{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MJOTSXTFLSZNHZHMYXJQV5BV4O","short_pith_number":"pith:MJOTSXTF","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"},"canonical_sha256":"625d395e655cb2d3e4ecc5d30af435e3813467d35b5c90d1155884ca45a0ec8a","source":{"kind":"arxiv","id":"2103.03116","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03116","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03116v1","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03116","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"pith_short_12","alias_value":"MJOTSXTFLSZN","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"pith_short_16","alias_value":"MJOTSXTFLSZNHZHM","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"pith_short_8","alias_value":"MJOTSXTF","created_at":"2026-07-05T02:20:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MJOTSXTFLSZNHZHMYXJQV5BV4O","target":"record","payload":{"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"},"canonical_sha256":"625d395e655cb2d3e4ecc5d30af435e3813467d35b5c90d1155884ca45a0ec8a","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"},"source_kind":"arxiv","source_id":"2103.03116","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:20:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUeMHYoWLrDsBU3aH1Hsar8dYMidWHIWQbF4CsrMnBRt/8GuX7UwHV6qD+rFAv3zUoiDjrbSj6o+7G2fO88RDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:49:09.976754Z"},"content_sha256":"753fe9085aa069398223a66a26a71444d56679d4d4ed6f207ae8e797d622b734","schema_version":"1.0","event_id":"sha256:753fe9085aa069398223a66a26a71444d56679d4d4ed6f207ae8e797d622b734"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MJOTSXTFLSZNHZHMYXJQV5BV4O","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:20:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mRB51CdAwGy1pT/vvwB8jw8kt8siJl05CTrxec8EwgMSMiWpc9nFyRA0aqoBZJu66bjQTraNpgM8N5LXo6PMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:49:09.977578Z"},"content_sha256":"d76a0430c30bf485be1a4a831b2a398f503a7efdc82199e240934b82226dd009","schema_version":"1.0","event_id":"sha256:d76a0430c30bf485be1a4a831b2a398f503a7efdc82199e240934b82226dd009"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/bundle.json","state_url":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T01:49:09Z","links":{"resolver":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O","bundle":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/bundle.json","state":"https://pith.science/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJOTSXTFLSZNHZHMYXJQV5BV4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MJOTSXTFLSZNHZHMYXJQV5BV4O","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9b610148104cfd6bb426a369a82bfec4697dd5ea631fa4dc6cd3a5e084250003","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T15:39:25Z","title_canon_sha256":"2b19c996ac7c424a347ae861ad8abd3d24492b5377c309dde54284e3d2a8cfd8"},"schema_version":"1.0","source":{"id":"2103.03116","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03116","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03116v1","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03116","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"pith_short_12","alias_value":"MJOTSXTFLSZN","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"pith_short_16","alias_value":"MJOTSXTFLSZNHZHM","created_at":"2026-07-05T02:20:24Z"},{"alias_kind":"pith_short_8","alias_value":"MJOTSXTF","created_at":"2026-07-05T02:20:24Z"}],"graph_snapshots":[{"event_id":"sha256:d76a0430c30bf485be1a4a831b2a398f503a7efdc82199e240934b82226dd009","target":"graph","created_at":"2026-07-05T02:20:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.03116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"George Karypis, Hoan Nguyen, Linfeng Liu, Srinivasan Sengamedu","cross_cats":["cs.AI","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T15:39:25Z","title":"Universal Representation for Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03116","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:753fe9085aa069398223a66a26a71444d56679d4d4ed6f207ae8e797d622b734","target":"record","created_at":"2026-07-05T02:20:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9b610148104cfd6bb426a369a82bfec4697dd5ea631fa4dc6cd3a5e084250003","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T15:39:25Z","title_canon_sha256":"2b19c996ac7c424a347ae861ad8abd3d24492b5377c309dde54284e3d2a8cfd8"},"schema_version":"1.0","source":{"id":"2103.03116","kind":"arxiv","version":1}},"canonical_sha256":"625d395e655cb2d3e4ecc5d30af435e3813467d35b5c90d1155884ca45a0ec8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"625d395e655cb2d3e4ecc5d30af435e3813467d35b5c90d1155884ca45a0ec8a","first_computed_at":"2026-07-05T02:20:24.433868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:24.433868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sLFwkWQYh9jZZ2cqqT50HIkvW3kO0P8eZV7OLrAw7HsNfMLhd30SS1K10HJXLydwstbe32pA0G381PZMJaxkCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:24.434298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03116","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:753fe9085aa069398223a66a26a71444d56679d4d4ed6f207ae8e797d622b734","sha256:d76a0430c30bf485be1a4a831b2a398f503a7efdc82199e240934b82226dd009"],"state_sha256":"a942ff0f485ed840f459b298d12dcf6dd26723f013a265ff5befa1ab34165a62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x7xMVnOzPZahY2r81kejzfI3nHbeX1sFULpXZ6ykO90KFShyhrktH7xWKhdtw+8sGO3uCiNc4AqATiyURlRjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:49:09.982325Z","bundle_sha256":"d2279baa5fcd683c0b2dd50575ed0ded3f544526c2c9fcaaa18052bcdc2fd9f7"}}