{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZQWDS6XK3BPJL7RVM2QANK6W2A","short_pith_number":"pith:ZQWDS6XK","canonical_record":{"source":{"id":"2212.06742","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-13T17:21:44Z","cross_cats_sorted":["cs.LG","cs.PL","cs.SE"],"title_canon_sha256":"34c4eb2d8897bbeb4e9413a4f5298b1be681538ac9f385910763ed7c24578a6d","abstract_canon_sha256":"2753945b36b0b35e817997b12f28a9ca5402ea1bbbbb922638ef5635e96a5b3c"},"schema_version":"1.0"},"canonical_sha256":"cc2c397aead85e95fe3566a006abd6d02483ae037a101e061367281dc623c720","source":{"kind":"arxiv","id":"2212.06742","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06742","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06742v2","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06742","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZQWDS6XK3BPJ","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZQWDS6XK3BPJL7RV","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZQWDS6XK","created_at":"2026-07-05T06:11:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZQWDS6XK3BPJL7RVM2QANK6W2A","target":"record","payload":{"canonical_record":{"source":{"id":"2212.06742","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-13T17:21:44Z","cross_cats_sorted":["cs.LG","cs.PL","cs.SE"],"title_canon_sha256":"34c4eb2d8897bbeb4e9413a4f5298b1be681538ac9f385910763ed7c24578a6d","abstract_canon_sha256":"2753945b36b0b35e817997b12f28a9ca5402ea1bbbbb922638ef5635e96a5b3c"},"schema_version":"1.0"},"canonical_sha256":"cc2c397aead85e95fe3566a006abd6d02483ae037a101e061367281dc623c720","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:43.941661Z","signature_b64":"SeX16qaeDzdR4G9Qd4IGtq7ux6E9c8u/3o+x78dOsfy8YuKtMvHuWKJD26H03ZltE/v3CnaHJn5ncMBPRqgnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc2c397aead85e95fe3566a006abd6d02483ae037a101e061367281dc623c720","last_reissued_at":"2026-07-05T06:11:43.941250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:43.941250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.06742","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:11:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9i1s21EWtz+N+0cQztGwtskYjOsrPn/7JroUOUyzHMdxbhvw6m6j2bKMRncI20K8L3mItNledzF5VOD8dw8pDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:35:09.850181Z"},"content_sha256":"c796b2c964fe23d572991a5c48f7ab622b31b45572b3bf78dc781799be39d500","schema_version":"1.0","event_id":"sha256:c796b2c964fe23d572991a5c48f7ab622b31b45572b3bf78dc781799be39d500"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZQWDS6XK3BPJL7RVM2QANK6W2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.PL","cs.SE"],"primary_cat":"cs.CL","authors_text":"Chao Pang, Hao Tian, Hua Wu, Shuohuan Wang, Yekun Chai, Yu Sun","submitted_at":"2022-12-13T17:21:44Z","abstract_excerpt":"Software engineers working with the same programming language (PL) may speak different natural languages (NLs) and vice versa, erecting huge barriers to communication and working efficiency. Recent studies have demonstrated the effectiveness of generative pre-training in computer programs, yet they are always English-centric. In this work, we step towards bridging the gap between multilingual NLs and multilingual PLs for large language models (LLMs). We release ERNIE-Code, a unified pre-trained language model for 116 NLs and 6 PLs. We employ two methods for universal cross-lingual pre-training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06742","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/2212.06742/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":"2026-07-05T06:11:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jxcfJGh0NcwNdENUqRm9uVLmXuym2EaSLDNCTobIauT/YGCuXZeB8QuD47pt+5bIvmUgh575sadH/iQgMg9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:35:09.850797Z"},"content_sha256":"cc1d81008484dd2f455484f92f82adb560d10c842affb7f3e223f3bee56ba1c4","schema_version":"1.0","event_id":"sha256:cc1d81008484dd2f455484f92f82adb560d10c842affb7f3e223f3bee56ba1c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQWDS6XK3BPJL7RVM2QANK6W2A/bundle.json","state_url":"https://pith.science/pith/ZQWDS6XK3BPJL7RVM2QANK6W2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQWDS6XK3BPJL7RVM2QANK6W2A/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":"2026-08-20T03:35:09Z","links":{"resolver":"https://pith.science/pith/ZQWDS6XK3BPJL7RVM2QANK6W2A","bundle":"https://pith.science/pith/ZQWDS6XK3BPJL7RVM2QANK6W2A/bundle.json","state":"https://pith.science/pith/ZQWDS6XK3BPJL7RVM2QANK6W2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQWDS6XK3BPJL7RVM2QANK6W2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZQWDS6XK3BPJL7RVM2QANK6W2A","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":"2753945b36b0b35e817997b12f28a9ca5402ea1bbbbb922638ef5635e96a5b3c","cross_cats_sorted":["cs.LG","cs.PL","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-13T17:21:44Z","title_canon_sha256":"34c4eb2d8897bbeb4e9413a4f5298b1be681538ac9f385910763ed7c24578a6d"},"schema_version":"1.0","source":{"id":"2212.06742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06742","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06742v2","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06742","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZQWDS6XK3BPJ","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZQWDS6XK3BPJL7RV","created_at":"2026-07-05T06:11:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZQWDS6XK","created_at":"2026-07-05T06:11:43Z"}],"graph_snapshots":[{"event_id":"sha256:cc1d81008484dd2f455484f92f82adb560d10c842affb7f3e223f3bee56ba1c4","target":"graph","created_at":"2026-07-05T06:11:43Z","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/2212.06742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Software engineers working with the same programming language (PL) may speak different natural languages (NLs) and vice versa, erecting huge barriers to communication and working efficiency. Recent studies have demonstrated the effectiveness of generative pre-training in computer programs, yet they are always English-centric. In this work, we step towards bridging the gap between multilingual NLs and multilingual PLs for large language models (LLMs). We release ERNIE-Code, a unified pre-trained language model for 116 NLs and 6 PLs. We employ two methods for universal cross-lingual pre-training","authors_text":"Chao Pang, Hao Tian, Hua Wu, Shuohuan Wang, Yekun Chai, Yu Sun","cross_cats":["cs.LG","cs.PL","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-13T17:21:44Z","title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06742","kind":"arxiv","version":2},"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:c796b2c964fe23d572991a5c48f7ab622b31b45572b3bf78dc781799be39d500","target":"record","created_at":"2026-07-05T06:11:43Z","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":"2753945b36b0b35e817997b12f28a9ca5402ea1bbbbb922638ef5635e96a5b3c","cross_cats_sorted":["cs.LG","cs.PL","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-13T17:21:44Z","title_canon_sha256":"34c4eb2d8897bbeb4e9413a4f5298b1be681538ac9f385910763ed7c24578a6d"},"schema_version":"1.0","source":{"id":"2212.06742","kind":"arxiv","version":2}},"canonical_sha256":"cc2c397aead85e95fe3566a006abd6d02483ae037a101e061367281dc623c720","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc2c397aead85e95fe3566a006abd6d02483ae037a101e061367281dc623c720","first_computed_at":"2026-07-05T06:11:43.941250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:43.941250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SeX16qaeDzdR4G9Qd4IGtq7ux6E9c8u/3o+x78dOsfy8YuKtMvHuWKJD26H03ZltE/v3CnaHJn5ncMBPRqgnCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:43.941661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.06742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c796b2c964fe23d572991a5c48f7ab622b31b45572b3bf78dc781799be39d500","sha256:cc1d81008484dd2f455484f92f82adb560d10c842affb7f3e223f3bee56ba1c4"],"state_sha256":"3d151677d631dd4233025fd98da0a335968c17e8587ddbff5e59159e82647893"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o4oKwOIB7f2sL1lsgL6qb3v2foAqy5M/pLX9XfwF6pCZxbsHP2hRIshp2hgIui3wfkG8vK69jsH9TwqhKN2pDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T03:35:09.855110Z","bundle_sha256":"ba19809d361da9dc2cfc9cc25e04ddefd1fc5b1ef7c71fdac05cc3c9f467ba1c"}}