{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EJMQQUN3A4AIWSSMCFMJQUK43P","short_pith_number":"pith:EJMQQUN3","schema_version":"1.0","canonical_sha256":"22590851bb07008b4a4c115898515cdbfae7469cd84f1cb82b17335c3a779b87","source":{"kind":"arxiv","id":"2212.05976","version":2},"attestation_state":"computed","paper":{"title":"DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecode","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"(2) Singapore Management University, (3) Kyungpook National University), David Lo (2), Dongsun Kim (3), Jacques Klein (1) ((1) University of Luxembourg, Kevin Allix (1), Kisub Kim (2), Tegawend\\'e F. Bissyand\\'e (1), Tiezhu Sun (1), Xin Zhou (2)","submitted_at":"2022-12-12T15:32:31Z","abstract_excerpt":"The automation of a large number of software engineering tasks is becoming possible thanks to Machine Learning (ML). Central to applying ML to software artifacts (like source or executable code) is converting them into forms suitable for learning. Traditionally, researchers have relied on manually selected features, based on expert knowledge which is sometimes imprecise and generally incomplete. Representation learning has allowed ML to automatically choose suitable representations and relevant features. Yet, for Android-related tasks, existing models like apk2vec focus on whole-app levels, or"},"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":"2212.05976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-12-12T15:32:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6221dc2e97c6da23721d4153318755527b03a2e9bb3a2fe42379f98bc055de07","abstract_canon_sha256":"cac99363b2e2c451abaf5b0ad95f3b8b538d2d5929e9f51cbe3b1d0e0ccbb9a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:05.596434Z","signature_b64":"PQyO9pqmVd7wVdyIR2hT5sow1VnMoATpqfaXCLnQDEm/obxWLwVTpERXm/OOfZnc1ry9WQ09V922ajVuWNm0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22590851bb07008b4a4c115898515cdbfae7469cd84f1cb82b17335c3a779b87","last_reissued_at":"2026-07-05T06:44:05.595858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:05.595858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecode","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"(2) Singapore Management University, (3) Kyungpook National University), David Lo (2), Dongsun Kim (3), Jacques Klein (1) ((1) University of Luxembourg, Kevin Allix (1), Kisub Kim (2), Tegawend\\'e F. Bissyand\\'e (1), Tiezhu Sun (1), Xin Zhou (2)","submitted_at":"2022-12-12T15:32:31Z","abstract_excerpt":"The automation of a large number of software engineering tasks is becoming possible thanks to Machine Learning (ML). Central to applying ML to software artifacts (like source or executable code) is converting them into forms suitable for learning. Traditionally, researchers have relied on manually selected features, based on expert knowledge which is sometimes imprecise and generally incomplete. Representation learning has allowed ML to automatically choose suitable representations and relevant features. Yet, for Android-related tasks, existing models like apk2vec focus on whole-app levels, or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05976","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/2212.05976/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":"2212.05976","created_at":"2026-07-05T06:44:05.595937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.05976v2","created_at":"2026-07-05T06:44:05.595937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05976","created_at":"2026-07-05T06:44:05.595937+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJMQQUN3A4AI","created_at":"2026-07-05T06:44:05.595937+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJMQQUN3A4AIWSSM","created_at":"2026-07-05T06:44:05.595937+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJMQQUN3","created_at":"2026-07-05T06:44:05.595937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13629","citing_title":"Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P","json":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P.json","graph_json":"https://pith.science/api/pith-number/EJMQQUN3A4AIWSSMCFMJQUK43P/graph.json","events_json":"https://pith.science/api/pith-number/EJMQQUN3A4AIWSSMCFMJQUK43P/events.json","paper":"https://pith.science/paper/EJMQQUN3"},"agent_actions":{"view_html":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P","download_json":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P.json","view_paper":"https://pith.science/paper/EJMQQUN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.05976&json=true","fetch_graph":"https://pith.science/api/pith-number/EJMQQUN3A4AIWSSMCFMJQUK43P/graph.json","fetch_events":"https://pith.science/api/pith-number/EJMQQUN3A4AIWSSMCFMJQUK43P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P/action/storage_attestation","attest_author":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P/action/author_attestation","sign_citation":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P/action/citation_signature","submit_replication":"https://pith.science/pith/EJMQQUN3A4AIWSSMCFMJQUK43P/action/replication_record"}},"created_at":"2026-07-05T06:44:05.595937+00:00","updated_at":"2026-07-05T06:44:05.595937+00:00"}