{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Y7ZHGMW57O2MVO5BSUHMEQOUW","short_pith_number":"pith:7Y7ZHGMW","schema_version":"1.0","canonical_sha256":"fe3f939996efdda655dd0ca876120ea5af97ad8951db10c1f6e9ad3e2f600172","source":{"kind":"arxiv","id":"2412.05049","version":1},"attestation_state":"computed","paper":{"title":"OCEAN: Open-World Contrastive Authorship Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.AI","authors_text":"Felix M\\\"achtle, Jan-Niclas Serr, Jonas Sander, Nils Loose, Thomas Eisenbarth","submitted_at":"2024-12-06T14:02:51Z","abstract_excerpt":"In an era where cyberattacks increasingly target the software supply chain, the ability to accurately attribute code authorship in binary files is critical to improving cybersecurity measures. We propose OCEAN, a contrastive learning-based system for function-level authorship attribution. OCEAN is the first framework to explore code authorship attribution on compiled binaries in an open-world and extreme scenario, where two code samples from unknown authors are compared to determine if they are developed by the same author. To evaluate OCEAN, we introduce new realistic datasets: CONAN, to impr"},"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":"2412.05049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T14:02:51Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"f70d086870c0225a79d10e0bc9bd68a89cb72b941542d68e2e8ec2bf8e9efab7","abstract_canon_sha256":"8ebdc0dd81cbb9b05669e9dfc875f275e330ce185cdf1865c40a662df975042b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:27.845331Z","signature_b64":"Mi8Kb/xBelnj9Jt1wVdOCMEAhNYICQXdo1njQn+X1kgMgwLs/abHTN+CX8DlOsNIEYeJDiJ2GPb2yRfvpFnFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe3f939996efdda655dd0ca876120ea5af97ad8951db10c1f6e9ad3e2f600172","last_reissued_at":"2026-07-05T09:45:27.844923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:27.844923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OCEAN: Open-World Contrastive Authorship Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.AI","authors_text":"Felix M\\\"achtle, Jan-Niclas Serr, Jonas Sander, Nils Loose, Thomas Eisenbarth","submitted_at":"2024-12-06T14:02:51Z","abstract_excerpt":"In an era where cyberattacks increasingly target the software supply chain, the ability to accurately attribute code authorship in binary files is critical to improving cybersecurity measures. We propose OCEAN, a contrastive learning-based system for function-level authorship attribution. OCEAN is the first framework to explore code authorship attribution on compiled binaries in an open-world and extreme scenario, where two code samples from unknown authors are compared to determine if they are developed by the same author. To evaluate OCEAN, we introduce new realistic datasets: CONAN, to impr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05049","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/2412.05049/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":"2412.05049","created_at":"2026-07-05T09:45:27.844979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05049v1","created_at":"2026-07-05T09:45:27.844979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05049","created_at":"2026-07-05T09:45:27.844979+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Y7ZHGMW57O2","created_at":"2026-07-05T09:45:27.844979+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Y7ZHGMW57O2MVO5","created_at":"2026-07-05T09:45:27.844979+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Y7ZHGMW","created_at":"2026-07-05T09:45:27.844979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.02695","citing_title":"Stylometric Defenses Against Author Impersonation in Software Repositories","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW","json":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW.json","graph_json":"https://pith.science/api/pith-number/7Y7ZHGMW57O2MVO5BSUHMEQOUW/graph.json","events_json":"https://pith.science/api/pith-number/7Y7ZHGMW57O2MVO5BSUHMEQOUW/events.json","paper":"https://pith.science/paper/7Y7ZHGMW"},"agent_actions":{"view_html":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW","download_json":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW.json","view_paper":"https://pith.science/paper/7Y7ZHGMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05049&json=true","fetch_graph":"https://pith.science/api/pith-number/7Y7ZHGMW57O2MVO5BSUHMEQOUW/graph.json","fetch_events":"https://pith.science/api/pith-number/7Y7ZHGMW57O2MVO5BSUHMEQOUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW/action/storage_attestation","attest_author":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW/action/author_attestation","sign_citation":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW/action/citation_signature","submit_replication":"https://pith.science/pith/7Y7ZHGMW57O2MVO5BSUHMEQOUW/action/replication_record"}},"created_at":"2026-07-05T09:45:27.844979+00:00","updated_at":"2026-07-05T09:45:27.844979+00:00"}