{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MJOTSXTFLSZNHZHMYXJQV5BV4O","short_pith_number":"pith:MJOTSXTF","schema_version":"1.0","canonical_sha256":"625d395e655cb2d3e4ecc5d30af435e3813467d35b5c90d1155884ca45a0ec8a","source":{"kind":"arxiv","id":"2103.03116","version":1},"attestation_state":"computed","paper":{"title":"Universal Representation for Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"George Karypis, Hoan Nguyen, Linfeng Liu, Srinivasan Sengamedu","submitted_at":"2021-03-04T15:39:25Z","abstract_excerpt":"Learning from source code usually requires a large amount of labeled data. Despite the possible scarcity of labeled data, the trained model is highly task-specific and lacks transferability to different tasks. In this work, we present effective pre-training strategies on top of a novel graph-based code representation, to produce universal representations for code. Specifically, our graph-based representation captures important semantics between code elements (e.g., control flow and data flow). We pre-train graph neural networks on the representation to extract universal code properties. The pr"},"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":"2103.03116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T15:39:25Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"2b19c996ac7c424a347ae861ad8abd3d24492b5377c309dde54284e3d2a8cfd8","abstract_canon_sha256":"9b610148104cfd6bb426a369a82bfec4697dd5ea631fa4dc6cd3a5e084250003"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:24.434298Z","signature_b64":"sLFwkWQYh9jZZ2cqqT50HIkvW3kO0P8eZV7OLrAw7HsNfMLhd30SS1K10HJXLydwstbe32pA0G381PZMJaxkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"625d395e655cb2d3e4ecc5d30af435e3813467d35b5c90d1155884ca45a0ec8a","last_reissued_at":"2026-07-05T02:20:24.433868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:24.433868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Representation for Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"George Karypis, Hoan Nguyen, Linfeng Liu, Srinivasan Sengamedu","submitted_at":"2021-03-04T15:39:25Z","abstract_excerpt":"Learning from source code usually requires a large amount of labeled data. Despite the possible scarcity of labeled data, the trained model is highly task-specific and lacks transferability to different tasks. In this work, we present effective pre-training strategies on top of a novel graph-based code representation, to produce universal representations for code. Specifically, our graph-based representation captures important semantics between code elements (e.g., control flow and data flow). We pre-train graph neural networks on the representation to extract universal code properties. The pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03116","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/2103.03116/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":"2103.03116","created_at":"2026-07-05T02:20:24.433924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03116v1","created_at":"2026-07-05T02:20:24.433924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03116","created_at":"2026-07-05T02:20:24.433924+00:00"},{"alias_kind":"pith_short_12","alias_value":"MJOTSXTFLSZN","created_at":"2026-07-05T02:20:24.433924+00:00"},{"alias_kind":"pith_short_16","alias_value":"MJOTSXTFLSZNHZHM","created_at":"2026-07-05T02:20:24.433924+00:00"},{"alias_kind":"pith_short_8","alias_value":"MJOTSXTF","created_at":"2026-07-05T02:20:24.433924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O","json":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O.json","graph_json":"https://pith.science/api/pith-number/MJOTSXTFLSZNHZHMYXJQV5BV4O/graph.json","events_json":"https://pith.science/api/pith-number/MJOTSXTFLSZNHZHMYXJQV5BV4O/events.json","paper":"https://pith.science/paper/MJOTSXTF"},"agent_actions":{"view_html":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O","download_json":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O.json","view_paper":"https://pith.science/paper/MJOTSXTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03116&json=true","fetch_graph":"https://pith.science/api/pith-number/MJOTSXTFLSZNHZHMYXJQV5BV4O/graph.json","fetch_events":"https://pith.science/api/pith-number/MJOTSXTFLSZNHZHMYXJQV5BV4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/action/storage_attestation","attest_author":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/action/author_attestation","sign_citation":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/action/citation_signature","submit_replication":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/action/replication_record"}},"created_at":"2026-07-05T02:20:24.433924+00:00","updated_at":"2026-07-05T02:20:24.433924+00:00"}