{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WVTPLFSOOQMKBTCYLX32VBTG7I","short_pith_number":"pith:WVTPLFSO","schema_version":"1.0","canonical_sha256":"b566f5964e7418a0cc585df7aa8666fa27c1424e75f623b956975a7f88a42200","source":{"kind":"arxiv","id":"2312.00413","version":1},"attestation_state":"computed","paper":{"title":"Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.SE","authors_text":"An Guo, Chunrong Fang, Mengzhe Yuan, Quanjun Zhang, Weisong Sun, Xiang Chen, Yang Liu, Yuchen Chen, Yudu You, Yun Miao, Zhenyu Chen","submitted_at":"2023-12-01T08:37:27Z","abstract_excerpt":"Programming language understanding and representation (a.k.a code representation learning) has always been a hot and challenging task in software engineering. It aims to apply deep learning techniques to produce numerical representations of the source code features while preserving its semantics. These representations can be used for facilitating subsequent code-related tasks. The abstract syntax tree (AST), a fundamental code feature, illustrates the syntactic information of the source code and has been widely used in code representation learning. However, there is still a lack of systematic "},"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":"2312.00413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-12-01T08:37:27Z","cross_cats_sorted":["cs.AI","cs.CL","cs.PL"],"title_canon_sha256":"2780c85f2c4ca38111706d4eedee543d6fa279950c33e82f5d98345f62549142","abstract_canon_sha256":"e868684ee5862b5e8dff0c22ebb9465f79bbaedc1ad7936af266202edb71e25c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:09.111008Z","signature_b64":"Zyf2uzK8caP3oWX09z8xDIDr/titG8xDBb9TNlSJy63mKD2mXadU9nHyWDZqopgAN+kkmgt+hTsSpzrEyTVBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b566f5964e7418a0cc585df7aa8666fa27c1424e75f623b956975a7f88a42200","last_reissued_at":"2026-07-05T07:19:09.110420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:09.110420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Abstract Syntax Tree for Programming Language Understanding and Representation: How Far Are We?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.SE","authors_text":"An Guo, Chunrong Fang, Mengzhe Yuan, Quanjun Zhang, Weisong Sun, Xiang Chen, Yang Liu, Yuchen Chen, Yudu You, Yun Miao, Zhenyu Chen","submitted_at":"2023-12-01T08:37:27Z","abstract_excerpt":"Programming language understanding and representation (a.k.a code representation learning) has always been a hot and challenging task in software engineering. It aims to apply deep learning techniques to produce numerical representations of the source code features while preserving its semantics. These representations can be used for facilitating subsequent code-related tasks. The abstract syntax tree (AST), a fundamental code feature, illustrates the syntactic information of the source code and has been widely used in code representation learning. However, there is still a lack of systematic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00413","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/2312.00413/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":"2312.00413","created_at":"2026-07-05T07:19:09.110497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00413v1","created_at":"2026-07-05T07:19:09.110497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00413","created_at":"2026-07-05T07:19:09.110497+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVTPLFSOOQMK","created_at":"2026-07-05T07:19:09.110497+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVTPLFSOOQMKBTCY","created_at":"2026-07-05T07:19:09.110497+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVTPLFSO","created_at":"2026-07-05T07:19:09.110497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01425","citing_title":"Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16420","citing_title":"Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03356","citing_title":"POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00504","citing_title":"EnCoDe: Energy Estimation of Source Code At Design-Time","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21051","citing_title":"Residual Risk Analysis in Benign Code: How Far Are We? A Multi-Model Semantic and Structural Similarity Approach","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I","json":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I.json","graph_json":"https://pith.science/api/pith-number/WVTPLFSOOQMKBTCYLX32VBTG7I/graph.json","events_json":"https://pith.science/api/pith-number/WVTPLFSOOQMKBTCYLX32VBTG7I/events.json","paper":"https://pith.science/paper/WVTPLFSO"},"agent_actions":{"view_html":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I","download_json":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I.json","view_paper":"https://pith.science/paper/WVTPLFSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00413&json=true","fetch_graph":"https://pith.science/api/pith-number/WVTPLFSOOQMKBTCYLX32VBTG7I/graph.json","fetch_events":"https://pith.science/api/pith-number/WVTPLFSOOQMKBTCYLX32VBTG7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I/action/storage_attestation","attest_author":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I/action/author_attestation","sign_citation":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I/action/citation_signature","submit_replication":"https://pith.science/pith/WVTPLFSOOQMKBTCYLX32VBTG7I/action/replication_record"}},"created_at":"2026-07-05T07:19:09.110497+00:00","updated_at":"2026-07-05T07:19:09.110497+00:00"}