{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FE44HQT7DCVRHELSPDM34XTVK7","short_pith_number":"pith:FE44HQT7","canonical_record":{"source":{"id":"2002.08155","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T13:09:07Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"dcc98ef73bcf2fdc08bfb8456dd7191878c3a6337f6fc973922706a1e8de2b28","abstract_canon_sha256":"937311bb63373b974595d7c96bcc6e31e587fa62a288b4637e91076b27f03c5f"},"schema_version":"1.0"},"canonical_sha256":"2939c3c27f18ab13917278d9be5e7557daaf9d7a67a2cbced1bcb4af66f80219","source":{"kind":"arxiv","id":"2002.08155","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08155","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08155v4","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08155","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_12","alias_value":"FE44HQT7DCVR","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_16","alias_value":"FE44HQT7DCVRHELS","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_8","alias_value":"FE44HQT7","created_at":"2026-07-05T01:36:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FE44HQT7DCVRHELSPDM34XTVK7","target":"record","payload":{"canonical_record":{"source":{"id":"2002.08155","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T13:09:07Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"dcc98ef73bcf2fdc08bfb8456dd7191878c3a6337f6fc973922706a1e8de2b28","abstract_canon_sha256":"937311bb63373b974595d7c96bcc6e31e587fa62a288b4637e91076b27f03c5f"},"schema_version":"1.0"},"canonical_sha256":"2939c3c27f18ab13917278d9be5e7557daaf9d7a67a2cbced1bcb4af66f80219","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:16.364825Z","signature_b64":"WVaLldR5szT+rFo1tnLa2xlIzgWZbhifPJlk+8zquAKO4g5d35Ai7WYUb5FvYphAU6QkVyGxq5AUuPl7sQTICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2939c3c27f18ab13917278d9be5e7557daaf9d7a67a2cbced1bcb4af66f80219","last_reissued_at":"2026-07-05T01:36:16.364235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:16.364235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.08155","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:36:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nqi9VkJU6RLn1qtzt6V1dkIsizhsZ5XxBoHb7LGp7OHGsYu780jI14iOp39JNGX2sZxtbaEAB1dNGnAT7fAnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:13:48.632353Z"},"content_sha256":"c63b2a356f045554438f1a1487ff72b9226ce35a2ccedf7b890b4ba30dfcd9e8","schema_version":"1.0","event_id":"sha256:c63b2a356f045554438f1a1487ff72b9226ce35a2ccedf7b890b4ba30dfcd9e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FE44HQT7DCVRHELSPDM34XTVK7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CodeBERT is a pre-trained bimodal model for natural language and code that uses replaced token detection to learn transferable representations.","cross_cats":["cs.PL"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Daxin Jiang, Daya Guo, Duyu Tang, Linjun Shou, Ming Gong, Ming Zhou, Nan Duan, Ting Liu, Xiaocheng Feng, Zhangyin Feng","submitted_at":"2020-02-19T13:09:07Z","abstract_excerpt":"We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code documentation generation, etc. We develop CodeBERT with Transformer-based neural architecture, and train it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators. This enables us to utilize both bimodal data of NL-PL pairs and unimodal data, wher"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the hybrid objective combining replaced token detection with bimodal NL-PL pairs and unimodal data produces general-purpose representations that transfer effectively to downstream tasks without the full paper's experimental details.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CodeBERT pre-trains a bimodal model on code and text pairs plus unimodal data to achieve state-of-the-art results on natural language code search and code documentation generation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CodeBERT is a pre-trained bimodal model for natural language and code that uses replaced token detection to learn transferable representations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6fd8e5065fc5d0269436050e5d974d9498d5e4eacb64771a1876e184ab0f84e7"},"source":{"id":"2002.08155","kind":"arxiv","version":4},"verdict":{"id":"83cc0011-e922-4346-a4e9-25cceee41868","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T20:59:34.348781Z","strongest_claim":"Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks.","one_line_summary":"CodeBERT pre-trains a bimodal model on code and text pairs plus unimodal data to achieve state-of-the-art results on natural language code search and code documentation generation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the hybrid objective combining replaced token detection with bimodal NL-PL pairs and unimodal data produces general-purpose representations that transfer effectively to downstream tasks without the full paper's experimental details.","pith_extraction_headline":"CodeBERT is a pre-trained bimodal model for natural language and code that uses replaced token detection to learn transferable representations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.08155/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":283,"sample":[{"doi":"","year":null,"title":"Advances in neural information processing systems , pages=","work_id":"0918de7c-da6a-4b90-a9b3-364e4087832d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"Proceedings of the 20th international conference on Computational Linguistics , pages=","work_id":"7691780c-dc7e-4deb-ac8c-2f12ab6ae0ab","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2002,"title":"Proceedings of the 40th annual meeting on association for computational linguistics , pages=","work_id":"619ec8ee-e0b4-4db2-a8f6-269c5e3ea698","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"URL https://s3-us-west-2","work_id":"15ee8fa0-4184-4f1a-99b6-0e34e227bb79","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"BioBERT: a pre-trained biomedical language repre- sentationmodelforbiomedicaltextmining","work_id":"4e684b3a-3a5b-48bb-b461-98435ffaf313","ref_index":8,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":283,"snapshot_sha256":"4a081985298087f2aa6a940197be472a80ff7a5fee303b42a60b1d4f8ce8b73e","internal_anchors":11},"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":"83cc0011-e922-4346-a4e9-25cceee41868"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:36:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzCXa8tuGmib3R9+AZQiWwtoFfDrDHQFzY14LbIosB9Tm4whI+HDaVWypDlM7HilvUV+c8n0IbNu7rwdiAjLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:13:48.633132Z"},"content_sha256":"4e927cca3b4aad11735f525d6d06d22cec1f6ee878617aab0eea73bcd303465c","schema_version":"1.0","event_id":"sha256:4e927cca3b4aad11735f525d6d06d22cec1f6ee878617aab0eea73bcd303465c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FE44HQT7DCVRHELSPDM34XTVK7/bundle.json","state_url":"https://pith.science/pith/FE44HQT7DCVRHELSPDM34XTVK7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FE44HQT7DCVRHELSPDM34XTVK7/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":"2026-08-05T17:13:48Z","links":{"resolver":"https://pith.science/pith/FE44HQT7DCVRHELSPDM34XTVK7","bundle":"https://pith.science/pith/FE44HQT7DCVRHELSPDM34XTVK7/bundle.json","state":"https://pith.science/pith/FE44HQT7DCVRHELSPDM34XTVK7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FE44HQT7DCVRHELSPDM34XTVK7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FE44HQT7DCVRHELSPDM34XTVK7","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":"937311bb63373b974595d7c96bcc6e31e587fa62a288b4637e91076b27f03c5f","cross_cats_sorted":["cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T13:09:07Z","title_canon_sha256":"dcc98ef73bcf2fdc08bfb8456dd7191878c3a6337f6fc973922706a1e8de2b28"},"schema_version":"1.0","source":{"id":"2002.08155","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08155","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08155v4","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08155","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_12","alias_value":"FE44HQT7DCVR","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_16","alias_value":"FE44HQT7DCVRHELS","created_at":"2026-07-05T01:36:16Z"},{"alias_kind":"pith_short_8","alias_value":"FE44HQT7","created_at":"2026-07-05T01:36:16Z"}],"graph_snapshots":[{"event_id":"sha256:4e927cca3b4aad11735f525d6d06d22cec1f6ee878617aab0eea73bcd303465c","target":"graph","created_at":"2026-07-05T01:36:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the hybrid objective combining replaced token detection with bimodal NL-PL pairs and unimodal data produces general-purpose representations that transfer effectively to downstream tasks without the full paper's experimental details."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CodeBERT pre-trains a bimodal model on code and text pairs plus unimodal data to achieve state-of-the-art results on natural language code search and code documentation generation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CodeBERT is a pre-trained bimodal model for natural language and code that uses replaced token detection to learn transferable representations."}],"snapshot_sha256":"6fd8e5065fc5d0269436050e5d974d9498d5e4eacb64771a1876e184ab0f84e7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.08155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code documentation generation, etc. We develop CodeBERT with Transformer-based neural architecture, and train it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators. This enables us to utilize both bimodal data of NL-PL pairs and unimodal data, wher","authors_text":"Bing Qin, Daxin Jiang, Daya Guo, Duyu Tang, Linjun Shou, Ming Gong, Ming Zhou, Nan Duan, Ting Liu, Xiaocheng Feng, Zhangyin Feng","cross_cats":["cs.PL"],"headline":"CodeBERT is a pre-trained bimodal model for natural language and code that uses replaced token detection to learn transferable representations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T13:09:07Z","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages"},"references":{"count":283,"internal_anchors":11,"resolved_work":283,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Advances in neural information processing systems , pages=","work_id":"0918de7c-da6a-4b90-a9b3-364e4087832d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Proceedings of the 20th international conference on Computational Linguistics , pages=","work_id":"7691780c-dc7e-4deb-ac8c-2f12ab6ae0ab","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Proceedings of the 40th annual meeting on association for computational linguistics , pages=","work_id":"619ec8ee-e0b4-4db2-a8f6-269c5e3ea698","year":2002},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":7,"title":"URL https://s3-us-west-2","work_id":"15ee8fa0-4184-4f1a-99b6-0e34e227bb79","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":8,"title":"BioBERT: a pre-trained biomedical language repre- sentationmodelforbiomedicaltextmining","work_id":"4e684b3a-3a5b-48bb-b461-98435ffaf313","year":1901}],"snapshot_sha256":"4a081985298087f2aa6a940197be472a80ff7a5fee303b42a60b1d4f8ce8b73e"},"source":{"id":"2002.08155","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-13T20:59:34.348781Z","id":"83cc0011-e922-4346-a4e9-25cceee41868","model_set":{"reader":"grok-4.3"},"one_line_summary":"CodeBERT pre-trains a bimodal model on code and text pairs plus unimodal data to achieve state-of-the-art results on natural language code search and code documentation generation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CodeBERT is a pre-trained bimodal model for natural language and code that uses replaced token detection to learn transferable representations.","strongest_claim":"Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks.","weakest_assumption":"That the hybrid objective combining replaced token detection with bimodal NL-PL pairs and unimodal data produces general-purpose representations that transfer effectively to downstream tasks without the full paper's experimental details."}},"verdict_id":"83cc0011-e922-4346-a4e9-25cceee41868"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c63b2a356f045554438f1a1487ff72b9226ce35a2ccedf7b890b4ba30dfcd9e8","target":"record","created_at":"2026-07-05T01:36:16Z","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":"937311bb63373b974595d7c96bcc6e31e587fa62a288b4637e91076b27f03c5f","cross_cats_sorted":["cs.PL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T13:09:07Z","title_canon_sha256":"dcc98ef73bcf2fdc08bfb8456dd7191878c3a6337f6fc973922706a1e8de2b28"},"schema_version":"1.0","source":{"id":"2002.08155","kind":"arxiv","version":4}},"canonical_sha256":"2939c3c27f18ab13917278d9be5e7557daaf9d7a67a2cbced1bcb4af66f80219","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2939c3c27f18ab13917278d9be5e7557daaf9d7a67a2cbced1bcb4af66f80219","first_computed_at":"2026-07-05T01:36:16.364235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:16.364235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WVaLldR5szT+rFo1tnLa2xlIzgWZbhifPJlk+8zquAKO4g5d35Ai7WYUb5FvYphAU6QkVyGxq5AUuPl7sQTICg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:16.364825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.08155","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c63b2a356f045554438f1a1487ff72b9226ce35a2ccedf7b890b4ba30dfcd9e8","sha256:4e927cca3b4aad11735f525d6d06d22cec1f6ee878617aab0eea73bcd303465c"],"state_sha256":"f3c83c73d5a721e19f0583375f3c7cf4e554b276ebdaecb38f42939dbdc6406c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ioAYFaOHDFqMhycIZQIWiep0C++2QWwxsaNokPTwt/VSvFV3sd7qyc6C6+U3EfmMIKv+OpsXwV+uDcStqkRCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:13:48.637933Z","bundle_sha256":"71383baeebc4e043e1a0a00b96abf8c7d63372925fe7cb79d36fdd6540d06eeb"}}