{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TLVFB6CWEQXM6R7MSR4BKHUVWF","short_pith_number":"pith:TLVFB6CW","schema_version":"1.0","canonical_sha256":"9aea50f856242ecf47ec9478151e95b16ad1fca024cc51773a9dc30bebc11a2f","source":{"kind":"arxiv","id":"2103.11318","version":1},"attestation_state":"computed","paper":{"title":"Language-Agnostic Representation Learning of Source Code from Structure and Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Daniel Z\\\"ugner, Jure Leskovec, Michele Catasta, Stephan G\\\"unnemann, Tobias Kirschstein","submitted_at":"2021-03-21T06:46:06Z","abstract_excerpt":"Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine learning models have relied predominantly either on Structure or Context. We propose a new model, which jointly learns on Context and Structure of source code. In contrast to previous approaches, our model uses only language-agnostic features, i.e., source code and features that can be computed directly from the AST. Besides obtaining state-of-the-art on monolingual code summarization on all five programming languages"},"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":"2103.11318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-21T06:46:06Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"f3c2b384992972dac85a363d2729bce23fd4aff71896ba96bc276c8dd223584d","abstract_canon_sha256":"3d26049835ea45b8ce55e42612dfbddd445cf6a6a2e463c14f4847e3456c7fa9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:59.186547Z","signature_b64":"ZB2jCXTADprJvO3WUaSwL3cFOsI1fIrvRG+ceYHNoMvCaOpefyU/Ywk5yYW0SKKv/V6l6+okcdqVlGZNJSJwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aea50f856242ecf47ec9478151e95b16ad1fca024cc51773a9dc30bebc11a2f","last_reissued_at":"2026-07-05T02:24:59.186154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:59.186154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Agnostic Representation Learning of Source Code from Structure and Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Daniel Z\\\"ugner, Jure Leskovec, Michele Catasta, Stephan G\\\"unnemann, Tobias Kirschstein","submitted_at":"2021-03-21T06:46:06Z","abstract_excerpt":"Source code (Context) and its parsed abstract syntax tree (AST; Structure) are two complementary representations of the same computer program. Traditionally, designers of machine learning models have relied predominantly either on Structure or Context. We propose a new model, which jointly learns on Context and Structure of source code. In contrast to previous approaches, our model uses only language-agnostic features, i.e., source code and features that can be computed directly from the AST. Besides obtaining state-of-the-art on monolingual code summarization on all five programming languages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11318","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/2103.11318/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":"2103.11318","created_at":"2026-07-05T02:24:59.186222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.11318v1","created_at":"2026-07-05T02:24:59.186222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11318","created_at":"2026-07-05T02:24:59.186222+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLVFB6CWEQXM","created_at":"2026-07-05T02:24:59.186222+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLVFB6CWEQXM6R7M","created_at":"2026-07-05T02:24:59.186222+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLVFB6CW","created_at":"2026-07-05T02:24:59.186222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00413","citing_title":"Recommending Variable Names for Extract Local Variable Refactorings","ref_index":91,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF","json":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF.json","graph_json":"https://pith.science/api/pith-number/TLVFB6CWEQXM6R7MSR4BKHUVWF/graph.json","events_json":"https://pith.science/api/pith-number/TLVFB6CWEQXM6R7MSR4BKHUVWF/events.json","paper":"https://pith.science/paper/TLVFB6CW"},"agent_actions":{"view_html":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF","download_json":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF.json","view_paper":"https://pith.science/paper/TLVFB6CW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.11318&json=true","fetch_graph":"https://pith.science/api/pith-number/TLVFB6CWEQXM6R7MSR4BKHUVWF/graph.json","fetch_events":"https://pith.science/api/pith-number/TLVFB6CWEQXM6R7MSR4BKHUVWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF/action/storage_attestation","attest_author":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF/action/author_attestation","sign_citation":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF/action/citation_signature","submit_replication":"https://pith.science/pith/TLVFB6CWEQXM6R7MSR4BKHUVWF/action/replication_record"}},"created_at":"2026-07-05T02:24:59.186222+00:00","updated_at":"2026-07-05T02:24:59.186222+00:00"}