{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YXNZBO35J4TANGHSV5GLSQJF6V","short_pith_number":"pith:YXNZBO35","schema_version":"1.0","canonical_sha256":"c5db90bb7d4f260698f2af4cb94125f56a6a637a9290fb008d5227472f11ce36","source":{"kind":"arxiv","id":"2509.23449","version":2},"attestation_state":"computed","paper":{"title":"Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.SE"],"primary_cat":"cs.AI","authors_text":"Benjamin C. M. Fung, Charles E. Gagnon, Philippe Charland, Steven H. H. Ding","submitted_at":"2025-09-27T18:34:32Z","abstract_excerpt":"Binary code similarity detection is a core task in reverse engineering. It supports malware analysis and vulnerability discovery by identifying semantically similar code in different contexts. Modern methods have progressed from manually engineered features to vector representations. Hand-crafted statistics (e.g., operation ratios) are interpretable, but shallow and fail to generalize. Embedding-based methods overcome this by learning robust cross-setting representations, but these representations are opaque vectors that prevent rapid verification. They also face a scalability-accuracy trade-o"},"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":"2509.23449","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-27T18:34:32Z","cross_cats_sorted":["cs.CR","cs.SE"],"title_canon_sha256":"5825e95340bb92f28f7719a2655e49d56741386c5ac88432bc12bca9ccc6b2fb","abstract_canon_sha256":"feebef7928e1e67af7691cefac4cad0001e3511f6b079f9231a0147dffedfabc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:03.093029Z","signature_b64":"txgbLLMSmnu8BG/1tNDxBpfMuprbfQKqzUpSOb5zBgTWZ/rLwPeS7sUuNk16s+tvQNEoRjeloCmdCW3oBlqCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5db90bb7d4f260698f2af4cb94125f56a6a637a9290fb008d5227472f11ce36","last_reissued_at":"2026-07-13T01:20:03.090378Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:03.090378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Embeddings: Interpretable Feature Extraction for Binary Code Similarity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.SE"],"primary_cat":"cs.AI","authors_text":"Benjamin C. M. Fung, Charles E. Gagnon, Philippe Charland, Steven H. H. Ding","submitted_at":"2025-09-27T18:34:32Z","abstract_excerpt":"Binary code similarity detection is a core task in reverse engineering. It supports malware analysis and vulnerability discovery by identifying semantically similar code in different contexts. Modern methods have progressed from manually engineered features to vector representations. Hand-crafted statistics (e.g., operation ratios) are interpretable, but shallow and fail to generalize. Embedding-based methods overcome this by learning robust cross-setting representations, but these representations are opaque vectors that prevent rapid verification. They also face a scalability-accuracy trade-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.23449","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/2509.23449/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":"2509.23449","created_at":"2026-07-13T01:20:03.091883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.23449v2","created_at":"2026-07-13T01:20:03.091883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.23449","created_at":"2026-07-13T01:20:03.091883+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXNZBO35J4TA","created_at":"2026-07-13T01:20:03.091883+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXNZBO35J4TANGHS","created_at":"2026-07-13T01:20:03.091883+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXNZBO35","created_at":"2026-07-13T01:20:03.091883+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/YXNZBO35J4TANGHSV5GLSQJF6V","json":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V.json","graph_json":"https://pith.science/api/pith-number/YXNZBO35J4TANGHSV5GLSQJF6V/graph.json","events_json":"https://pith.science/api/pith-number/YXNZBO35J4TANGHSV5GLSQJF6V/events.json","paper":"https://pith.science/paper/YXNZBO35"},"agent_actions":{"view_html":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V","download_json":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V.json","view_paper":"https://pith.science/paper/YXNZBO35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.23449&json=true","fetch_graph":"https://pith.science/api/pith-number/YXNZBO35J4TANGHSV5GLSQJF6V/graph.json","fetch_events":"https://pith.science/api/pith-number/YXNZBO35J4TANGHSV5GLSQJF6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V/action/storage_attestation","attest_author":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V/action/author_attestation","sign_citation":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V/action/citation_signature","submit_replication":"https://pith.science/pith/YXNZBO35J4TANGHSV5GLSQJF6V/action/replication_record"}},"created_at":"2026-07-13T01:20:03.091883+00:00","updated_at":"2026-07-13T01:20:03.091883+00:00"}