{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MSWIEUQPP2JMLHJ66E2QUUAM4J","short_pith_number":"pith:MSWIEUQP","schema_version":"1.0","canonical_sha256":"64ac82520f7e92c59d3ef1350a500ce263cb8c4edbce68286acd576cc18603aa","source":{"kind":"arxiv","id":"2206.08713","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Impact of Source Code Parsers on ML4SE Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Egor Bogomolov, Egor Spirin, Ilya Utkin, Timofey Bryksin","submitted_at":"2022-06-17T12:10:04Z","abstract_excerpt":"As researchers and practitioners apply Machine Learning to increasingly more software engineering problems, the approaches they use become more sophisticated. A lot of modern approaches utilize internal code structure in the form of an abstract syntax tree (AST) or its extensions: path-based representation, complex graph combining AST with additional edges. Even though the process of extracting ASTs from code can be done with different parsers, the impact of choosing a parser on the final model quality remains unstudied. Moreover, researchers often omit the exact details of extracting particul"},"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":"2206.08713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2022-06-17T12:10:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aa62074ebbc87414e67d3674fe40eb2ba19eba97ec359d0c360011966de84cb3","abstract_canon_sha256":"d243b92dd5cf6eefb6fa659da29c27bde3b9afe95f429a0c117628e0ff241468"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:42.362067Z","signature_b64":"6I9m+H0SD+u3A9/u+cljpbzJ0TOM+AFqz4mLgKuw96MBnopjJSO6SbNDEPS37UcP8AISuNWgoY06KcWVUtkZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64ac82520f7e92c59d3ef1350a500ce263cb8c4edbce68286acd576cc18603aa","last_reissued_at":"2026-07-05T04:32:42.361531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:42.361531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Impact of Source Code Parsers on ML4SE Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Egor Bogomolov, Egor Spirin, Ilya Utkin, Timofey Bryksin","submitted_at":"2022-06-17T12:10:04Z","abstract_excerpt":"As researchers and practitioners apply Machine Learning to increasingly more software engineering problems, the approaches they use become more sophisticated. A lot of modern approaches utilize internal code structure in the form of an abstract syntax tree (AST) or its extensions: path-based representation, complex graph combining AST with additional edges. Even though the process of extracting ASTs from code can be done with different parsers, the impact of choosing a parser on the final model quality remains unstudied. Moreover, researchers often omit the exact details of extracting particul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08713","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/2206.08713/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":"2206.08713","created_at":"2026-07-05T04:32:42.361593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08713v1","created_at":"2026-07-05T04:32:42.361593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08713","created_at":"2026-07-05T04:32:42.361593+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSWIEUQPP2JM","created_at":"2026-07-05T04:32:42.361593+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSWIEUQPP2JMLHJ6","created_at":"2026-07-05T04:32:42.361593+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSWIEUQP","created_at":"2026-07-05T04:32:42.361593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.07520","citing_title":"On the Effectiveness of Code Representation in Deep Learning-Based Automated Patch Correctness Assessment","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J","json":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J.json","graph_json":"https://pith.science/api/pith-number/MSWIEUQPP2JMLHJ66E2QUUAM4J/graph.json","events_json":"https://pith.science/api/pith-number/MSWIEUQPP2JMLHJ66E2QUUAM4J/events.json","paper":"https://pith.science/paper/MSWIEUQP"},"agent_actions":{"view_html":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J","download_json":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J.json","view_paper":"https://pith.science/paper/MSWIEUQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08713&json=true","fetch_graph":"https://pith.science/api/pith-number/MSWIEUQPP2JMLHJ66E2QUUAM4J/graph.json","fetch_events":"https://pith.science/api/pith-number/MSWIEUQPP2JMLHJ66E2QUUAM4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J/action/storage_attestation","attest_author":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J/action/author_attestation","sign_citation":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J/action/citation_signature","submit_replication":"https://pith.science/pith/MSWIEUQPP2JMLHJ66E2QUUAM4J/action/replication_record"}},"created_at":"2026-07-05T04:32:42.361593+00:00","updated_at":"2026-07-05T04:32:42.361593+00:00"}