{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LRPDDUO5N4CSGGKRWGNBESWUFB","short_pith_number":"pith:LRPDDUO5","schema_version":"1.0","canonical_sha256":"5c5e31d1dd6f05231951b19a124ad4284702af682f890c14458b249b8063a76b","source":{"kind":"arxiv","id":"2607.09452","version":1},"attestation_state":"computed","paper":{"title":"Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Benjamin C. M. Fung, Charles Edward Gagnon, Philippe Charland, Steven H. H. Ding","submitted_at":"2026-07-10T14:22:30Z","abstract_excerpt":"We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning. Our binary-to-source-code retrieval method attempts to identify the source function from a source code database, rather than generating approximate decompiled pseudocode. It extracts anchors such as strings, constants, external calls, and available function names using Ghidra, retrieves candidate files via an inverted-index search database, narrows candidates to likely function snippets, and re-ranks "},"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":"2607.09452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-10T14:22:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a29de3be0bccdba2ed51fd65958e4b2e9672464b293ed7c55be6f1b93bc97638","abstract_canon_sha256":"7ab2b9453eef32ef325d2db4f0a36eea055400f5a138906a811261dedc4e5ede"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:16.066681Z","signature_b64":"PMEvZ4hf0f7qYMy3hZ/FvOELlAe7/hwZgNxl4DsqzsBv4DlxbEOtA5h+Zzpw4osE9N4pPRM7HgTmy1rDaedEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c5e31d1dd6f05231951b19a124ad4284702af682f890c14458b249b8063a76b","last_reissued_at":"2026-07-13T01:19:16.065545Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:16.065545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Benjamin C. M. Fung, Charles Edward Gagnon, Philippe Charland, Steven H. H. Ding","submitted_at":"2026-07-10T14:22:30Z","abstract_excerpt":"We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning. Our binary-to-source-code retrieval method attempts to identify the source function from a source code database, rather than generating approximate decompiled pseudocode. It extracts anchors such as strings, constants, external calls, and available function names using Ghidra, retrieves candidate files via an inverted-index search database, narrows candidates to likely function snippets, and re-ranks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09452","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/2607.09452/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":"2607.09452","created_at":"2026-07-13T01:19:16.066114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09452v1","created_at":"2026-07-13T01:19:16.066114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09452","created_at":"2026-07-13T01:19:16.066114+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRPDDUO5N4CS","created_at":"2026-07-13T01:19:16.066114+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRPDDUO5N4CSGGKR","created_at":"2026-07-13T01:19:16.066114+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRPDDUO5","created_at":"2026-07-13T01:19:16.066114+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/LRPDDUO5N4CSGGKRWGNBESWUFB","json":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB.json","graph_json":"https://pith.science/api/pith-number/LRPDDUO5N4CSGGKRWGNBESWUFB/graph.json","events_json":"https://pith.science/api/pith-number/LRPDDUO5N4CSGGKRWGNBESWUFB/events.json","paper":"https://pith.science/paper/LRPDDUO5"},"agent_actions":{"view_html":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB","download_json":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB.json","view_paper":"https://pith.science/paper/LRPDDUO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09452&json=true","fetch_graph":"https://pith.science/api/pith-number/LRPDDUO5N4CSGGKRWGNBESWUFB/graph.json","fetch_events":"https://pith.science/api/pith-number/LRPDDUO5N4CSGGKRWGNBESWUFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB/action/storage_attestation","attest_author":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB/action/author_attestation","sign_citation":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB/action/citation_signature","submit_replication":"https://pith.science/pith/LRPDDUO5N4CSGGKRWGNBESWUFB/action/replication_record"}},"created_at":"2026-07-13T01:19:16.066114+00:00","updated_at":"2026-07-13T01:19:16.066114+00:00"}