{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IF4E4SYG22BIFIUIMBBJWTFM65","short_pith_number":"pith:IF4E4SYG","schema_version":"1.0","canonical_sha256":"41784e4b06d68282a28860429b4cacf77c4ee1f3e172969d041c10694df3ad8d","source":{"kind":"arxiv","id":"2608.11766","version":1},"attestation_state":"computed","paper":{"title":"Instruction Alignment for Binary Code Representation Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SE","authors_text":"Huaijin Wang, Shuai Wang","submitted_at":"2026-08-12T08:07:26Z","abstract_excerpt":"Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-level embeddings that capture coarse-grained semantic relationships between binary functions, but they largely ignore fine-grained instruction-level correspondences. This limitation misses valuable supervision signals available from compiler debug information, which can support the learning of more accurate and interpretable binary code representations.\n  We propose to leverage instruction alignment knowledge to further improve binary code representa"},"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":"2608.11766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-12T08:07:26Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"ae1c6d0df193d6327807e5ee7cc38d16bf15fba20c02e770d77138dda8dda5ef","abstract_canon_sha256":"890b6637dfc32b1ade5d47dbbfcd717fc80a38efcfc89325c3da1eac5cd3bba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:28:07.873800Z","signature_b64":"/iRBIJnpAzBW0gA5LjX3319JzRD8PRVwsvbrJdRvtg62d6RaH+dtWWjRmbEQCLxomqBhPXWem7bWdHySnKMYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41784e4b06d68282a28860429b4cacf77c4ee1f3e172969d041c10694df3ad8d","last_reissued_at":"2026-08-13T01:28:07.871474Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:28:07.871474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instruction Alignment for Binary Code Representation Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SE","authors_text":"Huaijin Wang, Shuai Wang","submitted_at":"2026-08-12T08:07:26Z","abstract_excerpt":"Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-level embeddings that capture coarse-grained semantic relationships between binary functions, but they largely ignore fine-grained instruction-level correspondences. This limitation misses valuable supervision signals available from compiler debug information, which can support the learning of more accurate and interpretable binary code representations.\n  We propose to leverage instruction alignment knowledge to further improve binary code representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11766","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/2608.11766/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":"2608.11766","created_at":"2026-08-13T01:28:07.872695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11766v1","created_at":"2026-08-13T01:28:07.872695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11766","created_at":"2026-08-13T01:28:07.872695+00:00"},{"alias_kind":"pith_short_12","alias_value":"IF4E4SYG22BI","created_at":"2026-08-13T01:28:07.872695+00:00"},{"alias_kind":"pith_short_16","alias_value":"IF4E4SYG22BIFIUI","created_at":"2026-08-13T01:28:07.872695+00:00"},{"alias_kind":"pith_short_8","alias_value":"IF4E4SYG","created_at":"2026-08-13T01:28:07.872695+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/IF4E4SYG22BIFIUIMBBJWTFM65","json":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65.json","graph_json":"https://pith.science/api/pith-number/IF4E4SYG22BIFIUIMBBJWTFM65/graph.json","events_json":"https://pith.science/api/pith-number/IF4E4SYG22BIFIUIMBBJWTFM65/events.json","paper":"https://pith.science/paper/IF4E4SYG"},"agent_actions":{"view_html":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65","download_json":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65.json","view_paper":"https://pith.science/paper/IF4E4SYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11766&json=true","fetch_graph":"https://pith.science/api/pith-number/IF4E4SYG22BIFIUIMBBJWTFM65/graph.json","fetch_events":"https://pith.science/api/pith-number/IF4E4SYG22BIFIUIMBBJWTFM65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65/action/storage_attestation","attest_author":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65/action/author_attestation","sign_citation":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65/action/citation_signature","submit_replication":"https://pith.science/pith/IF4E4SYG22BIFIUIMBBJWTFM65/action/replication_record"}},"created_at":"2026-08-13T01:28:07.872695+00:00","updated_at":"2026-08-13T01:28:07.872695+00:00"}