pith/6CANMG7VWKCXF2V3VGS6TS4OTT/bundle.json","state":"https://pith.science/pith/6CANMG7VWKCXF2V3VGS6TS4OTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CANMG7VWKCXF2V3VGS6TS4OTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CANMG7VWKCXF2V3VGS6TS4OTT","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":"72ef74f3453265f493918900e4eb49a84b4d20136fc132ce6ffef9cfcac207e1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-05-07T04:10:01Z","title_canon_sha256":"534cf54f284e05367a12133c2475640b5fa33485464c8735611a1a90cf937009"},"schema_version":"1.0","source":{"id":"2405.03991","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03991","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03991v2","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03991","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"6CANMG7VWKCX","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"6CANMG7VWKCXF2V3","created_at":"2026-07-05T09:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"6CANMG7V","created_at":"2026-07-05T09:30:13Z"}],"graph_snapshots":[{"event_id":"sha256:1eae110373b4d6a31f6cb6878f5dae5dac859957733f3b0a27c1ba6f3b2a09e1","target":"graph","created_at":"2026-07-05T09:30:13Z","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/2405.03991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Binary code is pervasive, and binary analysis is a key task in reverse engineering, malware classification, and vulnerability discovery. Unfortunately, while there exist large corpora of malicious binaries, obtaining high-quality corpora of benign binaries for modern systems has proven challenging (e.g., due to licensing issues). Consequently, machine learning based pipelines for binary analysis utilize either costly commercial corpora (e.g., VirusTotal) or open-source binaries (e.g., coreutils) available in limited quantities. To address these issues, we present Assemblage: an extensible clou","authors_text":"Chang Liu, Edward Raff, James Holt, Kristopher Micinski, Maya Fuchs, Rebecca Saul, Townsend Southard Pantano, Yihao Sun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-05-07T04:10:01Z","title":"Assemblage: Automatic Binary Dataset Construction for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03991","kind":"arxiv","version":2},"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:f1709d58e502966fa08fe17c05c2225b30e523e9c970f42c8fb89a2bc4f2e4aa","target":"record","created_at":"2026-07-05T09:30:13Z","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":"72ef74f3453265f493918900e4eb49a84b4d20136fc132ce6ffef9cfcac207e1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-05-07T04:10:01Z","title_canon_sha256":"534cf54f284e05367a12133c2475640b5fa33485464c8735611a1a90cf937009"},"schema_version":"1.0","source":{"id":"2405.03991","kind":"arxiv","version":2}},"canonical_sha256":"f080d61bf5b28572eabba9a5e9cb8e9ccc7310d4f32174fdbb346426f8c52c08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f080d61bf5b28572eabba9a5e9cb8e9ccc7310d4f32174fdbb346426f8c52c08","first_computed_at":"2026-07-05T09:30:13.632672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:13.632672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CKmiDhH8LQ+v3Py7/S/ZCeYy4DbNjxmIXV5lWeHbVDMUc0EXHOFspdHzfac5dABUrNWRJbc76alaYkhxiFIXAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:13.633142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03991","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1709d58e502966fa08fe17c05c2225b30e523e9c970f42c8fb89a2bc4f2e4aa","sha256:1eae110373b4d6a31f6cb6878f5dae5dac859957733f3b0a27c1ba6f3b2a09e1"],"state_sha256":"9613b405343f0c4c7170304b95daca2a82ac81426ba635819a509a509a892ccc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGn36a0+zyF2R/71FHtbNtdzWjc2YZ7Lh9Fi2rU3Zf/dRP5TWjDLMLT0L+iJjfHk4PTjFY3qelDIHifjoL7VDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T10:12:43.262157Z","bundle_sha256":"e376a559f58c14c93588a500c9fcd19efba7ae41badea6707981dc70577f84a5"}}