{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JSMJS2LXKUL32NZRJODVF6ENFP","short_pith_number":"pith:JSMJS2LX","schema_version":"1.0","canonical_sha256":"4c989969775517bd37314b8752f88d2bdfdb33108b666dc46a683277366c5865","source":{"kind":"arxiv","id":"2208.08643","version":2},"attestation_state":"computed","paper":{"title":"Learning Program Representations with a Tree-Structured Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Anran Li, Ge Li, Kechi Zhang, Shangqing Liu, Wenhan Wang, Yang Liu, Zhi Jin","submitted_at":"2022-08-18T05:42:01Z","abstract_excerpt":"Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to learn from tree-structured program representations, e.g., abstract syntax tree (AST) and concrete syntax tree (CST). However, most neural architectures either fail to capture long-range dependencies which are ubiquitous in programs, or cannot learn effective representations for syntax tree nodes, making them incapable of performing the node-level prediction tasks, e.g., bug localization. In this paper, we propose Tre"},"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":"2208.08643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2022-08-18T05:42:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f2625778329411decc8587e41b4b93679c57bb422039337898f49842b73dd87","abstract_canon_sha256":"44cdaccde9d5fbefd56543fb8d9b91e7de6a274b5eaf1f512abb749c47b7cced"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:16.493100Z","signature_b64":"dylcYcEqQvgO9futLvy6O/uWpfkJoEZU3+92l/R/IDddLAdx97MxaQj7B54vkzBZJa17cAa/posIzKglLFH/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c989969775517bd37314b8752f88d2bdfdb33108b666dc46a683277366c5865","last_reissued_at":"2026-07-05T05:31:16.492630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:16.492630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Program Representations with a Tree-Structured Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Anran Li, Ge Li, Kechi Zhang, Shangqing Liu, Wenhan Wang, Yang Liu, Zhi Jin","submitted_at":"2022-08-18T05:42:01Z","abstract_excerpt":"Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to learn from tree-structured program representations, e.g., abstract syntax tree (AST) and concrete syntax tree (CST). However, most neural architectures either fail to capture long-range dependencies which are ubiquitous in programs, or cannot learn effective representations for syntax tree nodes, making them incapable of performing the node-level prediction tasks, e.g., bug localization. In this paper, we propose Tre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08643","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/2208.08643/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":"2208.08643","created_at":"2026-07-05T05:31:16.492686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08643v2","created_at":"2026-07-05T05:31:16.492686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08643","created_at":"2026-07-05T05:31:16.492686+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSMJS2LXKUL3","created_at":"2026-07-05T05:31:16.492686+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSMJS2LXKUL32NZR","created_at":"2026-07-05T05:31:16.492686+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSMJS2LX","created_at":"2026-07-05T05:31:16.492686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.12138","citing_title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP","json":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP.json","graph_json":"https://pith.science/api/pith-number/JSMJS2LXKUL32NZRJODVF6ENFP/graph.json","events_json":"https://pith.science/api/pith-number/JSMJS2LXKUL32NZRJODVF6ENFP/events.json","paper":"https://pith.science/paper/JSMJS2LX"},"agent_actions":{"view_html":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP","download_json":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP.json","view_paper":"https://pith.science/paper/JSMJS2LX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08643&json=true","fetch_graph":"https://pith.science/api/pith-number/JSMJS2LXKUL32NZRJODVF6ENFP/graph.json","fetch_events":"https://pith.science/api/pith-number/JSMJS2LXKUL32NZRJODVF6ENFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP/action/storage_attestation","attest_author":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP/action/author_attestation","sign_citation":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP/action/citation_signature","submit_replication":"https://pith.science/pith/JSMJS2LXKUL32NZRJODVF6ENFP/action/replication_record"}},"created_at":"2026-07-05T05:31:16.492686+00:00","updated_at":"2026-07-05T05:31:16.492686+00:00"}