{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LR5VFQBSTKIK5EL3QJJFUYTIOK","short_pith_number":"pith:LR5VFQBS","schema_version":"1.0","canonical_sha256":"5c7b52c0329a90ae917b82525a6268728d883f5ac402acc13b88962cd3e575ff","source":{"kind":"arxiv","id":"2608.02084","version":1},"attestation_state":"computed","paper":{"title":"Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.SE","authors_text":"Johannes Kinder, Samuel Valenzuela","submitted_at":"2026-08-03T11:44:09Z","abstract_excerpt":"Binary function embedding models are trained to encode the semantics of binary code in such a way that they can be generalized to a variety of reverse engineering tasks, such as binary code search, vulnerability detection, or malware classification. While many models only take the function in question as contextual input, there have been successful attempts to improve function embeddings by leveraging information from the call graph. In this study, we dissect the implications of these embedding refinements. We conduct experiments using a range of graph-based models on the embeddings generated "},"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":"2608.02084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-03T11:44:09Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"4bccd4d288a81dd66ce81b09e2a8937e95daa8fd10eb7cb5ddfba66ac3ec8602","abstract_canon_sha256":"5bcd4a2538b6143033c81f95960fa447336d6312c7e991efb9a3ffc1ecf837d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:48.711133Z","signature_b64":"O5uUtoDxriUnWc3wCIGTKJkMmrK6Th6e6GH6Rl/OrBQ8DEhYSTWs5JlA+uKSbsV+UO0roGxbqV2WMyfjOBEwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7b52c0329a90ae917b82525a6268728d883f5ac402acc13b88962cd3e575ff","last_reissued_at":"2026-08-04T02:10:48.709634Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:48.709634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pretraining on Call Graphs: When Binary Analysis Tasks Profit From Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.SE","authors_text":"Johannes Kinder, Samuel Valenzuela","submitted_at":"2026-08-03T11:44:09Z","abstract_excerpt":"Binary function embedding models are trained to encode the semantics of binary code in such a way that they can be generalized to a variety of reverse engineering tasks, such as binary code search, vulnerability detection, or malware classification. While many models only take the function in question as contextual input, there have been successful attempts to improve function embeddings by leveraging information from the call graph. In this study, we dissect the implications of these embedding refinements. We conduct experiments using a range of graph-based models on the embeddings generated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02084","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/2608.02084/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":"2608.02084","created_at":"2026-08-04T02:10:48.711187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02084v1","created_at":"2026-08-04T02:10:48.711187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02084","created_at":"2026-08-04T02:10:48.711187+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR5VFQBSTKIK","created_at":"2026-08-04T02:10:48.711187+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR5VFQBSTKIK5EL3","created_at":"2026-08-04T02:10:48.711187+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR5VFQBS","created_at":"2026-08-04T02:10:48.711187+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/LR5VFQBSTKIK5EL3QJJFUYTIOK","json":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK.json","graph_json":"https://pith.science/api/pith-number/LR5VFQBSTKIK5EL3QJJFUYTIOK/graph.json","events_json":"https://pith.science/api/pith-number/LR5VFQBSTKIK5EL3QJJFUYTIOK/events.json","paper":"https://pith.science/paper/LR5VFQBS"},"agent_actions":{"view_html":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK","download_json":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK.json","view_paper":"https://pith.science/paper/LR5VFQBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02084&json=true","fetch_graph":"https://pith.science/api/pith-number/LR5VFQBSTKIK5EL3QJJFUYTIOK/graph.json","fetch_events":"https://pith.science/api/pith-number/LR5VFQBSTKIK5EL3QJJFUYTIOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK/action/storage_attestation","attest_author":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK/action/author_attestation","sign_citation":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK/action/citation_signature","submit_replication":"https://pith.science/pith/LR5VFQBSTKIK5EL3QJJFUYTIOK/action/replication_record"}},"created_at":"2026-08-04T02:10:48.711187+00:00","updated_at":"2026-08-04T02:10:48.711187+00:00"}